FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION (See section 10, rule 13)
“A COMPUTER IMPLEMENTED SYSTEM AND METHOD FOR COUNTING RIDERS TRAVELLING ON A TWO-WHEELER”
ZENSAR TECHNOLOGIES LIMITED of Zensar Knowledge Park, Plot # 4, Midc, Kharadi, Off Nagar Road, Pune, Maharashtra 411014, Indian
The following specification particularly describes the invention and the manner in which it
is to be performed.

CROSS REFERENCE TO RELATED APPLICATION
This patent application claims priority from an Indian Provisional application (having no. 201921011324) filed on March 23rd, 2019.
TECHNICAL FIELD
[0001] The present disclosure relates to counting individuals travelling on a two-wheeler. More particularly, but not exclusively, the present disclosure describes a system for detecting and identifying number of individual travelling on a two-wheeler and a method thereof.
BACKGROUND
[0002] In developing nations, like India, managing traffic is a tedious task. Further, despite of strict traffic rules, it can be observed that three people riding on a two-wheeler is a very common sight. Such riders are not really conscious of the threat and trouble they cause to themselves and to other fellow commuters.
[0003] The best way to prevent such riders from commuting is to penalize them regularly. Conventionally, the activity of identifying these offenders is done manually by traffic police. The traffic police are required to conduct programs across cities occasionally to get hold of such offenders. However, due to various limitations, the traffic police fail to continuously monitor and track these offenders as it is impossible for the traffic police to be present at each and every junction or signal post, thus resulting in the continuation of these ill-practices.
[0004] Therefore, there is felt a need to provide a computer implemented system and method for counting riders travelling on a two-wheeler which alleviates the above-mentioned drawbacks of conventional approach.

SUMMARY
[0005] The present disclosure overcomes one or more shortcomings of the prior art and provides additional advantages discussed throughout the present disclosure. Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.
[0006] In one non-limiting embodiment of the present disclosure, a method of identifying details of at least one vehicle on road is described. The method further discloses the step of receiving a plurality of images of the at least one vehicle on the road. Said method further discloses selecting from the plurality of images, at least one image comprising at least one two-wheeled vehicle and processing the at least one selected image of the at least one two-wheeled vehicle for determining number of individuals on the at least one two-wheeled vehicle. Said method further discloses comparing the determined number of individuals with a pre-determined threshold for the at least one two-wheeled vehicle and if the determined number of individuals of the at least one two-wheeled vehicle exceeds the pre-determined threshold and performing optical character recognition (OCR) of at least one image corresponding to the at least one two wheeled vehicle for which the number of determined individuals is more than the pre-determined threshold.
[0007] In still non-limiting embodiment of the present disclosure, the step of processing the image further comprises localizing the selected image, wherein localizing includes cropping multiple images of distinct two-wheeled vehicle.
[0008] In yet another non-limiting embodiment of the present disclosure, the step of performing OCR comprises further comprises extracting registration details of the two-wheeled vehicles based on information retrieved by performing optical character

recognition (OCR) of the at least one image and extracting vehicle owner details corresponding to the two wheeled vehicle registration details.
[0009] In yet another non-limiting embodiment of the present disclosure, said method discloses employing person detection technique for determining the number of individuals sitting on the two-wheeled vehicles, wherein the person detection technique is configured for identifying the individual sitting on the two-wheeled vehicles based on their sitting posture.
[0010] In yet another non-limiting embodiment of the present disclosure, said method further discloses triggering an alarm, upon comparing, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre¬determined threshold.
[0011] In yet another non-limiting embodiment of the present disclosure, a system to identify details of at least one vehicle on road is disclosed. Said system discloses having a communication unit configured to receive a plurality of images of the at least one vehicle on the road and a processing unit operatively coupled to the communication unit. Said processing unit being configured to select from the plurality of images, at least one image comprising at least one two-wheeled vehicle and process the at least one selected image of the at least one two-wheeled vehicle to determine number of individuals on the at least one two-wheeled vehicle. Further said processing unit is configured to compare the determined number of individuals with a pre-determined threshold for the at least one two-wheeled vehicle and if the determined number of individuals of the at least one two-wheeled vehicle exceeds the pre-determined threshold, perform optical character recognition (OCR) of at least one image corresponding to the at least one two wheeled vehicle for which the number of determined individuals is more than the pre-determined threshold.

[0012] In still non-limiting embodiment of the present disclosure, the processing unit is further configured to localize the selected image by cropping multiple images of distinct two-wheeled vehicle.
[0013] In yet another non-limiting embodiment of the present disclosure, to perform OCR, the processing unit is configured to extract registration details of the two-wheeled vehicle based on information retrieved by performing optical character recognition (OCR) of the at least one image and extract vehicle owner details corresponding to the vehicle registration details.
[0014] In yet another non-limiting embodiment of the present disclosure, the processing unit employs person detection technique for determining the number of individuals sitting on the two-wheeled vehicles, wherein the person detection technique is configured to identify the individual sitting on the two-wheeled vehicles based on their sitting posture.
[0015] In yet another non-limiting embodiment of the present disclosure, the processing unit is further configured to trigger an alarm, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre-determined threshold.
OBJECTIVES OF THE INVENTION
[0016] In one embodiment the objective of the present disclosure is to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
[0017] In another embodiment the objective of the present disclosure is to provide a computer implemented system and method for counting riders travelling on a two-wheeler.

[0018] In yet another embodiment the objective of the present disclosure is to provide a computer implemented system and method that eliminates the need of human intervention for counting riders.
[0019] In still another embodiment the objective of the present disclosure is to provide a computer implemented system and method which is accurate.
[0020] In yet another embodiment the objective of the present disclosure is to provide a computer implemented system and method which is cost effective.
[0021] Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
[0022] The features, nature, and advantages of the present disclosure will become more apparent from the detailed description set forth below when taken in conjunction with the drawings in which like reference characters identify correspondingly throughout. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:
[0023] Fig. 1 shows a block diagram illustrating a system for counting number of individuals on a two-wheeler in accordance with an embodiment of the present disclosure.
[0024] Fig. 2 shows a flowchart of an exemplary method for counting number of individuals on a two-wheeler in accordance with an embodiment of the present disclosure.

[0025] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.
DETAILED DESCRIPTION
[0026] In the present document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration”. Any embodiment or implementation of the present subject-matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
[0027] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.
[0028] The terms “comprises”, “comprising”, “include(s)”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, system or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or system or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.

[0029] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.
[0030] The present disclosure will be described herein below with reference to the accompanying drawings. In the following description, well known functions or constructions are not described in detail since they would obscure the description with unnecessary detail.
[0031] The present disclosure relates to a computer implemented system to identify detail of at least one vehicle on road. Precisely, said system discloses techniques to count the number of individual travelling on a two-wheeler and identify detail of such two-wheeler, where the number of individuals travelling on the two-wheeler are found above a pre-determined threshold.
[0032] Referring to figure 1, an exemplary system 100 for detecting and identifying individuals travelling on a two-wheeler is shown by way of block diagram. In order to detect and identify the number of individuals travelling on a two-wheeler (not shown) the system 100 disclose having a plurality of traffic surveillance units 105 and at least a server 110. In an exemplary embodiment, said system 100 may include multiple traffic surveillance unit 105, wherein each one said traffic surveillance unit 105 may remain attached to the one or more server 110 at any given point of time. It is to be appreciated that the system 100 disclosed in figure 1 may be configured to include plurality of surveillance unit and servers. However, for the sake of brevity the system 100 with single surveillance unit 105 is shown attached to the single server 110.

[0033] Further, in an exemplary embodiment, the plurality of traffic surveillance units 105 may be mounted on vertical posts in a one to one correspondence. In another exemplary embodiment, the vertical posts may be selected from the group consisting of a signal post, a street light post, and a street advertisement post. Further, as shown in system 100 of figure 1, the traffic surveillance unit 105 may include at least one image capturing device 115 and a transceiver 120. The image capturing device 115 may be selected from the group consisting of an infrared camera, a day and night camera, a PTZ (Pan, tilt and zoom) camera, a thermal camera or any other state of the art camera. Further, each of said image capturing device 115 may be placed inside the surveillance unit 105 in one or more different angular positions to cover traffic on road from different angles.
[0034] It is to be appreciated that each of said plurality of image capturing units 115 may be configured to periodically capture the images of vehicular traffic passing from the vicinity of the surveillance unit 105 placed across the road. The system 100 further shows that the surveillance unit 105 also includes a transceiver 120 operatively couple to the one or more image capturing units 105. Said transceiver 120 is configured to cooperate with the image capturing unit 115 to receive the captured images and transmit the captured images to the server 110. In an exemplary embodiment, the server 110 may be placed in the vicinity of the surveillance unit 105. In another exemplary embodiment, the server 110 may be placed at a central location distinct from the location of the surveillance unit 105.
[0035] Further as shown in figure 1, in order to receive the images captured by the image capturing unit 115, said server 110 includes a communication unit 125. In an embodiment, said communication unit 125 may remain connected to the transceiver 120 of the surveillance unit 105 through one of LAN, WAN or similar network technologies. In an exemplary embodiment, the communication unit 125 remain connected to the surveillance unit 105, through transceiver 120 so as to receive a

plurality of images, captured by the image capturing unit 115, of the at least one vehicle travelling on the road.
[0036] The server 110 further includes a processing unit 130. Said processing unit 130 may remain connected to the communication unit 125 so as to receive the plurality of images received by the communication unit 125 from the surveillance unit 105. Further the processing unit 130 is configured to select from the plurality of images, at least one image comprising at least one two-wheeled vehicle. In an exemplary embodiment, the processing unit 130 may include an object identification unit 150 for doing so.
[0037] The object detection module 150 of the processing unit 130 may be configured to employ supervised learning principle and identify presence of at least one two wheeler in the at least one of the images received by the processing unit 130 (captured by the image capturing unit 115 of the surveillance unit 105. In an embodiment, the object detection module 150 may be configured to select only the images where two-wheeler is detected and may be configured to discard the captured images where no two-wheeler is identified. In another embodiment, the object detection module 150 may be modeled to learn about different two-wheeler types. It is to be appreciated that since the object detection module 150 of the processing unit 130 is trained to select an image even where a single two-wheeler is captured, the processing unit may also be referred as image processing unit interchangeably throughout the specification. In one embodiment, the object detection module 150 may be an Artificial intelligence (AI) based module that is able to learn on its and is able to make improvement in itself using machine learning techniques.
[0038] Further as shown in figure 1, the image processing unit 130 may further include a localizer module 155. Said localizer module 155 may be configured to work in conjunction with the object detection module 150 to receive the selected images. In a specific embodiment, the localizer module 155 may be configured to localize the boundary regions of the two-wheelers within the selected images, and may be further

configured to generate at least one localized image from each of the selected image based on the number of two-wheelers present in the received selected image. In an embodiment, localized images may be cropped image of the selected image depicting two-wheeler and riders. Thus, in other words, the localizer module 155 of the processing unit 130 may be configured to localize the selected image by cropping multiple images of distinct two-wheeled vehicle from a single image. Thus, the localizer module 155 is configured to generate multiple images containing different two-wheelers from one single image. In one embodiment, the localizer module 155 may be an Artificial intelligence (AI) based module that is able to learn on its and is able to make improvement in itself using machine learning techniques.
[0039] Coming back to figure 1, the processing unit 130 is configured process the at least one selected image of the at least one two-wheeled vehicle, generated by the localizer module 155, to determine number of individuals on the at least one two-wheeled vehicle and compare the determined number of individuals with a pre¬determined threshold for the at least one two-wheeled vehicle. To do so, the processing unit 130 may include a rider detection module 160. Said rider detection module 160 may be configured to cooperate with the localizer module 155 to receive a plurality of the localized images, and may be further configured to analyze the localized images to determine a value corresponding to the count of riders riding the two-wheeler.
[0040] It is to be noted that the rider detection module is configured to not only detect rider riding the two-wheeler but all the individuals sitting on the two-wheeler. To do so, the rider detection module 160 may employ person detection technique for determining the number of individuals sitting on the two-wheeled vehicles. In one embodiment, the person detection technique is configured to identify the individual sitting on the two-wheeled vehicles based on their sitting posture which may include but is not limited to attributes such bent in angle of legs while sitting, number of hand visible on two wheeler, number of heads on two-wheeler and other like attributes. In one embodiment, the rider detection module 160 may be an Artificial intelligence (AI)

based module that is able to learn on its and is able to make improvement in itself using machine learning techniques.
[0041] Further, in one embodiment, the rider detection module 160 may be configured to trigger an alarm, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre-determined threshold. Precisely, the rider detection module 160 may generate the trigger signal when the count of riders is more than two. In one exemplary embodiment, the pre-determined threshold may be defined as two or any number below or above two based on the local traffic laws of a geographical location. In another exemplary embodiment, the pre-determined threshold may be defined based on the type of two-wheeled vehicle by the law enforcement agencies of a geographical location. Furthermore, the rider detection module 160 may be configured to tag the localized images with the value corresponding to the count of riders riding the two-wheeler upon generating of the trigger signal. In an embodiment, the rider detection module 160 may be configured to identify the riders riding in different poses by employing supervised learning principle.
[0042] Further, the processing unit 130 is configured to perform optical character recognition (OCR) of at least one image corresponding to the at least one two-wheeled vehicle for which the number of determined individuals is more than the pre¬determined threshold. In an embodiment, the processing unit 130 may be configured to perform optical character of at least one image corresponding to the at least one two-wheeled vehicle only if the determine number of individuals of the at least one two-wheeled vehicle exceeds the pre-determined threshold.
[0043] In order to perform the process of OCR, it is necessary that the processing unit 130 may be configured to identify and read the number plates of the at least one two-wheeled vehicle for which the number of determined individuals is more than the pre-determined threshold. In an embodiment, to achieve this, the processing unit 130 may include the license plate detection module 165 which may be configured to cooperate

with the rider detection module 160 to receive the tagged localized image. The license plate detection module 165 may be configured to identify the number plate of the two-wheelers present in the received tagged localized image and may be further configured to perform optical character recognition on the number plate to identify vehicle registration number. In one exemplary embodiment, the license plate detection module 165 may be equipped to read multiple languages with different font sizes. Further, the license plate detection module 165 may be configured to read both the front and rear license plates of a two-wheeled vehicle of any length and dimension. Further it is to be appreciated that like other modules, the license plate detection module 165 may be an Artificial intelligence (AI) based module that is able to learn on its and is able to make improvement in itself using machine learning techniques.
[0044] As shown in figure 1 system 100 may further includes a database management unit 135, a reporting module 140, and a database 145 each operatively coupled to the processing unit 130. In an embodiment, the database 145 may be configured to store a lookup table having a list of vehicle registration numbers, and vehicle owner details corresponding to each vehicle registration numbers. In an exemplary embodiment, the database 145 may include list of vehicle registration numbers, and vehicle owner details corresponding to the vehicle registered in one or more geographical location.
0045] Further, the database management unit 135 may be configured to cooperate with the image processing unit 130 and the database 145. More specifically, the database management unit 135 may be configured to receive the tagged localized image and the identified vehicle registration number corresponding to the tagged localized image from the license plate detection module 165. In an exemplary embodiment, the database management unit 135 may include a crawler and extractor, and an updater. The crawler and extractor may be configured to crawl through the lookup table and extract the vehicle owner details corresponding to the received vehicle registration number from the database 145. The updater may be configured to update the lookup table for the received vehicle registration number with details of the offense.

[0046] Further, the reporting module 140, of the server 110, may be configured to cooperate with the image processing unit 130 and the database management unit 135. Said reporting module 140 may be configured to receive the vehicle registration number and may be further configured to generate a notification signal to notify the owner of the two-wheeler and a traffic controller about the offense. Additionally, the reporting module 140 may be configured to maintain a log of such reporting in the database 145 corresponding to the vehicle registration number. In one embodiment, the reporting module 140 may be configured to notify the owner of the two-wheeler via an SMS, an email, and the like. Further, in one implementation, the image processing unit 130, the database management unit 135, and the reporting module 140 may be implemented using one or more processor(s) or microcontroller(s).
[0047] Fig. 2 shows a flowchart of an exemplary method 200 for identifying details of at least one vehicle on road, in accordance with an embodiment of the present disclosure. At block 202, the method 200 discloses receiving a plurality of images of the at least one vehicle on the road. by the server 100. Said one or more images of the vehicles on the road are captured by the one or more image capturing unit 115 placed inside the surveillance unit 105. Further, each of said images are sent by the transceiver 120 of the surveillance unit 105 to the server 110, wherein the communication unit 125 of the server is 110 is configured for receiving these images. In an exemplary embodiment, the communication unit 110 may be configured for receiving said plurality of images of the at least one vehicle on the road from the surveillance unit 105 periodically.
[0048] At block 204, the method 200 comprises selecting from the plurality of images, at least one image comprising at least one two-wheeled vehicle. For making said selection, the processing unit 130 may use the object detection module 150. he object detection module 150 of the processing unit 130 is configured to employ supervised learning principle for identifying presence of at least one two wheeler in the at least one of the images received by the processing unit 130 (captured by the image

capturing unit 115 of the surveillance unit 105. In an embodiment, the object detection module 150 may be configured for selecting only the images where two-wheeler is detected and may be configured for discarding the captured images where no two-wheeler is identified.
[0049] Further at block 206, the method 200 discloses processing the at least one selected image of the at least one two-wheeled vehicle. For processing the at least one selected image the processing unit may use the localizer module 155 that may work in conjunction with the object detection module 150 for receiving the selected images. In a specific embodiment, the step of processing includes localizing the boundary regions for all the two-wheelers present within the selected images using the localizer module 155. Said step further comprises generating at least one localized image from each of the selected image based on the number of two-wheelers present in the received selected image. In an embodiment, these localized images may be cropped image of the selected image depicting multiple two-wheeler and their riders within an image. Thus, the process of localization may be understood as a process of cropping multiple images of distinct two-wheeled vehicle from a single image. Therefore, it may be said that the process of localization generates multiple images containing different two-wheelers from one single image.
[0050] Further the method 200, at step 208 discloses determining number of individuals on the at least one two-wheeled vehicle. To do so, the processing unit 130 may make use of the rider detection module 160. Said rider detection module 160 may be configured to cooperate with the localizer module 155 to receive a plurality of the localized images, and may be further configured to analyze the localized images for determining a value corresponding to the count of riders riding the two-wheeler.
[0051] It is to be noted that the process of determining the number of individuals on the two-wheeler not only comprises detecting rider riding the two-wheeler but also includes detecting the individuals sitting on the two-wheeler. For determining the number of individuals, the rider detection module 160 may employ person detection

technique. In one embodiment, the person detection technique is configured for identifying the individual sitting on the two-wheeled vehicles based on their sitting posture which may include but is not limited to attributes such as bent in angle of legs while sitting, number of hand visible on two-wheeler, number of heads on two-wheeler and other like attributes.
[0052] Though not explicitly disclosed in figure 2, step 208, in one embodiment, may also comprise triggering an alarm, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre-determined threshold. Precisely, the rider detection module 160 may be configured for generating the trigger signal when the count of riders is more than, the pre-determined threshold. Furthermore, though not explicitly disclosed, the method 200 at step 208 also includes the step of tagging the localized images with the value corresponding to the count of riders riding the two-wheeler upon generating of the trigger signal.
[0053] Further at step 210, the method 200 discloses comparing the determined number of individuals with a pre-determined threshold for the at least one two-wheeled vehicle. Further as next step 212, the method 200 discloses checking if the number of individuals on the two-wheeled vehicles exceeds the predetermined threshold or not. In one example, if the number of individuals on the two-wheeled vehicle are not found exceeding the pre-determined threshold, the method proceeds to step 204 and continues selecting images for further processing.
[0054] However, if at step 212, it is found that the number of individual on the two-wheeled vehicle are found exceeding the pre-determined threshold, the method proceeds to step 214. At step 214, the method 200 discloses performing optical character recognition (OCR) of at least one image corresponding to the at least one two wheeled vehicles for which the number of determined individuals is more than the pre-determined threshold.

[0055] The process of performing OCR, further comprises identifying and reading the number plates of the at least one two wheeled vehicles for which the number of determined individuals is more than the pre-determined threshold. For performing said process, the processing unit 130 may include the license plate detection module 165 which may be configured for identifying the number plate of the two-wheelers present in the received tagged localized image and reading the number plate to identify vehicle registration number.
[0056] Though not explicitly disclosed in method 200 of figure 2, the method further includes extracting, using the database management unit 135, the identified vehicle registration number corresponding for the tagged localized images. In an exemplary embodiment, the database management unit 135 may include a crawler and extractor, and an updater. The crawler and extractor may be configured to crawl through the lookup table and extract the vehicle owner details corresponding to the received vehicle registration number from the database 145. The updater may be configured to update the lookup table for the received vehicle registration number with details of the offense.
[0057] The method 200 further includes generating, via the reporting module 140, of the server 110, a notification signal to notify the owner of the two-wheeler and a traffic controller about the offense. Said reporting module 140 may be configured to maintain a log of such reporting in the database 145 corresponding to the vehicle registration number. In one embodiment, the reporting module 140 may be configured for notifying the owner of the two-wheeler via an SMS, an email, and the like.
[0058] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the way functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description.

Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed.
[0059] Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[0060] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer- readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., are non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[0061] Suitable processors include, by way of example, a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) circuits, any other type of integrated circuit (IC), and/or a state machine.
[0062] Exemplary embodiments discussed above may provide certain advantages. Though not required to practice aspects of the disclosure, these advantages may include those provided by the following features. .

[0063] In an embodiment, the present disclosure provides an automated system for detecting number of individuals on a vehicle without human intervention.
[0064] In an embodiment, the present disclosure provides a cost effective yet accurate system for detecting number of individuals on a vehicle.
[0065] In an embodiment, the present disclosure provides a self-learning system for detecting number of individuals on a vehicle.

We claim:
1. A method of identifying details of at least one vehicle on road, the method
comprising:
receiving a plurality of images of the at least one vehicle on the road; selecting from the plurality of images, at least one image comprising at least one two-wheeled vehicle;
processing the at least one selected image of the at least one two-wheeled vehicle for:
determining number of individuals on the at least one two-wheeled vehicle;
comparing the determined number of individuals with a pre-determined threshold for the at least one two-wheeled vehicle; and
if the determined number of individuals of the at least one two-wheeled vehicle exceeds the pre-determined threshold, performing optical character recognition (OCR) of at least one image corresponding to the at least one two-wheeled vehicle for which the number of determined individuals is more than the pre-determined threshold.
2. The method as claimed in claim 1, wherein processing the image further comprises localizing the selected image, wherein localizing includes cropping multiple images of distinct two-wheeled vehicle.
3. The method as claimed in claim 1, wherein performing OCR comprises:
extracting registration details of the two-wheeled vehicle based on information retrieved by performing optical character recognition (OCR) of the at least one image; and
extracting vehicle owner details corresponding to the two wheeled vehicle registration details.
4. The method as claimed in claim 1, employs person detection technique for
determining the number of individuals sitting on the two-wheeled vehicles,

wherein the person detection technique is configured for identifying the individual sitting on the two-wheeled vehicles based on their sitting posture.
5. The method as claimed in claim 1, further comprises triggering an alarm, upon comparing, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre-determined threshold.
6. A system to identify details of at least one vehicle on road, said system comprising:
a communication unit configured to receive a plurality of images of the at least one vehicle on the road; and
a processing unit operatively coupled to the communication unit and configured to:
select from the plurality of images, at least one image comprising at least one two-wheeled vehicle;
process the at least one selected image of the at least one two-wheeled vehicle to determine number of individuals on the at least one two-wheeled vehicle;
compare the determined number of individuals with a pre-determined threshold for the at least one two-wheeled vehicle; and
if the determined number of individuals of the at least one two-wheeled vehicle exceeds the pre-determined threshold, perform optical character recognition (OCR) of at least one image corresponding to the at least one two wheeled vehicles for which the number of determined individuals is more than the pre-determined threshold.
7. The system as claimed in claim 6, wherein to process the image, the processing
unit is further configured to localize the selected image by cropping multiple
images of distinct two-wheeled vehicle.

8. The system as claimed in claim 6, wherein to perform OCR, the processing unit
is configured to:
extract registration details of the two-wheeled vehicle based on information retrieved by performing optical character recognition (OCR) of the at least one image; and
extract vehicle owner details corresponding to the vehicle registration details.
9. The system as claimed in claim 6, wherein the processing unit employs person detection technique for determining the number of individuals sitting on the two-wheeled vehicles, wherein the person detection technique is configured to identify the individual sitting on the two-wheeled vehicles based on their sitting posture.
10. The system as claimed in claim 6, wherein the processing unit is further configured to trigger an alarm, if the determined number of individuals of the at least one two-wheeled vehicle is found exceeding the pre-determined threshold.