TECHNICAL FIELD
[0001] The present invention relates to a parking space detection system, and in particular to a parking space detection system for detecting free parking spaces in a parking area using deep learning techniques.

BACKGROUND
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] Along with the rapid progress and development of science and technology, vehicle such as automobile has become a basic necessity to improve our living standard and quality of life, so it plays an important role in our daily life. Number of vehicles are increasing day by day, and due to challan and safety purpose the vehicle should be parked in the parking area only. There are so many parking areas in the cities, but still sometime when the user reach there, they got to know that no parking space is available in that parking area. And, they have to move to another parking area, thus waste their time, and got irritated also. This becomes a major issue for each and every person, thus, obtaining information of available parking spaces is a prerequisite.
[0004] Existing parking system are based on manual surveillance, when the person enter into the parking area, they have to check the available parking space by their own. Also, in some parking areas ground sensors are used to determine the status of the available parking spaces. However this requires installing of the sensors and maintaining sensors in every parking space, which might be expensive, especially in parking area having a high number of spaces available.
[0005] Therefore, to overcome the above mentioned drawback, there is need to develop a system which is easy to install and can provide detail of the available parking spaces in the parking area to a required person. .

OBJECTS OF THE PRESENT DISCLOSURE
[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are as listed herein below.
[0007] An object of the present invention is to provide a system for automatically and accurately detecting free parking spaces in a large parking area.
[0008] It is another object of the present invention to provide a system for detecting available parking spaces in a parking area, which is easy to install.
[0009] It is another object of the present invention to provide a cost-effective system for detecting available parking spaces in a parking area.
[0010] It is another object of the present invention to enhance image quality to overcome the problem of lighting variations in images taken in an open area.
[0011] It is another object of the present invention to provide a system which facilitates in reducing traffic congestions.
[0012] Other object, features, and advantages will become apparent from detail description and appended claims to those skilled in the art.

SUMMARY
[0013] Various aspects of the present disclosure relates to system for detecting parking space. In particular the present disclosure relates to a parking space detection system for detecting free parking spaces in a parking area using deep learning techniques.
[0014] According to an aspect of the present disclosure a system for detecting free parking space is disclosed. The system can include one or more image acquisition units positioned at a parking area, and configured to acquire one or more images of the parking area, a processing unit may be operatively coupled to each of the one or more image acquisition units.
[0015] In an aspect, the processing unit may include a learning engine coupled with a memory, the memory storing instructions executable by the learning engine and configured to receive the one or more images acquired by the one or more image acquisition units, classify the received one or more images and analyse the classified one or more images to detect one or more free parking spaces in the parking area, determine location information of one or more free parking spaces detected in the parking area, and correspondingly generating a set of signals, where the set of signals may be transmitted to a server.
[0016] In an aspect, the server may be accessed by a plurality of registered entities to view location of one or more free spaces in the parking area.
[0017] In an aspect, the learning engine may be a convolutional neural network architecture.
[0018] In an aspect, the server may be accessed by a client device associated with each of the plurality of registered entities.
[0019] In an aspect, a display unit may be positioned on entrance of the parking area, and configured to display location of one or more free parking spaces in the parking area.
[0020] In an aspect, the display unit may be selected from a group consisting of but not limited to light emitting diode (LED), liquid crystal display (LCD), organic light emitting diode (OLED), and LED matrix.
[0021] In an aspect, the learning engine may be configured to increase image quality of the one or more images acquired by the one or more image acquisition units, when the one or more images are acquired in day light.
[0022] In an aspect, the server may be a centralized server and configured to store location information of one or more parking areas.
[0023] In an aspect, the server may be configured to store one or more images acquired by the one or more image acquisition units that facilitates in training a learning engine.
[0024] Another aspect of the present disclosure pertains to a method for detecting free space in a parking area, the method may include obtaining one or more images of the parking area, classifying and analyzing the obtained one or more images to detect one or more free parking spaces in the parking area, detecting location information of the one or more free parking spaces found in the parking area, displaying the location information of the one or more free parking spaces on a display unit positioned on entrance of the parking area, storing the location information on a server, and accessing the server from a plurality of client devices to retrieve the location information of the one or more free parking spaces.
[0025] Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF DRAWINGS
[0026] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.
[0027] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details.
[0028] FIG. 1 illustrates an exemplary block diagram of parking space detection system, in accordance with an embodiment of the present disclosure.
[0029] FIG. 2 illustrates an exemplary representation of the proposed system, in accordance with an embodiment of the present disclosure.
[0030] FIG. 3 illustrates an exemplary functional components of a processing unit of the proposed system, in accordance with an embodiment of the present disclosure.
[0031] FIG. 4 illustrates a method to illustrate working of the proposed system, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION
[0032] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
[0033] In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details. Embodiments explained herein relate to system for detecting parking space. In particular the present disclosure relates to a parking space detection system for detecting free parking spaces in a parking area using deep learning techniques.
[0034] According to an embodiment of the present disclosure, a parking detection system for detecting free parking spaces in a parking area is disclosed. The parking detection system can include one or more acquisition units to capture images of parking area, and captured images may be analysed using Region-based Convolutional Neural Network (Mask R-CNN) to mark the parking position on the captured images of a whole parking area. In addition, each parking position can be examined to determine whether the position is vacant or not using deep learning architectures such as mAlexNet, Alexnet, and the likes. Further, the information of vacant parking spaces can be displayed on a display unit, thus, the user can easily find the free parking space, and can park vehicle.
[0035] Referring now to the drawings, FIG. 1 is a block diagram of the proposed system. The system 100 can include one or more image acquisition units 102 (collectively referred image acquisition units 102, and individually referred as image acquisition unit 102) configured to monitor the parking area, a display unit 110, a server 108, and a processing unit 104 can be operatively coupled to each of the image acquisition units 102, the display unit 110, and the server 108. For example, the parking area can include multiple aisles, and each aisle including two or three rows of parking spaces. Each pair of parking area can be monitored by the associated the image acquisition unit 102.
[0036] In an embodiment, the image acquisition units 102 can directly include a camera, or an image sensor and an image processing module. The camera 102 can include a CCD camera or a CMOS imaging device (i.e. high resolution, high sensitivity CMOS multi-megapixel digital cameras) that can be configured to acquire one or more images (interchangeably referred as images, hereinafter) of the parking area, and the acquired images can be transmitted to the processing unit 104 for analysis. In an exemplary embodiments, the image acquisition units 102 can process a still image or a moving image obtained by the image sensor (e.g., CMOS or CCD), and the image processing module can process the still image or the moving image acquired through the image sensor, can extract necessary image information, and the extracted image information can be delivered to the processing unit 104 for further analysis.
[0037] In an embodiment, the processing unit 104 including one or more processors configured to analyse the acquired images using a learning engine 106. The learning engine 106 can be configured to extract one or more features from the received images and apply deep learning architecture on the images to mark parking position in the parking area, and examining the parking position whether it is vacant or not. The deep learning architecture can include, but not limited to mAlexNet LeNet, AlexNet, and mLeNet, which can facilitate in accurately analysis of the free parking space and reduce processing time to detect parking space in real time. In another embodiment, the processing unit 104 can be configured to generate a set of signals, upon detection of free (interchangeably referred as vacant, hereinafter) parking spaces in the parking area. The set of signals can pertain location information of the free parking spaces, and can be transmitted to a server 106.
[0038] In an embodiment, one or more location identifiers such as GPS can be installed in the parking area that can facilitate in determining location information of the free parking spaces in the parking area.
[0039] In an embodiment, the server 108 can be configured to receive the analysed information, the server 108 can be located at a remote location or at parking controlling center. The server 108 can be accessed by one or more registered entities (interchangeably referred as user, hereinafter) to view location of free spaces in the parking area using a client device. The client device can be a desktop computer, a vehicle computer, a tablet computer, a personal digital assistant, a laptop, a navigational device, a portable media device, and a smart phone. Moreover, the server 106 can be communicatively coupled with the processing unit 104, the display unit 110, and the client device via a communication unit 112.
[0040] In an exemplary embodiment, the client device can include any one of a web client or application to facilitate communication and interaction between the entities and the system 100. In various embodiments, information communicated between the system 100 and the client device can involve user-selected functions available through one or more user interfaces (UIs). The UIs may be specifically associated with the web client (e.g., a browser) or the application. Accordingly, during a communication session with the client device, the system 100 may provide the client device with a set of machine-readable instructions that, when interpreted by the client device using the web client or the application, cause the client device to present the UI, and transmit user input received through such UIs back to the system 100. As an example, the UIs provided to the client device by the system 100 allow users to view information regarding free parking spaces and parking policy violations overlaid on a geospatial map.
[0041] In an embodiment, the communication unit 112 can be configured to facilitate wireless Internet technology. Examples of such wireless Internet technology include Wireless LAN (WLAN), Wireless Fidelity (Wi-Fi), Wi-Fi Direct, Digital Living Network Alliance (DLNA), Wireless Broadband (WiBro), Worldwide Interoperability for Microwave Access (WiMAX), High Speed Downlink Packet Access (HSDPA), HSUPA (High Speed Uplink Packet Access), Long Term Evolution (LTE), LTE-A (Long Term Evolution-Advanced), and the like.
[0042] In addition, the communication unit 112 can be configured to facilitate short-range communication. For example, short-range communication can be supported using at least one of Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee, Near Field Communication (NFC), Wireless-Fidelity (Wi-Fi), Wi-Fi Direct, Wireless USB (Wireless Universal Serial Bus), and the like.
[0043] In an embodiment, the display unit 110 can be configured to display information of free parking spaces in the parking area. The display unit 110 can be selected from a group consisting of but not limited to light emitting diode (LED), liquid crystal display (LCD), organic light emitting diode (OLED), LED matrix. Size of the display units 110 can be large, thus people sitting in the vehicle can check the free parking space easily. For example, inside the display units 110, a series of LED arrays can be placed adjacent one another to form the screen of the display unit 110, which shows both static and animated warnings, advisories and other information. Although a series of LED arrays can be shown in the illustrated embodiment, one large LED array can be used. Control circuit boards can be provided above the LED arrays. The display unit 110 can display images of vacant parking spaces in the parking area with location information of the parking space.
[0044] Referring to FIG. 2, an exemplary representation of a parking area is disclosed. One or more image acquisition units (102-1, 102-2, 102-3….104-N) can be positioned in a parking area to monitor parking area 202. The acquisition units 102 (i.e. camera) can be configured to capture images of the parking area. The system 100 help the individual users/ drivers (206-1, 206-2…206-N) to get information of free parking spaces on their associated client device (204-1, 204-2…204-N). The client device 204 can include, but not limited to a desktop computer, a vehicle computer, a tablet computer, a personal digital assistant, a laptop, a navigational device, a portable media device, and a smart phone. For example, the user 206 can check various parking areas in the city via the smartphone.
[0045] In an embodiment, a processing unit 104 can be operatively coupled with each of the image acquisition units 102, and the processing unit 104 can be configured to analyse the received images to get location information of the free parking spaces in the parking area. The processing unit including a learning engine 106 configured to apply deep learning architecture on the received images to mark parking position in the parking area, and examining the parking position whether it is vacant or not. The deep learning architecture can include, but not limited to mAlexNet LeNet, AlexNet, and mLeNet, which can facilitate in accurately analysis of the free parking space and reduce processing time to detect parking space in real time.
[0046] In an embodiment, the processing unit 104 can be operatively coupled to a server 108 that can be centralized server positioned remotely. The server 108 can be configured to store location information of the free parking spaces fond in the parking area. The server 108 can be communicatively coupled with a display unit 110 to display location information of the free parking spaces in the parking area 202. The display unit 110 can be positioned on the entrance of the parking.
[0047] In an exemplary embodiment, when a user 206 needs to park the vehicle, he can check the free parking spaces through an application installed on the smartphone. The smartphone can access the location information stored on the server 108, and accordingly can park the vehicle easily without wasting the time.
[0048] In an embodiment, power supply unit (not illustrated) can be configured to supply power required to operate the respective components under the control of the processing unit 104. In particular, the power supply unit can receive power from, for example, a battery (not illustrated). The power supply unit can be operatively coupled with the image acquisition units 102, the processing unit 104, and the display unit 110.
[0049] Referring to FIG. 3, a processing unit 104 can include one or more processor(s) 302. The one or more processor(s) 302 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and/or any devices that manipulate data based on operational instructions. Among other capabilities, the one or more processor(s) 302 can be configured to fetch and execute computer readable instructions stored in a memory 304 of the processing unit 104. The memory 304 can store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service. The memory 304 can include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the likes.
[0050] In an embodiment, the processing unit 104 can also include an interface(s) 306. The interface(s) 306 may comprise a variety of interfaces, for example, interfaces for data input and output devices, referred to as I/O devices, storage devices, and the like. The interface(s) 306 may facilitate communication of system 100. The interface(s) 306 may also provide a communication pathway for one or more components of the system 100. Examples of such components include, but are not limited to, learning engine(s) 106 and database 310.
[0051] In an embodiment, the learning engine(s) 106 can be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the learning engine(s) 106. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the learning engine(s) 106 may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the learning engine(s) 106 may include a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the learning engine(s) 106. In such examples, the processing unit 104 can include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to processing unit 104 and the processing resource. In other examples, the learning engine(s) 106 may be implemented by electronic circuitry. The database 310 can include data that is either stored or generated as a result of functionalities implemented by any of the components of the learning engine(s) 106.
[0052] In an embodiment, the learning engine(s) 106 can include an extraction unit 312, a classification and training unit 314, a matching unit 316, a signal generation unit 318, and other unit(s) 320. The other unit(s) 320 can implement functionalities that supplement applications or functions performed by the system 100 or the learning engine(s) 106.
[0053] In an embodiment, the database 310 can include data that is either stored or generated as a result of functionalities implemented by any of the components of the learning engine(s) 106. The database 310 can be a server including several local and/or remote servers
[0054] It would be appreciated that units being described are only exemplary units and any other unit or sub-unit may be included as part of the system 100. These units too may be merged or divided into super- units or sub-units as may be configured.
[0055] In an embodiment, the processing unit 104 can be configured to receive one or more images acquired by image capturing units 102 in an electric form, where the images include information of parking spaces in the parking area. The extraction unit 312 can be configured to extract one or more features from the images. The extracted information can be transmitted to the matching unit 316.
[0056] In an embodiment, the matching unit 316 can be configured to match the extracted information from a set of pre-defined images. The images can transmitted to the classification and training unit 314 in machine readable form or binary form, where the classification and training unit 314 can classify the information and correspondingly the signal generation unit 318 can generate and transmit a set of signals.
[0057] In an embodiment, the classification and training unit 314 can be configured to analyse the received images using Region-based Convolutional Neural Network (Mask R-CNN). The Mask R-CNN can be used to mark the parking position on the captured images of a whole parking area. In addition, each parking position can be examined to determine whether the position is vacant or not using deep learning architectures (CNN) such as mAlexNet, Alexnet, and the likes. Further, the learning engine 106 can be configured to update and train the classification and training unit 214 based on extracted information. The learning model can be trained based on the received and analysed information where the leaning model can be stored in the database 310.
[0058] In an embodiment, the CNN is trained to directly detect the vacant status of the individual parking spaces from the received images of the parking area in less time.
[0059] In an embodiment, the signal generation unit 318 can be further configured to generate and transmit the set of signals which can be transmitted to the display unit 110 to display free parking spaces, which can assist the drivers to check parking spaces before entering the parking area.
[0060] The signal generation unit 318 can be configured to provide location information in form of signals to the server 108. The user 206 can access the server 106 via an associated client device 204. For example, the user can check the free parking spaces in the parking area in the smartphone before entering the parking area. Upon detection of free parking spaces in the parking area, the user can enter in the parking area, else can search for another parking area nearby.
[0061] In another embodiment, the learning engine 106 can be configured to increase image quality of the one or more images acquired by the image acquisition units 102 in day light to provide accurate free spaces detection in less time. A contrast enhancement techniques (such as exposure fusion framework method) can be applied on the acquired images to enhance the image quality to overcome the problem of lighting variations in images taken in an open area.
[0062] As illustrated in FIG. 4, a method (400) for detecting free space in a parking area is disclosed. At step (402) the method (400) can include receiving at a processing unit 104 one or more images acquired by one or more image acquisition units 102 positioned at the parking area.
[0063] At step (404), the method (400) can include classifying and analyzing the obtained one or more images to detect one or more free parking spaces in the parking area. The classification and analysis can be performed using a learning engine 106.
[0064] At step (406), the method (400) can include detecting location information of the one or more free parking spaces found in the parking area, using the learning engine 106 by applying deep learning architecture such as mAlexNet that facilitates in getting location information of free parking spaces accurately in less time.
[0065] At step (408), the method (400) can include displaying the location information of the one or more free parking spaces on a display unit 110 positioned on entrance of the parking area, the display unit 110 can be positioned on road also, nearby the parking area, thus enables the user to enter in the parking area, only when the parking spaces are vacant.
[0066] At step (410), the method (400) can include storing the location information on a server 108, the server 108 can be a centralized server.
[0067] At step (412), the method (400) can include accessing the server 106 from a one or more client devices 204 to retrieve the location information of the one or more free parking spaces by the user 206. The user 206 can check the parking area on the application installed in the smartphone to get location information of the vacant parking space, and can park the vehicle there.
[0068] The above described features, configurations, effects, and the like are included in at least one of the embodiments of the present invention, and should not be limited to only one embodiment. In addition, the features, configurations, effects, and the like as illustrated in each embodiment may be implemented with regard to other embodiments as they are combined with one another or modified by those skilled in the art. Thus, content related to these combinations and modifications should be construed as including in the scope and spirit of the invention as disclosed in the accompanying claims.
[0069] Further, although the embodiments have been mainly described until now, they are just exemplary and do not limit the present invention. Thus, those skilled in the art to which the present invention pertains will know that various modifications and applications which have not been exemplified may be performed within a range which does not deviate from the essential characteristics of the embodiments. For instance, the constituent elements described in detail in the exemplary embodiments can be modified to be performed. Further, the differences related to such modifications and applications shall be construed to be included in the scope of the present invention specified in the attached claims.
[0070] The present invention encompasses various modifications to each of the examples and embodiments discussed herein. According to the invention, one or more features described above in one embodiment or example can be equally applied to another embodiment or example described above. The features of one or more embodiments or examples described above can be combined into each of the embodiments or examples described above. Any full or partial combination of one or more embodiment or examples of the invention is also part of the invention.

ADVANTAGES OF THE INVENTION
[0071] The proposed invention provides a system for automatically and accurately detecting free parking spaces in a large parking area.
[0072] The proposed invention provides a system for detecting available parking spaces in a parking area, which is easy to install.
[0073] The proposed invention provides a cost-effective system for detecting available parking spaces in a parking area.
[0074] The proposed invention provides a system to enhance image quality to overcome the problem of lighting variations in images taken in an open area.
[0075] The proposed invention provides a system which facilitates in reducing traffic congestions.

We Claims:

1. A system 100 for detecting free parking space, the system comprising:
one or more image acquisition units 102 positioned at the a parking area, and configured to acquire one or more images of the parking area;
a processing unit 104 operatively coupled to each of the one or more image acquisition units 102, the processing unit 104 comprising a learning engine 106 coupled with a memory, the memory storing instructions executable by the learning engine and configured to:
receive the one or more images acquired by the one or more image acquisition units 102;
classify the received one or more images and analyse the classified one or more images to detect one or more free parking spaces in the parking area; and
determine location information of one or more free parking spaces detected in the parking area, and correspondingly generating a set of signals, wherein the set of signals are transmitted to a server 108, wherein the server 108 is accessed by a plurality of registered entities to view location of one or more free spaces in the parking area.
2. The system as claimed in claim 1, wherein the learning engine 106 comprises a convolutional neural network architecture.
3. The system as claimed in claim 1, wherein the server 108 is accessed by a client device 204 associated with each of the plurality of registered entities 206.
4. The system as claimed in claim 1, wherein a display unit 110 is positioned on entrance of the parking area, and configured to display location of one or more free parking spaces in the parking area, wherein the display unit 110 is selected from a group consisting of but not limited to light emitting diode (LED), liquid crystal display (LCD), organic light emitting diode (OLED), and LED matrix.
5. The system as claimed in claim 1, wherein the learning engine 106 is configured to increase image quality of the one or more images acquired by the one or more image acquisition units 102, when the one or more images are acquired in day light.
6. The system as claimed in claim 1, wherein the server 108 is a centralized server and configured to store location information of one or more parking areas.
7. The system as claimed in claim 1, wherein the server 108 is configured to store one or more images acquired by the one or more image acquisition units 102, that facilitates in training a learning engine.
8. A method 400 for detecting free space in a parking area, the method comprising:
obtaining one or more images of the parking area;
classifying and analyzing the obtained one or more images to detect one or more free parking spaces in the parking area;
detecting location information of the one or more free parking spaces found in the parking area;
displaying the location information of the one or more free parking spaces on a display unit positioned on entrance of the parking area;
storing the location information on a server; and
accessing the server from a plurality of client devices 204 to retrieve the location information of the one or more free parking spaces.