Parking space occupying method and system based on face recognition

Abstract

The present invention discloses a parking space occupying method and system based on face recognition. When the method learns that the parking space of the first owner is parked, the facial images of all passengers in the vehicle are collected by a camera, and the first facial recognition is performed to determine whether it is stored in the database of the garage access control system, and then the second judgment is performed to determine whether the matched facial image is associated with the parking space of the first owner, and finally the third judgment is performed to determine whether the facial image in the vehicle is stored in the database of the community property management system. If no result can be obtained in the three judgments, the first facial image set is sent to the first owner, and the owner confirms whether the parking space is occupied. The present invention optimizes the entire judgment logic, reduces the probability of misjudgment events and improves user experience while minimizing manual intervention.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a parking space occupying method and system based on face recognition. Background Art

[0002] With the development of technology, more and more smart devices are being deployed in residential areas, and there are more supporting property management systems, security systems, etc. Parking management in residential areas generally involves setting up access control systems at the entrances and exits of garages to identify vehicles entering and leaving as registered vehicles of owners or visitor vehicles. After a vehicle enters the garage, the visitor vehicle will follow the garage guidance signs to park the vehicle in the corresponding vacant parking space.

[0003] However, visitor vehicles often do not follow the guidance of the signboards and park arbitrarily, occupying the parking spaces purchased by the owners, resulting in nowhere for the owners to park their vehicles when they return, and the community manager needs to notify the visitor owners to move their vehicles away. Existing smart communities all solve the above problem by linking cameras to the property management system. By setting up cameras near the parking spaces to monitor the status of the parking spaces, the cameras capture and identify the license plate number after the vehicle is parked, and compare it with the license plate number recorded in the property management system (provided by the parking space owner). If the comparison fails, it means that the owner's parking space is occupied, and the property manager will be notified in time to handle it, thereby solving the problem of the owner's parking space being occupied.

[0004] Existing solutions rely on the license plate records of the property management system, and the property management system generally only gives a few fixed record quotas to the owner, such as only three license plates can be registered for one parking space. Other registrations for the owner are non-fixed quotas and often have a certain time limit, such as expiring after one day. If the owner forgets to register or the registration expires, it will still be identified as a parking space occupied, resulting in misjudgment and affecting the user experience. Summary of the invention

[0005] The present invention provides a parking space occupying method and system based on face recognition, which reduces the probability of misjudgment events and improves user experience.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a parking space occupying method based on face recognition, comprising:

[0007] When it is identified that the first vehicle parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space, photographing facial images of all passengers in the first vehicle through a camera to obtain a first facial image set;

[0008] Determining whether a first facial image database preset by the garage access control system has stored a facial image matching the first facial image set;

[0009] If yes, determining whether the matched facial image is associated with the first owner's parking space;

[0010] If not, sending the first face image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space;

[0011] When it is determined that the matched facial image is associated with the first owner's parking space, it is confirmed that the first vehicle is parked normally;

[0012] When it is determined that the matched facial image is not associated with the first owner's parking space, determining whether a second facial image database preset by the community property management system has stored a facial image matching the first facial image set;

[0013] If the second facial image database stores facial images that match the first facial image set, and the matched facial images in the second facial database are associated with the first owner's parking space, it is confirmed that the first vehicle is parked normally; otherwise, the first facial image set is sent to the first owner for the first owner to confirm whether the first vehicle occupies the parking space.

[0014] Furthermore, before determining whether the second facial image database preset by the residential property management system has stored facial images matching the first facial image set, the method further includes:

[0015] Extracting facial features of each image in the first facial image set, and judging whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to a preset kinship recognition model;

[0016] If there is a kinship relationship, sending the first face image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space;

[0017] If there is no kinship relationship, the step of determining whether a second facial image database preset by the community property management system has stored facial images matching the first facial image set is executed.

[0018] Furthermore, before identifying that the first vehicle parked in the first owner parking space is different from the vehicle registered in the first owner parking space, the method further includes:

[0019] Obtaining a license plate photo of a first vehicle parked in the first owner's parking space taken by a camera, and determining whether the first vehicle is a vehicle registered in the first owner's parking space based on the license plate photo;

[0020] If so, the process ends; otherwise, it is confirmed that the first vehicle currently parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space.

[0021] Furthermore, the first facial image database is set and managed by the garage access control system;

[0022] The second facial image database is set up and managed by the residential property management system;

[0023] The residential property management system and the garage access control system are independent systems.

[0024] Accordingly, an embodiment of the present invention further provides a parking space occupying system based on face recognition, comprising: an acquisition module, a first judgment module, a second judgment module, a sending module, a first confirmation module, a third judgment module and a second confirmation module;

[0025] The acquisition module is used to capture facial images of all passengers in the first vehicle through a camera to obtain a first facial image set when it is identified that the first vehicle parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space;

[0026] The first determination module is used to determine whether a first facial image database preset by the garage access control system has stored a facial image matching the first facial image set;

[0027] The second judgment module is used to judge whether the matched face image is associated with the first owner parking space when the judgment result of the first judgment module is yes;

[0028] The sending module is used for sending the first face image set to the first owner when the judgment result of the first judgment module is no, so that the first owner can confirm whether the first vehicle occupies the parking space;

[0029] The first confirmation module is used to confirm that the first vehicle is parked normally when the second judgment module determines that the matched facial image is associated with the first owner's parking space;

[0030] The third judgment module is used to judge whether a second facial image database preset by the community property management system has stored a facial image matching the first facial image set when the second judgment module determines that the matched facial image is not associated with the first owner's parking space;

[0031] The second confirmation module is used to confirm that the first vehicle is parked normally when the third judgment module determines that the second facial image database stores facial images matching the first facial image set, and the matched facial images in the second facial database are associated with the first owner's parking space; otherwise, the sending module is also used to send the first facial image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space.

[0032] Furthermore, the parking space occupying system based on face recognition further includes: a fourth judgment module;

[0033] The fourth judgment module is used to extract the facial features of each image in the first facial image set before the third judgment module performs judgment, and judge whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to a preset kinship recognition model;

[0034] If the fourth judgment module determines that there is a kinship relationship, the sending module sends the first face image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space;

[0035] If the fourth judgment module determines that there is no kinship relationship, the third judgment module executes: judging whether a second facial image database preset by the community property management system has stored facial images matching the first facial image set.

[0036] Furthermore, the parking space occupying system based on face recognition further includes: a fifth judgment module;

[0037] The fifth judgment module is used to obtain a license plate photo of the first vehicle parked in the first owner's parking space taken by a camera, and determine whether the first vehicle is the vehicle registered in the first owner's parking space based on the license plate photo; if so, end this process; otherwise, confirm that the first vehicle currently parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space.

[0038] The embodiments of the present invention have the following beneficial effects:

[0039] The present invention provides a parking space occupation method and system based on face recognition. When the method learns that the parking space of the first owner is parked, the facial images of all passengers in the vehicle are collected by a camera, and the first facial recognition is performed to determine whether it is stored in the database of the garage access control system, and then the second judgment is performed to determine whether the matched facial image is associated with the parking space of the first owner, and finally the third judgment is performed to determine whether the facial image in the car is stored in the database of the community property management system. If no result can be obtained in the three judgments, the first facial image set is sent to the first owner, and the owner confirms whether the parking space is occupied. Compared with the prior art that only relies on whether the parking space is associated with the license plate number to determine whether the parking space is occupied, the present invention optimizes the entire judgment logic, reduces the probability of misjudgment events, and improves user experience while minimizing manual intervention.

[0040] Furthermore, before performing the third facial image judgment, the present invention performs relative image judgment to determine whether the passenger in the vehicle has a relative relationship with the owner, thereby further reducing the probability of misjudgment and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of an embodiment of a parking space occupying method based on face recognition provided by the present invention;

[0042] Figure 2 It is a structural schematic diagram of an embodiment of a parking space occupying system based on face recognition provided by the present invention. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] It should be noted that the step numbers in the text are only for the convenience of explaining the specific embodiment and do not limit the order of execution of the steps. The method provided in this embodiment can be executed by a related server, and the following description will be given by taking the server as the execution subject as an example.

[0045] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of an embodiment of a parking space occupying method based on face recognition provided by the present invention. Figure 1 As shown, the method includes steps 101 to 107, and each step is specifically as follows:

[0046] Step 101: When it is identified that a first vehicle parked in a first owner's parking space is different from a vehicle registered in the first owner's parking space, facial images of all passengers in the first vehicle are captured by a camera to obtain a first facial image set.

[0047] In this embodiment, before step 101, it also includes: obtaining a license plate photo of the first vehicle parked in the first owner's parking space taken by a camera, and judging whether the first vehicle is the vehicle registered in the first owner's parking space according to the license plate photo; if so, the process ends; otherwise, confirming that the first vehicle currently parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space. In this embodiment, a camera is used to photograph whether there is a car parked in each owner's parking space, so as to identify whether the parking space is idle or occupied, and then the license plate photo is identified to confirm whether the license plate number is a registered license plate number, so as to determine whether the first vehicle is the owner's vehicle. For a community, an owner's parking space usually only gives the owner two to three registration quotas to avoid too many foreign vehicles and inconvenience in management.

[0048] In this embodiment, one camera may correspond to one parking space, or one camera may correspond to multiple parking spaces. The number of cameras may be adjusted according to actual conditions.

[0049] As an example of this embodiment, the method for identifying whether the currently parked vehicle is a registered vehicle also includes: detecting the parking space usage status through radar recognition, infrared recognition and other technologies, and then combining camera photography of license plate numbers and other technologies to determine whether the parking space is occupied.

[0050] In this embodiment, after parking the vehicle, people will get off the vehicle and enter the community. At this time, the camera in the parking lot can capture the facial images of all passengers in the first vehicle to form a first facial image set. The camera that photographs the passengers can be, but is not limited to, a camera that photographs the license plate, or other cameras (such as a camera that photographs another parking space), or other high-precision facial image acquisition devices. For example, the access control device when entering the community building from the parking lot records the facial images of people entering the community building through the access control device, thereby forming a first facial image set.

[0051] Step 102 : Determine whether a first facial image database preset in the garage access control system has stored a facial image matching the first facial image set; if so, execute step 103 ; otherwise, execute step 107 .

[0052] In this embodiment, the garage access control system is pre-set with a first facial image database, which is used to record the facial images corresponding to each owner's parking space. One owner's parking space can match multiple facial images, which overcomes the problem of limited registration quotas in the prior art, and multiple facial images in one parking space will not cause too many external vehicles to be unmanageable. For example, if an owner or a user who has entered facial images into the facial image database drives a new car (without license plate entered) into the community and parks it in his own parking space, there will be no false alarm that the parking space is occupied.

[0053] In this embodiment, if a match is found, step 103 is executed. If a match is not found, the parking space may be occupied, and the first face image set is sent to the first owner for the first owner to confirm whether the first vehicle occupies the parking space. The first owner can know whether it is a visitor or a relative by checking the corresponding face image, so as to determine whether the vehicle is parked normally. The face image can be sent to the mobile terminal of the first owner via a wireless network or the Internet to improve the real-time and effectiveness of message transmission.

[0054] Step 103: Determine whether the matched facial image is associated with the first owner's parking space; if so, execute step 106; otherwise, execute step 104.

[0055] In this embodiment, after matching the first face image set, it is determined whether the face image is associated with the first owner's parking space based on the matching information, so as to prevent owners in the same community from parking their vehicles in other people's parking spaces. For example, if the parking space of owner A is parked by his visitors or relatives, owner A parks his vehicle in the parking space of owner B. This step can prevent the vehicles of owners from being parked randomly and reduce the situation where the parking space is occupied by other owners.

[0056] In this embodiment, if the judgment result is associated, it means that the passenger of the vehicle has a visitor or relative relationship with the first owner, so this parking is considered normal parking, and step 106 is executed. If the judgment result is not associated, step 104 is executed for further determination.

[0057] Step 104: Determine whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set; if so, execute step 105; otherwise, execute step 107.

[0058] In this embodiment, the community property management system is pre-set with a second face image database, the data source of which is the face images collected by the community property management system in various aspects, such as the community access system, the community security system, the community visitor system, the community logistics system, etc. That is, the face images that can be collected in the smart community, and the second face image database is established based on the data, and then through the judgment of step 104, it is determined whether the passenger has been active in the community. This step further matches the first face image set to avoid the situation where a person who drives less often drives into the garage but generates a false alarm because the face image is not entered into the first face database. Since the present invention no longer uses the method of associating parking spaces with license plates, it may occur that different users drive the same car. For example, the owner is the main driver of the vehicle. One day, the owner's father drives the vehicle to the parking space, but because the owner's father's face image has not been actively entered into the first face image database before, his face image cannot be found in the first face image database, and the matching fails. However, since the person lives and moves in the community, his face image will be automatically entered into the second face image database. The secondary judgment in step 104 can reduce the occurrence of misjudgment and improve accuracy.

[0059] As an example of this embodiment, in step 103, the process jumps to step 104. Before step 104 is executed, the process may further include: extracting facial features of each image in the first facial image set, and judging whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to a preset kinship recognition model; if there is a kinship relationship, executing step 107 or executing step 106; if there is no kinship relationship, executing step 104. In this example, by setting a kinship recognition model, the facial features of the facial image set are accurately recognized to judge whether they are relatives of the first owner. The kinship recognition model generally recognizes facial kinship relationships through a convolutional neural network model. Specifically, a convolutional neural network model is obtained by training multiple training image sets and a binary classification loss function, and then two facial images are input into the convolutional neural network model. The convolutional neural network model can output whether the two facial images are kinship or non-kinship. When it is confirmed to be a kinship relationship, it can be directly confirmed as normal parking, or the first owner can make a second confirmation to improve the fault tolerance rate.

[0060] In this embodiment, the first face image database is set and managed by the garage access control system; the second face image database is set and managed by the community property management system. The community property management system and the garage access control system are independent systems. The present invention uses the first face image database to achieve accurate face recognition, and then uses the second face image database to achieve a wider range of face recognition, which can take into account both accuracy and breadth, and further reduce the probability of false alarms.

[0061] Step 105: Determine whether the matched facial image in the second facial database is associated with the first owner's parking space; if so, execute step 106; otherwise, execute step 107.

[0062] In this embodiment, in order to avoid parking space occupation between owners, step 105 is executed to determine whether the face image is associated with the first owner's parking space. For example, the unit where the user lives is matched through the face image, and then the corresponding owner's parking space information is queried to finally determine whether the two are associated.

[0063] Step 106: Confirm that the first vehicle is parked normally.

[0064] Step 107: Send the first face image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space.

[0065] As an example of an embodiment of the present invention, for the facial image registered by the owner, the user can define its usage rights according to actual conditions, such as one day, one year or forever, etc., without the need for multiple entry, thereby improving the user experience.

[0066] Accordingly, see Figure 2 , Figure 2 1 is a schematic diagram of a parking space occupation system based on face recognition provided by the present invention. The system includes: an acquisition module 201, a first judgment module 202, a second judgment module 203, a sending module 204, a first confirmation module 205, a third judgment module 206 and a second confirmation module 207.

[0067] The acquisition module 201 is used to obtain a first facial image set by capturing facial images of all passengers in the first vehicle through a camera when it is identified that the first vehicle parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space.

[0068] The first determination module 202 is used to determine whether a first facial image database preset by the garage access control system has stored a facial image matching the first facial image set.

[0069] The second judgment module 203 is used to judge whether the matched face image is associated with the first owner parking space when the judgment result of the first judgment module 202 is yes.

[0070] The sending module 204 is used for sending the first face image set to the first owner when the judgment result of the first judgment module 202 is no, so that the first owner can confirm whether the first vehicle occupies the parking space.

[0071] The first confirmation module 205 is used to confirm that the first vehicle is parked normally when the second judgment module 203 determines that the matched facial image is associated with the first owner's parking space.

[0072] The third judgment module 206 is used to judge whether the second facial image database preset by the community property management system has stored a facial image matching the first facial image set when the second judgment module 203 determines that the matched facial image is not associated with the first owner's parking space.

[0073] The second confirmation module 207 is used to confirm that the first vehicle is parked normally when the third judgment module 206 determines that the second facial image database stores facial images that match the first facial image set, and the matched facial images in the second facial database are associated with the first owner's parking space; otherwise, the sending module 204 is also used to send the first facial image set to the first owner, so that the first owner can confirm whether the first vehicle occupies the parking space.

[0074] As an example of this embodiment, the parking space occupation system also includes a fourth judgment module. The fourth judgment module is used to extract the facial features of each image in the first facial image set before the third judgment module 206 performs the judgment, and judge whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to the preset kinship recognition model; if the fourth judgment module determines that there is a kinship relationship, the sending module 204 sends the first facial image set to the first owner, so that the first owner can confirm whether the first vehicle occupies the parking space; if the fourth judgment module determines that there is no kinship relationship, the third judgment module 206 performs: judging whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set.

[0075] As an example of this embodiment, the parking space occupation system further includes a fifth judgment module. The fifth judgment module is used to obtain a license plate photo of the first vehicle parked in the first owner's parking space taken by a camera, and determine whether the first vehicle is the vehicle registered in the first owner's parking space based on the license plate photo; if so, end this process; otherwise, confirm that the first vehicle currently parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space.

[0076] The more detailed working principle and process of this system can refer to but is not limited to the parking space occupying method recorded above.

[0077] As can be seen from the above, the present invention provides a parking space occupation method and system based on face recognition. When the method learns that the parking space of the first owner is parked, the facial images of all passengers in the vehicle are collected by a camera, and the first facial recognition is performed to determine whether it is stored in the database of the garage access control system, and then a second judgment is performed to determine whether the matched facial image is associated with the parking space of the first owner. Finally, a third judgment is performed to determine whether the facial image in the car is stored in the database of the community property management system. If no result can be obtained in the three judgments, the first facial image set is sent to the first owner, and the owner confirms whether the parking space is occupied. Compared with the prior art that only relies on whether the parking space is associated with the license plate number to determine whether the parking space is occupied, the present invention optimizes the entire judgment logic, reduces the probability of misjudgment events, and improves user experience while minimizing human intervention.

[0078] Furthermore, before performing the third facial image judgment, the present invention performs relative image judgment to determine whether the passenger in the vehicle has a relative relationship with the owner, thereby further reducing the probability of misjudgment and improving user experience.

[0079] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

[0080] Those skilled in the art can understand that all or part of the processes in the above embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

Claims

1. A parking space occupying method based on face recognition, characterized in that: include: When it is identified that the first vehicle parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space, photographing facial images of all passengers in the first vehicle through a camera to obtain a first facial image set; Determining whether a first facial image database preset by the garage access control system has stored a facial image matching the first facial image set; If yes, determining whether the matched facial image is associated with the first owner's parking space; If not, sending the first face image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space; When it is determined that the matched facial image is associated with the first owner's parking space, it is confirmed that the first vehicle is parked normally; When it is determined that the matched facial image is not associated with the parking space of the first owner, it is determined whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set; wherein, before determining whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set, it also includes: extracting facial features of each image in the first facial image set, and determining whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to a preset kinship recognition model; if there is a kinship relationship, the first facial image set is sent to the first owner for the first owner to confirm whether the first vehicle occupies the parking space; if there is no kinship relationship, the step of determining whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set; If the second facial image database stores facial images that match the first facial image set, and the matched facial images in the second facial image database are associated with the first owner's parking space, it is confirmed that the first vehicle is parked normally; otherwise, the first facial image set is sent to the first owner for the first owner to confirm whether the first vehicle occupies the parking space.

2. The parking space occupying method based on face recognition according to claim 1 is characterized in that: Before the method identifies that the first vehicle parked in the first owner parking space is different from the vehicle registered in the first owner parking space, the method further includes: Obtaining a license plate photo of a first vehicle parked in the first owner's parking space taken by a camera, and determining whether the first vehicle is a vehicle registered in the first owner's parking space based on the license plate photo; If so, the process ends; otherwise, it is confirmed that the first vehicle currently parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space.

3. The parking space occupying method based on face recognition according to claim 1 is characterized in that: The first facial image database is set and managed by the garage access control system; The second facial image database is set up and managed by the residential property management system; The residential property management system and the garage access control system are independent systems.

4. A parking space occupying system based on face recognition, characterized in that: include: An acquisition module, a first judgment module, a second judgment module, a sending module, a first confirmation module, a third judgment module and a second confirmation module; The acquisition module is used to capture facial images of all passengers in the first vehicle through a camera to obtain a first facial image set when it is identified that the first vehicle parked in the first owner's parking space is different from the vehicle registered in the first owner's parking space; The first determination module is used to determine whether a first facial image database preset by the garage access control system has stored a facial image matching the first facial image set; The second judgment module is used to judge whether the matched face image is associated with the first owner parking space when the judgment result of the first judgment module is yes; The sending module is used for sending the first face image set to the first owner when the judgment result of the first judgment module is no, so that the first owner can confirm whether the first vehicle occupies the parking space; The first confirmation module is used to confirm that the first vehicle is parked normally when the second judgment module determines that the matched facial image is associated with the first owner's parking space; The third judgment module is used to judge whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set when the second judgment module determines that the matched facial image is not associated with the first owner's parking space; wherein, before judging whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set, a fourth judgment module is also used, and the fourth judgment module is used to extract facial features of each image in the first facial image set before the third judgment module performs judgment, and judge whether there is a kinship relationship between each image in the first facial image set and the facial image of the first owner according to a preset kinship recognition model; if the fourth judgment module determines that there is a kinship relationship, the sending module sends the first facial image set to the first owner, so that the first owner can confirm whether the first vehicle occupies the parking space; if the fourth judgment module determines that there is no kinship relationship, the third judgment module performs: judging whether the second facial image database preset by the community property management system has stored facial images matching the first facial image set; The second confirmation module is used to confirm that the first vehicle is parked normally when the third judgment module determines that the second facial image database stores facial images matching the first facial image set, and the matched facial images in the second facial image database are associated with the first owner's parking space; otherwise, the sending module is also used to send the first facial image set to the first owner so that the first owner can confirm whether the first vehicle occupies the parking space.

5. The parking space occupying system based on face recognition according to claim 4 is characterized in that: Also includes: The fifth judgment module; The fifth judgment module is used to obtain a license plate photo of the first vehicle parked in the first owner's parking space taken by a camera, and determine whether the first vehicle is the vehicle registered in the first owner's parking space according to the license plate photo; if so, end this process; Otherwise, it is confirmed that the first vehicle currently parked in the first owner parking space is different from the vehicle registered in the first owner parking space.

6. The parking space occupying system based on face recognition according to claim 4 is characterized in that: The first facial image database is set and managed by the garage access control system; The second facial image database is set up and managed by the residential property management system; The residential property management system and the garage access control system are independent systems.

Images