The present invention relates to a technique for grasping the number of occupants of the vehicle.
BACKGROUND
[0002]
　There is a need that you want to know the number of occupants of the vehicle. For example, in Europe, HOV such (High-Occupancy Vehicle) lane and HOT (High-Occupancy Toll) lanes, there are lanes that appeared number is preferential is more than a predetermined number of the vehicle, the vehicle traveling such lanes there is a need that you want to know the number of occupants.
[0003]
　The contrast needs, for example, a technique as described in Patent Document. The following Patent Document 1 and Patent Document 2, it acquires an image including a vehicle as an object by installing the imaging device to the side of the road, by analyzing the image, a technique for detecting the number of occupants of the vehicle is disclosed there.
CITATION
Patent Document
[0004]
Patent Document 1: WO 2014/064898 Patent
Patent Document 2: International Publication No. WO 2014/061195
Summary of the Invention
Problems that the Invention is to Solve
[0005]
　In conventional systems, in order to detect an occupant of a vehicle in a road having a plurality of lanes, it is necessary to install the individual lanes dedicated camera. However, in view of the constraints and system installation costs of installation environments, installation space for equipment, techniques to cover a plurality of lanes in one camera it is desired. However, if you try to cover a plurality of lanes in one camera, not aligned camera focus for some or all of the plurality of lanes, blurred outline of the subject (the vehicle and the occupant of the vehicle) sister, there is a problem that can not be accurately detect the number of occupants.
[0006]
　An object of the present invention is to provide a technique that makes it possible to detect the number of occupants of a vehicle using images one camera taken as an object a plurality of lanes.
Means for Solving the Problems
[0007]
　According to the present invention,
　the image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, the object caught on the image using the parameters corresponding to the position where the vehicle is traveling blur by executing the correction processing for reducing an image correction means for generating a corrected image based on the image,
　and counting means, for counting the number of occupants of the vehicle using the corrected image
　occupant speed detection system comprising the It is provided.
[0008]
　According to the present invention,
　the computer,
　the image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, caught on the image using the parameters corresponding to the position where the vehicle is traveling by executing the correction processing for reducing blur of a subject, it generates a corrected image based on the image,
　and counts the number of occupants of the vehicle using the correction image,
　the number of passengers detection method comprising it is provided .
[0009]
　According to the present invention, the computer program for executing the passenger number detecting method described above is provided.
The invention's effect
[0010]
　According to the present invention, it is possible to detect the number of occupants of a vehicle using images one camera taken as an object a plurality of lanes.
BRIEF DESCRIPTION OF THE DRAWINGS
[0011]
　Above objects, and other objects, features and advantages, preferred embodiments described below, and become more apparent from the following drawings associated therewith.
[0012]
FIG. 1 is a block diagram conceptually showing the functional configuration of the passenger number detecting system of the first embodiment.
2 is a diagram conceptually showing the system configuration of the passenger number detecting system.
[Figure 3] is a diagram showing a hardware configuration of the passenger number detecting system in a simplified manner, is a block diagram conceptually showing the hardware configuration of the information processing apparatus.
4 is a flowchart illustrating a flow of processing in the passenger number detecting system of the first embodiment.
[5] image correction unit is a diagram showing an example of a table used in determining the parameters for correction process.
It is a diagram illustrating an example of a screen for outputting the FIG. 6 passenger counts results by the counting unit.
7 is a diagram conceptually illustrating the configuration of the first embodiment.
8 is a diagram conceptually illustrating a second specific example.
9 is a diagram showing an example of a vehicle coordinate system set on the generated correction images from the image correcting unit
[10] block diagram conceptually showing the functional configuration of the passenger number detecting system of the second embodiment it is.
11 is a flowchart illustrating a flow of processing in the passenger number detecting system of the first embodiment.
12 is a flowchart illustrating the flow of processing in the passenger number detecting system of the first embodiment.
13 is a diagram showing an example of a table in association with each lane to adjust the time zone and focus.
14 is a diagram conceptually showing another system configuration of the passenger number detecting system.
DESCRIPTION OF THE INVENTION
[0013]
　Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the drawings, like numerals represent like components, the explanation will be appropriately omitted. Further, unless otherwise particularly stated, in each block diagram, each block is not a configuration of the hardware units, representing an arrangement of functional units.
[0014]
　[First Embodiment]
　[Functional Configuration]
　FIG. 1 is a block diagram conceptually showing the functional configuration of the passenger number detecting system 1 of the first embodiment. As shown in FIG. 1, the passenger number detecting system 1 includes an imaging unit 110, image correction unit 120 and the count unit 130.
[0015]
　Imaging unit 110 is an imaging device such as a camera. Imaging unit 110 takes an image of the vehicle traveling on the road having a plurality of lanes, and generates an image including the occupant of the vehicle and the vehicle as a subject. Imaging unit 110 is, for example, by interlocking with the sensor for vehicle detection, not shown, it can be included vehicle imaging range. The imaging unit 110, in order to accurately allow grasp the number of occupants of the vehicle may be configured to generate a plurality of images by imaging the continuous vehicle at a predetermined frame rate.
[0016]
　Image correcting unit 120 obtains an image generated by the imaging unit 110. Then, the image correction unit 120 subjects the image generated by the imaging unit 110, executes the correction processing for reducing blur of a subject caught on image to generate a corrected image based on the image. This correction process is a process using a so-called blur correction (Deblur) technology, for example, it can be realized by utilizing the following references [1] and [2] techniques disclosed or the like. By using the techniques disclosed in the following literature, the image correction unit 120, for example, it is possible to correct motion blur blur and the subject of the object due to the deviation of the focus (the traveling direction of the vibration of the vehicle).
　[1] TSUMURAYA, F., MIURA, N., AND BABA, N. 1994. Iterative Blind Deconvolution Method Using Lucy'S Algorithm. Astron. Astrophys. 282, 2 (Feb), 699-708.
　[2] Hradis Michal, Kotera Jan, Zemcik Pavel and Sroubek Filip, Convolutional Neural Networks for Direct Text Deblurring, Proceedings of BMVC 2015, Swansea, the British Machine Vision Association and Society for Pattern Recognition, 2015, ISBN 1-901725-53-7.
　the correction process it is performed using the parameters corresponding to the position where the vehicle is subject image travels. This parameter, depth of correction for the image is determined.
[0017]
　Counting unit 130 uses the corrected image generated by the image correction unit 120 counts the number of occupants of a vehicle which is subject of the corrected image. Counting unit 130 is, for example, by utilizing the technique disclosed in Patent Document 1 or Patent Document 2, on the basis of the image including the vehicle as a subject, it is possible to count the number of occupants of the vehicle. By combining the image correction unit 120 and the counting unit 130 may also be referred to as an image processing unit.
[0018]
　Above, the passenger number detecting system 1 according to the present invention is not provided with the imaging unit 110 such as a camera for each lane. In this case, in some or all of the lanes of the plurality of lanes not match the focus of the imaging unit 110 relative to the object during traveling (vehicle and occupant), possible thereby completed the image in a state the subject is blurred there is sex. Therefore, as described in the present embodiment, by using the parameters corresponding to the position where the vehicle is traveling, the correction processing for reducing blur of a subject is performed. Thus, the subject had blurring become clear by away from the focal length of the imaging unit 110. Note that the correction processing for reducing blur of a subject, for example, high-precision processing enough available for personal authentication is not necessary, the degree of accuracy that can determine other regions with a person (e.g., a face portion of a person) if it is the collateral is sufficient. Then, thus using the corrected image, counting the number of passengers of the vehicle included in the image as a subject is performed. With this configuration, as for a plurality of lanes on a single imaging apparatus, it is possible to detect the number of occupants of the vehicle. Also, reducing the number of imaging devices required by the system, the effect of relaxing the constraints of the installation environment (for example, the land size, etc.), and also expected effect of reducing the cost of the system.
[0019]
　Hereinafter, a first embodiment will be described in more detail.
[0020]
　[Hardware Configuration]
　functional components of the occupant number detecting system 1, the hardware for realizing each functional configuration unit: may be realized by (eg hard such as a wired electronic circuitry), hardware and software combination of: may be implemented in (example combinations such as electronic circuits and programs for controlling it). Hereinafter, the case where the functional structure of the occupant number detecting system 1 is realized by a combination of hardware and software will be further described.
[0021]
　Figure 2 is a diagram conceptually showing the system configuration of the passenger number detecting system 1. As shown in FIG. 2, the passenger number detecting system 1, the information processing apparatus 20, the image pickup apparatus 30 configured vehicle detection sensor 40, and includes a light projector 50. Further, the information processing apparatus 20, a display device 22 for displaying the count result of the number of passengers by the counting unit 130 is connected.
[0022]
　Imaging device 30 is equivalent to the imaging unit 110 of the passenger number detecting system 1. Imaging device 30 is connected to the information processing apparatus 20 via the network. Incidentally although not shown, a plurality of imaging devices 30 installed in different locations, each may be connected to the information processing apparatus 20.
[0023]
　Vehicle detection sensor 40 is a sensor for (for measuring the timing of taking the image) for detecting the vehicle V to be passed through the front of the imaging device 30. Vehicle detection sensor 40 may be provided separately from the imaging device 30 may be incorporated in the imaging device 30.
[0024]
　Projector 50 is provided to clearly photograph the person in the vehicle. Emitter 50 may be provided separately from the imaging device 30 may be incorporated in the imaging device 30. Projector 50, in conjunction with the imaging timing of the imaging device 30 is irradiated to the vehicle V as an object light (e.g., infrared, etc.). In passenger number detecting system 1, to the common emitter 50 at a plurality of lanes may be provided one, it may be provided with a dedicated light projector 50 to each of the plurality of lanes. In the latter case, may be controlled so that all of the projector 50 in response to the vehicle V is detected by the vehicle detection sensor 40 irradiates light, until the vehicle V measured by the vehicle detection sensor 40 it may be controlled so that the projector 50 of the lanes corresponding to the distance is irradiated with light.
[0025]
　Figure 3 is a block diagram conceptually showing the hardware configuration of the information processing apparatus 20. The information processing apparatus 20 is configured bus 201, processor 202, memory 203, storage device 204, input and output interface 205, and includes a network interface 206.
[0026]
　Bus 201, a processor 202, memory 203, storage device 204, input and output interface 205 and the network interface 206, is a data transmission path for transmitting and receiving data with each other. However, processor 202, memory 203, storage device 204, how to connect input and output interface 205, and the network interface 206 and the like each other is not limited to the bus connection.
[0027]
　Processor 202 is an arithmetic unit such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). Memory 203, RAM (Random Access Memory) or a ROM (Read Only Memory) which is a main storage device which is implemented by using a. The storage device 204, HDD (Hard Disk Drive), SSD (Solid State Drive), an auxiliary storage device which is implemented by using a memory card.
[0028]
　The storage device 204, a program module for realizing the image correction unit 120 and the counting unit 130, and stores a program module for realizing the function of acquiring the image generated by the imaging device 30. Processor 202 by executing these program modules is read into the memory 203, to implement the function corresponding to each program module.
[0029]
　Output interface 205 is an interface for connecting the information processing apparatus 20 and the peripheral device. For example, or an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) device for display output such as a display (display device 22), the device for input such as a keyboard or a mouse, or the touch panel to which they are integrated, It may be connected to the information processing apparatus 20 via the input and output interface 205.
[0030]
　Network interface 206 is an interface for connecting the information processing apparatus 20 to various networks such as LAN (Local Area Network) or WAN (Wide Area Network). As shown in FIG. 2, the information processing apparatus 20 is connected to the network via the network interface 206 can communicate with other terminals that do not imaging device 30 and shown. For example, the information processing apparatus 20 can communicate with the imaging device 30 via the network interface 206, and acquires the image generated by the imaging device 30. In this case, the information processing apparatus 20, the information processing apparatus for the administrator via the network interface 206 (not shown) is communicatively connected. The number of occupants detection result by the counting unit 130 is transmitted to the information processing apparatus for the administrator (not shown). The method for the information processing apparatus 20 is connected to various networks may be a wireless connection, or may be a wired connection.
[0031]
　Note that the configuration of FIG. 2 and FIG. 3 is merely an example, the hardware configuration of the present invention is not limited to the example of FIGS. For example, the information processing apparatus 20 and the imaging device 30 may be integrated.
[0032]
　Operational Example
　with reference to FIG. 4, illustrating the flow of processing in the passenger number detecting system 1 of the first embodiment. Figure 4 is a flowchart illustrating a flow of processing in the passenger number detecting system 1 of the first embodiment.
[0033]
　First, the imaging unit 110 images the vehicle traveling road, and generates an image including the vehicle as a subject (S102). The imaging unit 110 includes, for example, can be based on the output signal from the vehicle detection sensor 40 detects the presence of a vehicle attempting to pass through the front of the imaging unit 110, determines the timing of taking the image .
[0034]
　Then, the image correcting unit 120 determines parameters used in the correction process for the image generated in the process of S102 (S104).
[0035]
　Image correction unit 120, for example, the vehicle based on the output signal from the distance measuring means for measuring a distance to a vehicle (not shown) (information indicating the distance to the vehicle) are included as a subject in the image identify traveling to that lane, it is possible to determine the parameters used in the correction process. In this case, the image correction unit 120 may use a vehicle detection sensor 40 as described above for the distance measuring means. Furthermore, provided as the distance measuring means such as a separate distance sensor for measuring the distance to the vehicle and the vehicle detection sensor 40, the image correction unit 120 uses the output signal from the distance sensor, the vehicle is traveling lane it may be identified. Is not particularly limited, as an example, the image correction unit 120, the distance the vehicle identifies the lane the vehicle is traveling by reference to a table as shown in FIG. 5 on the basis of the distance measured by the measuring means, the correction process it is possible to determine the parameters to use.
[0036]
　Figure 5 is a diagram showing an example of a table used when the image correction unit 120 determines the parameters for correction process. In Figure 5, the distance to the vehicle, and information indicating each of the plurality of lanes (lane identification information), and a correction processing parameter is illustrated a table which stores in association with each other. In the example of FIG. 5, it is also possible to use a "distance to the vehicle" itself instead of the lane identification information. In this case, "lane identifying information" as illustrated in Figure 5 may not. Image correcting unit 120, the distance from the distance measuring means to the vehicle indicated by the acquired information to identify the appropriate lines from the table based, it can be read out correction processing parameters stored in the row. As a specific example, the distance from the distance measuring means to the vehicle indicated by the acquired information d 1 or d 2 is less than, the image correction unit 120 identifies the lane in which the vehicle is traveling with the "center lane" , it is possible to read the correction parameter associated with the "center lane".
[0037]
　Besides, the image correcting unit 120, without the vehicle to identify the lane the vehicle is traveling, may determine the parameters according to the distance to the vehicle measured by the distance measuring means. In this case, the image correcting unit 120 obtains information indicating the distance from the distance measuring means to the vehicle, the distance function and to calculate the parameters as arguments, by using a table that stores defining a parameter corresponding to a distance by , it is possible to determine the parameters corresponding to the distance indicated by the information obtained from the distance measuring means.
[0038]
　The image correction unit 120, by analyzing the image generated by the imaging unit 110, determines the degree of blur of the image, it is also possible to determine the parameter corresponding to blurriness of the image. For example, the image correction unit 120 acquires the analysis information of the spatial frequency of the image, it is possible to determine the parameters for the correction based on the information. Is not particularly limited, the image correction unit 120, for example, if the point spread function (Point Spread Function) such blur function representing the nature of the blurring of the image is known, the blurring function of the image in the spatial frequency components by the Fourier transform decompose and, as shown in the following equation can be derived Wiener filter for blurring reduction.
[0039]
[Number 1]

[0040]
　In the above formula, H is shown a Fourier transform of the blurring function image, H * denotes a complex conjugate of the Fourier transform H, gamma represents a constant determined by SN (Signal to Noise) ratio of the image signal. Incidentally, the above formula, for example, is stored in a predetermined storage area such as the memory 203 and storage devices 204, the image correction unit 120 may determine the parameter by reading an expression from the storage area.
[0041]
　Besides, the image correction unit 120, information indicating the shake of the subject is calculated using an autocorrelation function, acquired as information indicating the extent of blurring of the image, it is possible to determine the parameters for correction . In this case, the image correction unit 120 uses a predetermined function to derive a parameter to cancel the shake by substituting the direction and amount of shake of an object in calculable image using an autocorrelation function, correction it can be determined parameters. Note that the function described above, for example, is stored in a predetermined storage area such as the memory 203 and storage devices 204, the image correction unit 120 may determine the parameters by reading the function from the storage area.
[0042]
　Here, when a plurality of vehicles to the image acquired in S102 is included as a subject, the image correction unit 120, using the method as described above for each of the vehicle, the correction process corresponding to the position of each vehicle it is possible to determine the parameters of use. For example, the image containing the two vehicles traveling the different lanes (the first vehicle and the second vehicle) as a subject is generated by the imaging unit 110. In this case, the image correcting unit 120, the lane and a position where the vehicle is traveling, or, depending on the blurriness of each vehicle can be determined as a parameter used for correction processing a plurality of different parameters to each other. Specifically, the image correction unit 120, based on the position where the first vehicle is traveling, with determining a first parameter for reducing the blur of the first vehicle, the second vehicle traveling based on the position, to determine a second parameter for reducing the blur of the second vehicle. Further, when three or more vehicles traveling the different lanes are reflected in the image, the image correcting unit 120 can determine the three or more parameters. Although not particularly limited, the image correction unit 120, the known image processing algorithms for recognizing an object (vehicle) on the image, and the real space from the image feature amount of the vehicle (e.g., the size of the image, etc.) using known image processing algorithms for estimating the position (traveling lane) of the vehicle above, it is possible to a plurality of vehicles traveling in different lanes each of which determines that the image contains. Besides, the image correcting unit 120, by vehicle detection sensor 40 is compared with a timing of detecting a plurality of vehicles, and a timing and an imaging range of the imaging device 30 of the imaging by the imaging device 30 (imaging section 110) , it is possible to determine whether it contains a plurality of vehicles to the image generated by the photographing.
[0043]
　Then, the image correction unit 120, using the parameters determined by the processing S104, the generated image in the process of S102, it executes correction processing for reducing blur of a subject (S106). Here, if a plurality of different parameters in S104 is determined, the image correcting unit 120 performs correction processing on the image acquired in S102 using the respective parameters, a plurality corrected by each parameter to generate an image. For example, in the process of S102, the image including two vehicles traveling the different lanes (first vehicle and the second vehicle) as a subject is acquired. In this case, the image correcting unit 120 performs correction by using one above the first parameter and the second parameter, respectively. Accordingly, the image obtained in the processing in S102 as a base, two correction image (first corrected image and the second corrected image) is generated. In the case where three or more vehicles traveling the different lanes are reflected in the image, the image correction unit 120 may generate three or more corrected image using three or more parameters.
[0044]
　The counting unit 130 processes the corrected image generated by the processing in S106, and counts the number of occupants of the vehicle (S108). Here, the count unit 130, when a plurality of correction images are generated in S106, a plurality of corrected images were processed respectively, counts the number of occupants of the vehicle. For example, in the process of S106, as described above, is an image acquisition comprising two vehicle traveling on the different lanes (first vehicle and the second vehicle) as a subject, a blur of the first vehicle the first correction image with reduced, the second corrected image obtained by reducing the blur in the second vehicle is generated. In this case, count section 130 can count with the number of occupants of the second vehicle with the second corrected image and counts the number of occupants of the first vehicle using the first corrected image. In the case where three or more vehicles traveling the different lanes are reflected in the image, the image correcting unit 120 uses three or more corrected image, respectively, to the number of occupants of the vehicles counted, respectively can.
[0045]
　The counting unit 130 outputs the result of counting the number of occupants of the vehicle (S110). For example, the count unit 130 may display a screen as shown in FIG. 6 on the display device 22 connected to the information processing apparatus 20.
[0046]
　Figure 6 is a diagram illustrating an example of a screen for outputting the number of occupants of the count result by the counter unit 130. In Figure 6, the number of vehicle license plate, a screen for displaying the number of occupants of counted vehicle counting unit 130 is illustrated. Incidentally, license plate number of the vehicle, captured by another imaging device that is not the image pickup section 110 or illustrated, by analyzing the image number plate of the vehicle is captured, it can be obtained as such as text information.
[0047]
　Here, the count unit 130, a lane HOV lane and HOT lane with the vehicle is traveling, if the number of occupants of the vehicle is less than a prescribed number, the number of occupants information of the vehicle, the number of occupants it may include certain additional information indicating that but is less than the specified number. Counting unit 130 is, for example, information about the specified number stored in advance in the memory 203, the image by comparing the number of occupants of a vehicle count based on, whether or not the number of passengers of the vehicle is defined persons or it is possible to determine. Then, the information processing apparatus 20, for example, by applying a predetermined mark M as shown in FIG. 6 according to the presence or absence of additional information, information about the vehicle speed occupant is less than the specified is distinguished from information relating to other vehicles Display it may be configured to. Besides, the information processing device 20, by changing the characters and background colors in accordance with the presence or absence of additional information, that the number of passenger information about the vehicle is lower than the specified, be displayed differently from information about other vehicles it can. According to such a screen, the administrator of the presence of a vehicle traveling on the HOV lane and HOT lane passenger number less than the predetermined number can be easily grasped. Besides, when the additional information to the passengers count of results output from the counter 130 is given, the information processing apparatus 20 is configured to output a predetermined buzzer sound and updates the display of the screen it may be. Thus, the person operating the information processing apparatus 20, easily notice the presence of a vehicle traveling on the HOV lane and HOT lane passenger number less than the predetermined number.
[0048]
　[Examples]
　Hereinafter, specific examples of the passenger number detecting system 1 of the present embodiment.
[0049]
　
　In a road having a plurality of lanes, the central portion of the focus distance of the image pickup unit 110 a plurality of lanes (e.g., lane boundary if the number of lanes is even, if the number of lanes is odd be fixed to the distance corresponding to the lane) located at the center, since the maximum value of the blur amount of the vehicle caught on the image is suppressed, it is possible to reduce the amount of processing of the overall blur correction process. In this example, for simplicity of description, a road with two lanes, exemplarily for the case that the focus of the imaging unit 110 is fixed to the center portion of the two lanes (e.g., lane boundary line) explain. Figure 7 is a diagram conceptually illustrating the construction in the first embodiment. Hatched area in FIG. 7 shows the focus distance of the image pickup device 30 (imaging section 110) (depth of field DOF). Subject positioned outside the range of the depth of field DOF will be imaged in the blurred state.
[0050]
　In this specific example, for example, been optimized for each of the two lanes, two parameters for the correction processing are prepared in advance in the memory 203. Parameter for correction processing corresponding to each of the two lanes, for example, can be determined based on the difference of the traveling position of the average vehicle in each lane, and the focus distance of the image pickup section 110. Specifically, the parameters of the back side of the lane position relative to the imaging unit 110, cancel the blurring of the image caused by the back side of a position where the position of the object is properly focused (around lane boundary) Parameters It is prepared as. The parameter of the near side of the lane position relative to the imaging unit 110 is provided as a parameter to cancel the blurring of the image caused by in front of the position where the position of the object is properly focused (around lane boundary) that.
[0051]
　For this example, not in focus of the imaging unit 110 in either lane. Therefore, the vehicle even though the vehicle is traveling either lane, there is a possibility that the contour blurs of the subject (the vehicle occupant and the vehicle) in the image generated by the imaging unit 110. However, in this embodiment, as compared with the case where in focus to one of the lanes can blur amount (blurriness) smaller. For example, if the vehicle was traveling a first lane, than when the focus distance of the image capturing section 110 is aligned with the other of the second lane, the central boundary line (i.e., the central portion of the plurality of lanes) who are aligned in the vicinity of the deviation from the focus distance of the imaging unit 110 is reduced. Therefore, as a result, the blur amount of the subject in the image is reduced. This has the advantage that it can be clearly corrected with a small amount of processing the image acquired by the imaging unit 110.
[0052]
　
　In the present embodiment, the focus distance of the image capturing unit 110 will be exemplified case fixed at a distance corresponding to one lane that is predetermined among a plurality of lanes. Specifically, in a road with two lanes, it will be exemplified a case where the focus of the imaging unit 110 is fixed to either one the two lanes. Figure 8 is a diagram conceptually showing the structure of a second embodiment. Hatched region in FIG. 8 shows the focus distance of the image pickup device 30 (imaging section 110) (depth of field DOF). Subject positioned outside the range of the depth of field DOF will be imaged in the blurred state.
[0053]
　In this example, when imaging the vehicles traveling toward the lane focus is fixed, it is possible to obtain a degree clear image, the correction process in many cases may not be executed. On the other hand, when the vehicle traveling towards the lane where the focus is not fixed is imaged is likely to be necessary to correct the process of reducing the blur of the subject. Here, the either fixed focus image pickup unit 110 in either lane, for example, can be determined based on the statistics of the traffic volume of each lane. By fixing the focus of the imaging unit 110 towards the lanes often statistically traffic, reduce the frequency of execution of the correction processing on the image, it is possible to reduce the overall throughput. Further, in this case, the image correction unit 120, when the vehicle traveling lane with a fixed focus image pickup unit 110 is captured, and performs processing to confirm whether the subject (the vehicle occupant or the vehicle) is not blurred . Image correcting unit 120, specifically, for example, by processing as described below, the image can be judged whether or not blurred. As an example, the image correction unit 120, an image generated by the imaging unit 110 as a result of degradation in the spatial frequency components by Fourier transform, when the low frequency component is small high-frequency component is large distribution is obtained, the image but it can be determined that not blurred. As another example, the image correction unit 120, when the half width of the autocorrelation function of the image is below a predetermined threshold, the image can be determined that no blur. As another example, the image correction unit 120, image blurring function (e.g., the point spread function, etc.) As a result of estimating the impulse (i.e., delta functions) or a function of the waveform close to an impulse (half-width is equal to or less than a predetermined threshold value when the function) is obtained, the image can be determined that no blur. The processing of these processes is smaller than the processing amount of the correction processing for reducing blur of a subject. Therefore, the overall amount of processing in this specific example, when performing correction processing on all lanes (e.g., the case of the first embodiment)
[0054]
　In the road having three or more lanes, by fixing the distance corresponding to the lane to position the focus distance of the image capturing unit 110 to the center side, the effect as described in the first embodiment described above to give It is.
[0055]
　
　possibly subject blurred due to the difference in the seat position of the vehicle. For example, the amount of deviation from the focus distance of the image pickup unit 110 in the seating position of the seat position and the passenger seat side of the driver's seat side is different. Then, the amount of deviation of the difference from the focus distance, the subject will vary the contour of the blurriness of (a person in the vehicle). Here, an example is shown of the case to execute the correction process using the parameters this difference into account.
[0056]
　In this specific example, the image correction unit 120 is used for the correction process, parameters corresponding to the position is constituted by a plurality of parameters corresponding to the position of the vehicle. For example, parameters for correction process reduces the first vehicle in the positional parameters for reducing the blur of the subject in the image of the driver's seat side as a reference, the blur of the subject in the image of the front passenger seat side as a reference configured to include a second vehicle in position parameters for the.
[0057]
　In this example, the image correction unit 120, when identifying the lane in which the vehicle is traveling, reads the parameter set (the first vehicle in the position parameter and the second vehicle in position parameter) corresponding to the lane. The parameter set may, for example, stored in the memory 203 and storage devices 204. Then, the image correcting unit 120 performs correction processing on the image by using the read first vehicle in position parameter and the second vehicle in the positional parameters, respectively. Thus, with respect to one image captured at a certain timing, a plurality of correction images based on a plurality of parameters corresponding to the in-vehicle position is generated.
[0058]
　In this example, the count unit 130, by using a plurality of images generated by using the first position parameter and location parameter in the second vehicle in the vehicle described above, respectively, counts the number of occupants of the vehicle.
[0059]
　Specifically, the count unit 130, as follows, it is possible to count the number of occupants of a vehicle using a plurality of correction images. First, the count unit 130, each of the plurality of corrected images generated by correcting for on the basis of the correction parameter corresponding to the position of the vehicle to one image captured at a certain timing, counting the number of occupants to. Next, the count unit 130 integrates counted the number of occupants using each correction image, determines the number of occupants of the final vehicle to be counted from one image. For example, the count unit 130, the result of comparing the position in the respective images for the person detected by the person and another corrected image is detected in a certain one of the corrected image, the position is substantially equal to (multiple correction images the difference between the positions is below a predetermined threshold value is) the case between counts and one and determines these person as the same person. The count unit 130, a result of comparing the position in the respective images for the person detected by the certain one corrected image at the detected person and another corrected image, the position of the person is different (more correcting the difference between the positions between the image exceeds a predetermined threshold), determines these person as different persons, each counted separately.
[0060]
　Although not particularly limited, the image correction unit 120 detects the reference point and a reference direction of the vehicle from a plurality of corrected images each origin detected reference position, and the detected reference direction x-axis and y-axis directions the two-dimensional coordinate system (vehicle coordinate system) determined for each image, it is possible to determine the positional relationship of a person among a plurality of correction images. Hereinafter, an example of a reference point and a reference direction with reference to FIG. Figure 9 is a diagram showing an example of a vehicle coordinate system set on the corrected image F generated by the image correction unit 120. In the illustrated example, the rear end portion of the bumper which is attached to the back of the vehicle body as a reference point, and the reference direction of the longitudinal and height directions of the vehicle. Then, the rear end portion of the bumper is the origin, the longitudinal direction of the vehicle is x-axis, vehicle coordinate system the height direction is y-axis is defined. The reference position and the reference direction is not limited to the illustrated example. For example, the reference point is the front pillar, center pillar, rear pillar, or may be a predetermined portion of such side mirror. The reference direction may be set in any direction on the image. Image correction unit 120 may be in the vehicle coordinate system as shown, identifying the position coordinates of the person area B detected from the image.
[0061]
　In the present embodiment, by performing the correction processing on the image by using a plurality of parameters in consideration of the difference in the seating position in the vehicle, a plurality of corrected image is generated. By doing so, eliminates the outline of the subject is blurred due to the difference in seat position in the vehicle, it is possible to accurately count the number of occupants of the vehicle.
[0062]
　[Second Embodiment]
　In a second specific example of the first embodiment has been described a specific example of fixing the focus of the imaging unit 110 to a predetermined lane. In the present embodiment, further configured will be described with a processing unit that controls the focus of the imaging unit 110 based on a predetermined condition.
[0063]
　[Functional Configuration]
　FIG. 10 is a block diagram conceptually showing the functional configuration of the passenger number detecting system 1 of the second embodiment. As shown in FIG. 10, the passenger number detecting system 1 of the present embodiment, in addition to the configuration of the first embodiment, further comprises a control unit 140.
[0064]
　As an example, the control unit 140, based on the traffic volume of each of the plurality of lanes of a predetermined time, it is possible to switch lanes to focus the imaging unit 110. In this case, the control unit 140, an image generated by the imaging unit 110, or by using a output of the vehicle detection sensor 40, the traffic volume of the predetermined time can be calculated for each lane. As an example, the control unit 140 uses the distance to a vehicle to be measured by using a vehicle detection sensor 40, it is possible to calculate the traffic volume of each lane of the predetermined time as follows. First, the control unit 140, a predetermined table defining the correspondence between the distance and the travel lane to the vehicle: see (Example 5), to identify the lane in which the vehicle is traveling. Then, the control unit 140 stores the number of times each lane has been identified in a predetermined storage area such as memory 203. By continuing these processes for a predetermined time, it is possible to store the information indicating the traffic amount for each lane a predetermined time in a predetermined storage area. As another example, the control unit 140, based on the analysis result of the image generated by an imaging unit 110 may calculate the traffic volume of each lane of the predetermined time. Specifically, the control unit 140, image feature amount of the vehicle (e.g., size, etc. of the image) using known image processing algorithms for estimating the vehicle position in the real space from a (lane), imaging the vehicle traveling lane contained in the image generated by such parts 110 can be identified. Then, the control unit 140, the number of vehicles identified in each lane within a predetermined time by counting each can calculate the traffic volume of each lane of the predetermined time. The predetermined time can be arbitrarily determined.
[0065]
　As another example, the control unit 140 may be configured to switch lanes to focus the imaging unit 110 in accordance with the date or time. Specifically, the change in the traffic volume of each lane on the basis of the results of the investigation beforehand, lanes should adjust the focus for each time period is determined. Then, in a state where information indicating the thus determined lanes attached information and string indicating the time zone, for example, is prepared in the memory 203 or the like. Control unit 140 refers to information provided in the memory 203 after having acquired the current time, an instruction to adjust the focus to the lane corresponding to the current time, can be transmitted to the imaging unit 110.
[0066]
　[Hardware Configuration]
　The hardware configuration of this embodiment, as in the first embodiment: a (of FIG. 2 and FIG. 3). In the present embodiment, the storage device 204 of the information processing apparatus 20 further stores a program module for realizing the functions of the control unit 140 described above. Processor 202 of the information processing apparatus 20 by executing the program module, the function of the control unit 140 described above is realized.
[0067]
　Operational Example
　with reference to FIGS. 11 and 12, the flow of processing of the passenger number detecting system 1 of the present embodiment. 11 and FIG. 12 is a flowchart illustrating a flow of processing in the passenger number detecting system 1 of the first embodiment. In the flowchart of FIG. 11, the control unit 140 based on the traffic volume of a given time each of the plurality of lanes, the flow of controlling the lane to focus the imaging unit 110 are described. Further, in the flowchart of FIG. 12, the control unit 140 is described the flow for controlling the lane to focus the imaging unit 110 in accordance with the date or time.
[0068]
　First, the control unit 140 based on the traffic volume of a given time each of the plurality of lanes, the flow of controlling the lane to focus the imaging unit 110.
[0069]
　First, the control unit 140 obtains information indicating a traffic volume of each lane in the predetermined time (S202). Control unit 140, for example, image analysis results and the imaging unit 110, based on the output signal of the vehicle detection sensor 40, it is possible to aggregate the passage number of the vehicle at predetermined time intervals for each lane. The control unit 140 communicates with an external device (not shown), the traffic volume of each lane at a given time may be acquired from the external device. Then, the control unit 140, acquired in the process of S202, by comparing the traffic volume of each lane at a given time, identifying a busiest lane at a predetermined time (S204). Then, the control unit 140, a control instruction to adjust the focus to the lanes identified in the process of S204, and transmits it to the imaging unit 110 (S206). Imaging unit 110 controls the focus mechanism in accordance with the control instructions from the control unit 140, adjust the focus to the lane indicated by the control instruction (S208).
[0070]
　Next, the flow of control unit 140 controls the lane to focus the imaging unit 110 according to the time zone.
[0071]
　First, the control unit 140 such as to synchronize with unillustrated NTP (Network Time Protocol) server, and acquires the current time (S302). Then, the control unit 140, based on the current time acquired in the process of S302, for example, by referring to the table shown in FIG. 13, identifies the lane to adjust the focus (S304). Figure 13 is a diagram showing an example of a table stored in association with the lanes to align the time zone and focus. For traffic conditions that may be affected in the day of the week or the weather, day of week or more by weather tables may be prepared. Further, for example, traffic is expected to increase in such a long holiday period such Golden Week and Bon timing. Therefore, the table that is used during such long vacations may be further provided. Then, the control unit 140, a control instruction to adjust the focus to the lanes identified in the process of S304, and transmits it to the imaging unit 110 (S306). Imaging unit 110 controls the focus mechanism in accordance with the control instructions from the control unit 140, adjust the focus to the lane indicated by the control instruction (S308). Thereafter, the image of the vehicle traveling each lane is generated by the imaging unit 110, on the image, as described in the second specific example of the first embodiment, the correction processing for reducing blur of a subject it may be executed. At this time, as described in the third specific example of the first embodiment, a plurality of parameter correction processing may be performed using corresponding to the position of the vehicle.
[0072]
　Above, in this embodiment, based on the statistical traffic volume, date or time-specific traffic volume for a predetermined time, the focus of the imaging unit 110 is controlled to match the heavily traveled lane. Thus, lowering the frequency of execution of the correction processing on the image, it is possible to reduce the overall throughput.
[0073]
　Having described embodiments of the present invention with reference to the attached drawings, merely as examples of the present invention, it is also possible to adopt various other configurations. For example, in the embodiments described above, an example in which the imaging device 30 (imaging unit 110) is provided on the roadside, the imaging device 30, as shown in FIG. 14, may be provided, such as the gantry . In this configuration, since the difference in the distance from the imaging device 30 to the vehicle by the lane in which the vehicle is traveling occurs, there is a possibility that the subject objects appear blurred. In this case, as described in the embodiments described above, using the parameters corresponding to the position where the vehicle is traveling, the corrected image by performing the correction processing for reducing blur of a subject object caught on clear by generated, it is possible to accurately count the number of occupants of the vehicle based on the corrected image.
[0074]
　Further, the plurality of flow chart used in the above description, a plurality of steps (processes) are described in order, the execution order of steps performed in each embodiment is not limited to the order of the description. In each embodiment, it is possible to change the order of the steps illustrated where not contents to trouble. Further, each of the embodiments discussed above can be combined to the extent that the content is not inconsistent.
[0075]
　Some or all of the above embodiments, can be described as the following notes, are not limited to.
1.
　The image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, the correction processing for reducing blur of a subject caught on the image using the parameters corresponding to the position where the vehicle is traveling by performing an image correction means for generating a corrected image based on the image,
　and counting means for counting the number of occupants of the vehicle using the corrected image
　occupant speed detection system comprising.
2.
　Wherein the image correction means, when a plurality of vehicles traveling in different lanes in the image is captured, the by performing the correction processing using a first said parameters corresponding to a position in which one of the vehicle is traveling generating one correction image to generate a second corrected image by executing the correction by using a second said parameter of corresponding to the position where the other vehicle runs,
　said counting means, said first counting the number of occupants of the one vehicle using one of the corrected image, and counts the number of occupants of the other vehicle using the second corrected image,
　1. Passenger number detecting system according to.
3.
　The image correcting means determines the parameter based on at least one of information indicating a blur of the subject is calculated using the spatial frequency and the autocorrelation function of the image,
　1. Or 2. Passenger number detecting system according to.
4.
　The image correcting means determines the parameter based on the distance to the vehicle measured by the distance measuring means for measuring the distance to the vehicle,
　1. Or 2. Passenger number detecting system according to.
5.
　A storage unit for storing information and information indicating each of the plurality of lanes and the parameters associated,
　the image correcting unit specifies the lane on which the vehicle is traveling based on the distance to the vehicle , executes the correction process using the parameters corresponding to the lanes identified,
　1. Or 4. Passenger number detecting system according to any one of.
6.
　Focus distance of the imaging means is fixed at a distance corresponding to one lane predetermined among the plurality of lanes,
　1. To 5. Passenger number detecting system according to any one of.
7.
　Focus distance of the imaging means is fixed at a distance corresponding to the central portion of the plurality of lanes,
　1. To 5. Passenger number detecting system according to any one of.
8.
　Wherein the plurality of basis lanes on each of traffic, further comprises control means for switching the lanes to focus of the imaging means,
　1. To 5. Passenger number detecting system according to any one of.
9.
　Further comprising a control means for switching the lanes to focus of the imaging means in accordance with the date or time,
　1. To 5. Passenger number detecting system according to any one of.
10.
　The parameters corresponding to the position includes a plurality of parameters which differ depending on the position in the vehicle,
　wherein the image correcting means, on the image, by using a plurality of parameters which differ depending on the position in the vehicle wherein by executing the correction process, the plurality of generating a corrected image based on the image,
　said counting means counts the number of occupants of the vehicle using the plurality of correction images,
　1. To 9. Passenger number detecting system according to any one of.
11.
　Imaging means for imaging a vehicle traveling on a road having a plurality of lanes,
　the distance measuring means for measuring a distance to the vehicle,
　comprising an image processing means for processing an image generated by the imaging means,
　the image processing means acquires information indicating the distance from the distance measuring means, to reduce the blur of the object caught on the image according to the acquired information, counts the number of occupants of the vehicle with the image,
　number of passengers detection system.
12.
　Computer,
　The image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, the correction processing for reducing blur of a subject caught on the image using the parameters corresponding to the position where the vehicle is traveling by performing, generating a corrected image based on the image,
　and counts the number of occupants of the vehicle using the correction image,
　the number of passengers detection method comprising.
13.
　The computer,
　when a plurality of vehicles traveling in different lanes in the image is captured, the correction processing first by executing with the first said parameters corresponding to a position in which one of the vehicle is traveling to generate a corrected image, to generate a second corrected image by executing the correction by using a second said parameter of corresponding to the position where the other vehicle is traveling,
　by using the first corrected image the counts number of occupants of one vehicle, counts the number of occupants of the other vehicle using the second corrected image,
　12 including that. Passenger number detecting method according to.
14.
　The computer,
　to determine the parameters based on at least one of information indicating a blur of the subject is calculated using the spatial frequency and the autocorrelation function of the image,
　12 including that. Or 13. Passenger number detecting method according to.
15.
　The computer is,
　To determine the parameter based on the distance to the vehicle measured by the distance measuring means for measuring the distance to the vehicle
　12 that comprises. Or 13. Passenger number detecting method according to.
16.
　The computer is
　based on the distance to the vehicle to identify the lane in which the vehicle is traveling, it is associated with information indicating each of the plurality of lanes of the parameters corresponding to the lanes identified with the parameters from the storage unit for storing information, it executes the correction process using the read parameters,
　including the 12. To 15. Passenger number detecting method according to any one of.
17.
　The focus distance of the image pickup means, said being secured in a plurality of distances corresponding to one lane predetermined in lanes
　12 which comprises. To 16. Passenger number detecting method according to any one of.
18.
　Focus distance of the imaging means, the are fixed to a plurality of distances corresponding to the central portion of the lane,
　12 including that. To 16. Passenger number detecting method according to any one of.
19.
　The computer,
　on the basis of the traffic volume of each of the plurality of lanes, switching lanes to focus of the imaging means,
　12 which includes. To 16. Passenger number detecting method according to any one of.
20.
　The computer,
　in accordance with the date or time switch lanes to focus of the imaging means,
　12 which includes. To 16. Passenger number detecting method according to any one of.
21.
　The parameters corresponding to the position includes a plurality of parameters which differ depending on the position in the vehicle,
　the computer,
　the corrected using on the image, a plurality of parameters which differ depending on the position in the vehicle by executing the processing, the plurality of correction images to generate a based on the image,
　and counts the number of occupants of the vehicle using the plurality of correction images
　12 including the. To 20. Passenger number detecting method according to any one of.
22.
　Computer,
　captures a vehicle traveling on a road having a plurality of lanes,
　the distance to the vehicle is measured,
　to reduce the blur of the object caught on the image in accordance with information indicating the distance the measured, the image counting the number of occupants of the vehicle using,
　passenger number detecting method comprising.
23.
　To computer, 12. To 22. Program for executing the passenger number detecting method according to any one of.
[0076]
　This application claims priority based on Japanese Patent Application No. 2017-140226, filed on July 19, 2017, the entire disclosure of which is incorporated herein.

WE claims

[Requested item 1]
　The image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, the correction processing for reducing blur of a subject caught on the image using the parameters corresponding to the position where the vehicle is traveling by performing an image correction means for generating a corrected image based on the image,
　and counting means for counting the number of occupants of the vehicle using the corrected image
　occupant speed detection system comprising.
[Requested item 2]
　Wherein the image correction means, when a plurality of vehicles traveling in different lanes in the image is captured, the by performing the correction processing using a first said parameters corresponding to a position in which one of the vehicle is traveling generating one correction image to generate a second corrected image by executing the correction by using a second said parameter of corresponding to the position where the other vehicle runs,
　said counting means, said first counting the number of occupants of the one vehicle using one of the corrected image, and counts the number of occupants of the other vehicle using the second corrected image,
　the passenger number detecting system according to claim 1.
[Requested item 3]
　The image correcting means determines the parameter based on at least one of information indicating a blur of the subject is calculated using the spatial frequency and the autocorrelation function of the image,
　according to claim 1 or 2 number of passengers detection system.
[Requested item 4]
　The image correcting means determines the parameter based on the distance to the vehicle measured by the distance measuring means for measuring the distance to the vehicle,
　occupant number detecting system according to claim 1 or 2.
[Requested item 5]
　A storage unit for storing information and information indicating each of the plurality of lanes and the parameters associated,
　the image correcting unit specifies the lane on which the vehicle is traveling based on the distance to the vehicle , executes the correction process using the parameters corresponding to the lanes identified,
　passenger number detecting system according to any one of claims 1 to 4.
[Requested item 6]
　Focus distance of the image pickup means in advance to one of the lane defined is fixed to a distance corresponding, among the plurality of lanes
　passenger number detecting system according to any one of claims 1 to 5.
[Requested item 7]
　The focus length of the imaging means, the are fixed at a distance corresponding to the center portion of the plurality of lanes,
　passenger number detecting system according to any one of claims 1 to 5.
[Requested item 8]
　Wherein the plurality of basis lanes on each of traffic, further comprises control means for switching the lanes to focus of the imaging means,
　passenger number detecting system according to any one of claims 1 to 5.
[Requested item 9]
　Depending on the date or time further comprises control means for switching the lanes to focus of the imaging means,
　passenger number detecting system according to any one of claims 1 to 5.
[Requested item 10]
　The parameters corresponding to the position includes a plurality of parameters which differ depending on the position in the vehicle,
　wherein the image correcting means, on the image, by using a plurality of parameters which differ depending on the position in the vehicle by executing the correction process to generate a plurality of correction images based on said image,
　said counting means counts the number of occupants of the vehicle using the plurality of correction images,
　one of the claims 1 to 9 passenger number detecting system according to any one of claims.
[Requested item 11]
　Imaging means for imaging a vehicle traveling on a road having a plurality of lanes,
　the distance measuring means for measuring a distance to the vehicle,
　comprising an image processing means for processing an image generated by the imaging means,
　the image processing means acquires information indicating the distance from the distance measuring means, to reduce the blur of the object caught on the image according to the acquired information, counts the number of occupants of the vehicle with the image,
　number of passengers detection system.
[Requested item 12]
　Computer,
　the image generated by the imaging means for imaging the vehicles traveling on a road having a plurality of lanes, reducing the blur of the object caught on the image using the parameters corresponding to the position where the vehicle is traveling by executing the correction process to generate a corrected image based on the image,
　and counts the number of occupants of the vehicle using the correction image,
　the number of passengers detection method comprising.
[Requested item 13]
　The computer,
　when a plurality of vehicles traveling in different lanes in the image is captured, the correction processing first by executing with the first said parameters corresponding to a position in which one of the vehicle is traveling to generate a corrected image, to generate a second corrected image by executing the correction by using a second said parameter of corresponding to the position where the other vehicle is traveling,
　by using the first corrected image counting the number of occupants of the one vehicle, counts the number of occupants of the other vehicle using the second corrected image,
　the passenger number detecting method according to claim 12 which comprises.
[Requested item 14]
　The computer,
　to determine the parameters based on at least one of information indicating a blur of the subject is calculated using the spatial frequency and the autocorrelation function of the image,
　according to claim 12 or 13 comprising the number of passengers method of detecting.
[Requested item 15]
　The computer,
　to determine the parameter based on the distance to the vehicle measured by the distance measuring means for measuring the distance to the vehicle,
　occupant number detecting method according to claim 12 or 13 comprising.
[Requested item 16]
　The computer is
　based on the distance to the vehicle to identify the lane in which the vehicle is traveling, it is associated with information indicating each of the plurality of lanes of the parameters corresponding to the lanes identified with the parameters read from the storage unit for storing information, read executes the correction processing using the parameters,
　number of occupants detection method according to any one of claims 12 to 15 comprising.
[Requested item 17]
　Focus distance of the imaging means, the plurality of which is fixed to a distance corresponding to one lane predetermined in the lane,
　the number of passengers of any one of claims 12 to 16 comprising detection method.
[Requested item 18]
　The focus length of the imaging means, the are fixed at a distance corresponding to the center portion of the plurality of lanes,
　passenger number detecting method according to any one of claims 12 to 16 comprising.
[Requested item 19]
　The computer,
　on the basis of the traffic volume of each of the plurality of lanes, switching lanes to focus of the imaging means,
　the passenger number detecting method according to any one of claims 12 to 16 comprising.
[Requested item 20]
　The computer,
　in accordance with the date or time switch lanes to focus of the imaging means,
　the passenger number detecting method according to any one of claims 12 to 16 comprising.
[Requested item 21]
　The parameters corresponding to the position includes a plurality of parameters which differ depending on the position in the vehicle,
　the computer,
　the corrected using on the image, a plurality of parameters which differ depending on the position in the vehicle by executing the processing, to generate a plurality of correction images based on the image,
　and counts the number of occupants of the vehicle using the plurality of correction images
　that any one of claims 12 to 20 including passenger number detecting method according.
[Requested item 22]
　Computer,
　a vehicle traveling on a road having a plurality of lanes acquires a captured image and
　a distance to the vehicle is measured,
　the blur of the object caught on the image reduced in accordance with the information indicating the distance the measured counts the number of occupants of the vehicle using the image,
　the number of passengers detection method comprising.
[Requested item 23]
　The computer program for executing the passenger number detecting method according to any one of claims 12 to 22.