Parking lot monitoring system

Abstract

The invention discloses a parking lot monitoring system, belongs to the technical field of parking lot monitoring, and solves the problem that when a vehicle is stolen at late night or afternoon, security personnel cannot find the theft in time, and finally loss of a vehicle owner is caused. Comprising a monitoring module, a data temporary storage module and a data processing module, the output end of the monitoring module is coupled with the input end of the data processing module, the data processing module is coupled with the data temporary storage module, and the monitoring module is used for collecting monitoring videos of vehicles parked in a parking lot. And the data temporary storage module is used for storing and reading the monitoring video. Parking lot videos are collected through the monitoring module, whether a person is beside a vehicle is identified, and one-minute historical videos are traced back to check whether vehicle lamps flicker or not. If not, the theft risk possibly exists, then whether a vehicle door or a trunk is opened or not is judged, and finally, security personnel are reminded to prevent vehicle loss through early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of parking lot monitoring, and in particular to a parking lot monitoring system. Background Art

[0002] Underground parking garages are common parking facilities in modern cities. They are usually built in the basement or underground space of buildings, aiming to provide efficient and safe parking services for densely populated urban areas. Due to the scarcity of urban land resources, underground parking garages have effectively alleviated the problem of ground parking difficulties by making full use of underground space. Its design usually focuses on maximizing the use of space and adopts an intelligent management system to achieve rapid navigation and reservation functions for parking spaces. At the same time, the structure of underground parking garages is mostly concrete or steel structure, with good load-bearing capacity and durability. In order to ensure safety, parking garages are usually equipped with advanced fire protection systems, monitoring equipment and emergency evacuation passages to deal with emergencies. In addition, underground parking garages can also avoid direct sunlight, effectively protect vehicles from external weather factors, and improve the maintenance status of vehicles. Although the construction cost of underground parking garages is relatively high, they are still an indispensable and important facility in urban environments with tight land and huge parking demand, which greatly facilitates the parking needs of residents and merchants and improves the overall efficiency of urban transportation.

[0003] At present, underground parking lots are more popular among car owners. Not only can they separate people and vehicles, but they can also prevent vehicles from being affected by the external weather environment. At the same time, if a vehicle is parked in an underground parking lot, whether it is stolen or scratched, it can be captured through surveillance. However, the current surveillance video is mainly judged by the naked eye of security personnel to determine whether there are outsiders stealing and prying the vehicle. A small number of security personnel need to observe a large number of surveillance video images at the same time. As a result, when theft occurs in the vehicle late at night or in the afternoon, the security personnel cannot discover it in time, which ultimately causes losses to the car owner.

[0004] Therefore, a parking lot monitoring system is proposed to solve or alleviate the above problems. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a parking lot monitoring system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A parking lot monitoring system includes a monitoring module, a data storage module, and a data processing module. The output end of the monitoring module is coupled to the input end of the data processing module, the data processing module is coupled to the data storage module, the monitoring module is used to collect monitoring videos of vehicles parked in the parking lot, the data storage module is used to store and read the monitoring videos, and the data processing module is used to store the monitoring videos in the data storage module and read the monitoring videos from the data storage module to identify whether the parked vehicles have a theft risk.

[0008] Preferably, the monitoring module comprises a camera, which captures monitoring videos of vehicles parked in the parking lot and feeds the videos back to the data processing module.

[0009] Preferably, the data temporary storage module includes a temporary register, and the temporary register is used to store and read the surveillance video.

[0010] Preferably, the data processing module includes a central processing unit, and the central processing unit is used to store the surveillance video in the data temporary storage module and read the surveillance video from the data temporary storage module to identify whether the parked vehicle has a theft risk.

[0011] Preferably, the data processing module is used to store the surveillance video in the data temporary storage module, and read the surveillance video from the data temporary storage module to identify whether the parked vehicle has a theft risk, including the following steps:

[0012] Get the video frame of the current surveillance video;

[0013] Use the target detection model to detect the vehicle in the video frame of the current surveillance video and obtain the vehicle's bounding box B vehicle =DetectVehicle(F current )=(x min ,y min ,x max ,y max ) as the vehicle coordinate information, where DetectVehicle is the target detection model, and F current is the video frame of the current surveillance video;

[0014] Bounding box B for the vehicle vehicle Expand by a certain multiple to cover people close to the vehicle;

[0015] Use the target detection model to enlarge the bounding box of the vehicle B vehicle Perform detection and return the position bounding box B of the person after detecting the person close to the vehicle staff =DetectStaff(F current ,B vehicle );

[0016] After detecting a person approaching the vehicle and returning the person's position boundary box, the corresponding historical frame F is extracted by going back 1 minute through the video frame of the current surveillance video. history .

[0017] Preferably, the data processing module is used to store the surveillance video in the data temporary storage module, and read the surveillance video from the data temporary storage module to identify whether the parked vehicle has a theft risk, and further includes the following steps:

[0018] The target detection model is used to extract the vehicle headlight area from the historical frames and the video frames of the current surveillance video.

[0019] Calculate the average brightness of the vehicle area in the historical frames and the video frame of the current surveillance video Among them, |B headlight | is the number of pixels in the headlight area, I(x,y,t) is the pixel value at point (x,y);

[0020] Set the judgment threshold of brightness change to ∈, and compare the brightness change of two consecutive frames ΔL(t) = |L headlight (t+1)-L headlight (t)|, if ΔL(t)>∈, it is considered that the car lights are flashing, and the output result is that there is no theft risk. Otherwise, it is considered that the car lights are not flashing, and the output result is that there may be a theft risk.

[0021] Preferably, the data processing module is used to store the surveillance video in the data temporary storage module, and read the surveillance video from the data temporary storage module to identify whether the parked vehicle has a theft risk, and further includes the following steps:

[0022] Continuously read the video frame F of the current surveillance video current , and the vehicle's bounding box B vehicle ;

[0023] The vehicle's bounding box B vehicle Divided into multiple sub-areas, the multiple sub-areas include the door area B door and trunk area B trunk ;

[0024] In the door area B door and trunk area B trunk The object detection algorithm is used to detect whether the door or trunk is open and output the door area B. door and trunk area B trunk If the door is open, then S door =1, if the door is not opened, then S door =0, if the trunk is open, then S trunk=1, if the trunk is not opened, then S trunk =0, the object detection algorithm is S door =DetectDoorStatus(F current ,B vehicle ), S trunk =DetectTrunkStatus(F current ,B vehicle );

[0025] According to the door area B door and trunk area B trunk The change of state can be used to determine whether there is a risk of theft. If S door +S trunk ≥1, it means there is no theft risk. door +S trunk If the value is less than 1, it indicates that there is a risk of theft and an early warning is issued.

[0026] Preferably, the target detection model includes a YOLO model.

[0027] The present invention has the following beneficial effects:

[0028] The present invention can collect a monitoring video through the monitoring module, and the content of the monitoring video is that the vehicle is parked in the parking space. Through the monitoring system, it can be identified whether there is someone next to the vehicle parked in the parking space. If it is identified that there is someone next to the vehicle parked in the parking space, the historical video of 1 minute backward from the current time is retrieved to identify whether the headlights of the vehicle parked in the parking space in the historical video flash and then remain on. If the headlights have not flashed or remained on, it is considered that there may be a theft risk; if the headlights have flashed and are on, it is considered that there is no theft risk. Then further judgment is made to identify whether the vehicle parked in the parking space has its door open or its trunk open. If the door or the trunk is open, it means that there is no theft risk; if the door and the trunk are not opened, it means that there is a theft risk. Finally, an early warning is issued, so as to remind the security personnel who observe and monitor, and to timely remind the security personnel if they find that there are people stealing or damaging vehicles in the monitoring video in the parking lot, so as to avoid losses of vehicles parked in the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0030] Figure 1It is a structural block diagram of the present invention.

[0031] 1. Monitoring module; 2. Data processing module; 3. Data temporary storage module. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0033] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0034] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0035] In the description of the present invention, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of the invention is conventionally placed when in use, or are the orientations or positional relationships conventionally understood by those skilled in the art. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0036] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0037] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] A parking lot monitoring system, such as Figure 1 As shown, it includes a monitoring module 1, a data storage module 3, and a data processing module 2. The monitoring module 1 includes a camera, which captures monitoring videos of vehicles parked in a parking lot and feeds them back to the data processing module 2. The data storage module 3 includes a register, which is used to store and read the monitoring videos. The data processing module 2 includes a central processing unit, which is used to store the monitoring videos in the data storage module 3 and read the monitoring videos from the data storage module 3 to identify whether the parked vehicles are at risk of theft.

[0039] The output end of the monitoring module 1 is coupled to the input end of the data processing module 2, and the data processing module 2 is coupled to the data temporary storage module 3. The monitoring module 1 is used to collect monitoring videos of parked vehicles in the parking lot, and the data temporary storage module 3 is used to store and read the monitoring videos. The data processing module 2 is used to store the monitoring videos in the data temporary storage module 3 and read the monitoring videos from the data temporary storage module 3 to identify whether the parked vehicles are at risk of theft.

[0040] Preferably, the data processing module 2 is used to store the surveillance video in the data temporary storage module 3, and read the surveillance video from the data temporary storage module 3 to identify whether the parked vehicle has a theft risk, including the following steps:

[0041] Get the video frame of the current surveillance video;

[0042] Use the target detection model to detect the vehicle in the video frame of the current surveillance video and obtain the vehicle's bounding box B vehicle =DetectVehicle(F current )=(x min ,y mi n,x max ,y max ) as the vehicle coordinate information, where DetectVehicle is the target detection model, and F current is the video frame of the current surveillance video;

[0043] Bounding box B for the vehicle vehicle Expand by a certain multiple to cover people close to the vehicle;

[0044] Use the target detection model to enlarge the bounding box of the vehicle B vehicle Perform detection and return the position bounding box B of the person after detecting the person close to the vehicle staff =DetectStaff(F current ,B vehicle );

[0045] After detecting a person approaching the vehicle and returning the person's position boundary box, the corresponding historical frame F is extracted by going back 1 minute through the video frame of the current surveillance video. history .

[0046] Preferably, the data processing module 2 is used to store the surveillance video in the data temporary storage module 3, and read the surveillance video from the data temporary storage module 3 to identify whether the parked vehicle has a theft risk, and also includes the following steps:

[0047] The target detection model is used to extract the vehicle headlight area from the historical frames and the video frames of the current surveillance video.

[0048] Calculate the average brightness of the vehicle area in the historical frames and the video frame of the current surveillance video Among them, |B headlight | is the number of pixels in the headlight area, I(x,y,t) is the pixel value at point (x,y);

[0049] Set the judgment threshold of brightness change to ∈, and compare the brightness change of two consecutive frames ΔL(t) = |L headlight (t+1)-L headlight (t)|, if ΔL(t)>∈, it is considered that the car lights are flashing, and the output result is that there is no theft risk. Otherwise, it is considered that the car lights are not flashing, and the output result is that there may be a theft risk.

[0050] Preferably, the data processing module 2 is used to store the surveillance video in the data temporary storage module 3, and read the surveillance video from the data temporary storage module 3 to identify whether the parked vehicle has a theft risk, and also includes the following steps:

[0051] Continuously read the video frame F of the current surveillance video current , and the vehicle's bounding box B vehicle ;

[0052] The vehicle's bounding box B vehicle Divided into multiple sub-areas, the multiple sub-areas include the door area B door and trunk area B trunk ;

[0053] In the door area B door and trunk area B trunk The object detection algorithm is used to detect whether the door or trunk is open and output the door area B. door and trunk area B trunk If the door is open, then S door =1, if the door is not opened, then S door =0, if the trunk is open, then S trunk =1, if the trunk is not opened, then Strunk =0, the object detection algorithm is S door =DetectDoorStatus(F current ,B vehicle ), S trunk =DetectTrunkStatus(F current ,B vehicle );

[0054] According to the door area B door and trunk area B trunk The change of state can be used to determine whether there is a risk of theft. If S door +S trunk ≥1, it means there is no theft risk. door +S trunk If the value is less than 1, it indicates that there is a risk of theft and an early warning is issued.

[0055] Preferably, the target detection model includes a YOLO model.

[0056] The present invention uses a parking lot monitoring system to monitor the vehicle status in the parking lot in real time. With the help of real-time video data collected by the monitoring module 1, it can effectively identify abnormal behaviors around the vehicle, analyze and judge, and timely warn of potential theft or damage risks, thereby ensuring the safety of vehicles parked in the parking lot.

[0057] Specifically, the present invention monitors vehicles in parking spaces through a monitoring system, and first identifies whether there are people staying around the vehicle. If a suspicious person is detected next to the vehicle, the system will automatically retrieve the historical monitoring video 1 minute before the current moment for further analysis. In this historical video, the system will focus on checking the status of the vehicle's lights to determine whether the lights are flashing or remain on. If it is found that the vehicle's lights are not flashing or remain on, the system determines that the vehicle may be at risk of theft.

[0058] If the vehicle's lights do flash and remain on in the historical video, it means that the vehicle may not have encountered external interference. The system will consider the theft risk to be low and continue monitoring. However, if the lights do not flash and remain on, the risk assessment of the vehicle will be further strengthened, and it will be considered that there may be safety hazards.

[0059] On this basis, the system will further monitor the status of the vehicle, especially whether the doors and trunk are open. Through surveillance video analysis, the system can automatically identify whether the vehicle doors or trunk are open. If the vehicle doors or trunk are open, the system will judge it as normal and believe that the vehicle has a low risk of theft, indicating that the vehicle may have been opened or checked by the owner. However, if the doors and trunk are not opened and there are suspicious people staying next to the vehicle, the system will further judge that the vehicle has a high risk of theft.

[0060] Through these layers of analysis and judgment, the monitoring system of the present invention can provide timely safety warnings for the security personnel of the parking lot. Once a potential theft risk is detected, the system will immediately send an alarm message to the security personnel to remind them to pay attention to the safety status of the vehicle, thereby helping the security personnel to respond quickly and avoid the loss of vehicles in the parking lot.

[0061] In summary, the present invention can comprehensively analyze the safety status of vehicles in the parking lot through the monitoring system combined with historical video backtracking, headlight flashing detection, door and trunk status and other identifications, and issue early warnings in time when there is a risk, ensuring that security personnel can take measures in the shortest time, thereby effectively preventing theft and vandalism.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A parking lot monitoring system, characterized in that: The invention comprises a monitoring module (1), a data temporary storage module (3), and a data processing module (2); the output end of the monitoring module (1) is coupled to the input end of the data processing module (2); the data processing module (2) is coupled to the data temporary storage module (3); the monitoring module (1) is used to collect monitoring videos of vehicles parked in a parking lot; the data temporary storage module (3) is used to store and read the monitoring videos; the data processing module (2) is used to store the monitoring videos in the data temporary storage module (3) and read the monitoring videos from the data temporary storage module (3) to identify whether the parked vehicles have a theft risk.

2. A parking lot monitoring system according to claim 1, characterized in that: The monitoring module (1) comprises a camera, which captures monitoring video of vehicles parked in the parking lot and feeds it back to the data processing module (2).

3. A parking lot monitoring system according to claim 1, characterized in that: The data temporary storage module (3) comprises a temporary storage device, and the temporary storage device is used to store and read the monitoring video.

4. A parking lot monitoring system according to claim 1, characterized in that: The data processing module (2) comprises a central processing unit, which is used to store the monitoring video in the data temporary storage module (3) and read the monitoring video from the data temporary storage module (3) to identify whether the parked vehicle has a theft risk.

5. A parking lot monitoring system according to claim 1, characterized in that: The data processing module (2) is used to store the surveillance video in the data temporary storage module (3), and read the surveillance video from the data temporary storage module (3) to identify whether the parked vehicle has a theft risk, comprising the following steps: Get the video frame of the current surveillance video; Use the target detection model to detect the vehicle in the video frame of the current surveillance video and obtain the vehicle's bounding box B vehicle =DetectVehicle(F current )=(x min ,y min ,x max ,y max ) as the vehicle coordinate information, where DetectVehicle is the target detection model, and F current is the video frame of the current surveillance video; Bounding box B for the vehicle vehicle Expand by a certain multiple to cover people close to the vehicle; Use the target detection model to enlarge the bounding box of the vehicle B vehicle Perform detection and return the position bounding box B of the person after detecting the person close to the vehicle staff =DetectStaff(F current ,B vehicle ); After detecting a person approaching the vehicle and returning the person's position boundary box, the corresponding historical frame F is extracted by going back 1 minute through the video frame of the current surveillance video. history .

6. A parking lot monitoring system according to claim 5, characterized in that: The data processing module (2) is used to store the surveillance video in the data temporary storage module (3), and read the surveillance video from the data temporary storage module (3) to identify whether the parked vehicle has a theft risk, and also includes the following steps: The target detection model is used to extract the vehicle headlight area from the historical frames and the video frames of the current surveillance video. Calculate the average brightness of the vehicle area in the historical frames and the video frame of the current surveillance video Among them, |B headlight | is the number of pixels in the headlight area, I(x,y,t) is the pixel value at point (x,y); Set the judgment threshold of brightness change to ∈, and compare the brightness change of two consecutive frames ΔL(t) = |L headlight (t+1)-L headlight (t)|, if ΔL(t)>∈, it is considered that the car lights are flashing, and the output result is that there is no theft risk. Otherwise, it is considered that the car lights are not flashing, and the output result is that there may be a theft risk.

7. A parking lot monitoring system according to claim 6, characterized in that: The data processing module (2) is used to store the surveillance video in the data temporary storage module (3), and read the surveillance video from the data temporary storage module (3) to identify whether the parked vehicle has a theft risk, and also includes the following steps: Continuously read the video frame F of the current surveillance video current , and the vehicle's bounding box B vehicle ; The vehicle's bounding box B vehicle Divided into multiple sub-areas, the multiple sub-areas include the door area B door and trunk area B trunk ; In the door area B door and trunk area B trunk The object detection algorithm is used to detect whether the door or trunk is open and output the door area B. door and trunk area B trunk If the door is open, then S door =1, if the door is not opened, then S door =0, if the trunk is open, then S trunk =1, if the trunk is not opened, then S trunk =0, the object detection algorithm is S door =DetectDoorStatus(F current ,B vehicle ), S trunk =DetectTrunkStatus(F current ,B vehicle ); According to the door area B door and trunk area B trunk The change of state can be used to determine whether there is a risk of theft. If S door +S trunk ≥1, it means there is no theft risk. If S door +S trunk If the value is less than 1, it indicates that there is a risk of theft and an early warning is issued.

8. A parking lot monitoring system according to claim 7, characterized in that: The target detection model includes a YOLO model.

Images