Intelligent parking lot management system

Abstract

The invention discloses an intelligent parking lot management system, belongs to the technical field of parking lot management, and solves the problem that in an underground parking lot in a dark environment, if a vehicle with dark vehicle paint is parked at an incorrect position and is not in the middle, the parking lot cannot be parked. And when other vehicles are parked into the adjacent parking spaces subsequently, the probability is high, and then the vehicles are scratched. Comprising an entrance monitoring and collecting module, a vehicle data collecting module, a parking space monitoring and collecting module and a vehicle and parking space matching module, and the output end of the entrance monitoring and collecting module is coupled with the input end of the vehicle data collecting module; the output end of the vehicle data acquisition module and the output end of the parking space monitoring acquisition module are both coupled with the input end of the vehicle parking space matching module, and the entrance monitoring acquisition module is used for obtaining an entrance video of a vehicle entering a parking lot and feeding back the entrance video to the vehicle data acquisition module. According to the invention, when the underground parking lot is dark, the parking condition of deep-color vehicles is detected through the vehicle lamps, the problems of incorrect parking and non-centering are analyzed, and the scratch risk is evaluated.

Description

Technical Field

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

[0002] Parking lots are an indispensable part of urban transportation facilities. Their main function is to provide parking space for vehicles and solve the problem of parking difficulties. With the advancement of urbanization, the demand for parking is increasing. Traditional ground parking lots often cannot meet the demand. Therefore, underground parking lots are gradually being widely used as an effective solution. Conventional underground parking lots are usually located in the basement or two floors above the ground of a building. The underground space is used to increase the number of parking spaces and save ground space. Compared with ground parking lots, the advantage of underground parking lots is that they do not occupy precious urban land resources. Especially in the city center or bustling commercial areas, underground parking lots can effectively alleviate parking pressure.

[0003] The design of a conventional underground parking lot usually includes multiple parking spaces, spacious passages and a good ventilation system to ensure smooth access and air circulation for vehicles. To ensure safety, underground parking lots are generally equipped with complete fire-fighting facilities, surveillance cameras and automatic license plate recognition systems. In addition, with the popularity of electric vehicles, many underground parking lots have also added charging piles to meet the charging needs of new energy vehicles. In general, underground parking lots play an important role in solving urban parking problems and improving urban land use efficiency, and are one of the indispensable transportation supporting facilities in modern cities.

[0004] As for underground parking lots, they are not like open-air parking lots. Since they are located underground, they are quite dependent on lighting systems and the power systems that go with them. If the power system stops working or the lighting system is damaged and cannot provide light, then the underground parking lot will not receive natural light and the environment will be dim. However, both the lighting system and the power system are part of the management investment required by the property party for parking lot management. Such investment is directly proportional to the income of the parking lot itself. For parking lots with excess parking spaces, in order to reduce their daily expenses and reduce the consumption incurred by the property party in parking lot management, the investment in lighting and power systems will be reduced in the parking lot. For example, the damaged lighting system is not repaired in time, and the power system is not repaired in time after it is damaged and cannot supply power to the lighting system. As a result, the parking spaces in the underground parking lot are quite dim.

[0005] In a dimly lit underground parking lot, if a vehicle with dark, gray, or dark silver paint is not parked properly or centered, there is a high probability that other vehicles will be scratched and damaged when they park in adjacent parking spaces.

[0006] Therefore, an intelligent parking lot management system is proposed to solve or alleviate the above problems. Summary of the invention

[0007] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent parking lot management system.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] An intelligent parking lot management system includes an entrance monitoring and acquisition module, a vehicle data acquisition module, a vehicle monitoring and acquisition module, and a vehicle parking space matching module. The output end of the entrance monitoring and acquisition module is coupled to the input end of the vehicle data acquisition module. The output ends of the vehicle data acquisition module and the vehicle monitoring and acquisition module are both coupled to the input end of the vehicle parking space matching module. The entrance monitoring and acquisition module is used to obtain an entry video of a vehicle entering a parking lot and feed it back to the vehicle data acquisition module. The vehicle data acquisition module is used to detect the headlight spacing of the vehicle and the light angle difference of the vehicle based on the entry video and feed it back to the vehicle parking space matching module. The vehicle monitoring and acquisition module is used to collect a parking picture after the vehicle is parked in the parking space and feed it back to the vehicle parking space matching module. The vehicle parking space matching module is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and judge the risk of scratching the vehicle when parking.

[0010] Preferably, the entrance monitoring and acquisition module includes an entrance camera, which is used to be arranged at the entrance of the parking lot, and the entrance camera is used to obtain entry videos of vehicles entering the parking lot.

[0011] Preferably, the entrance monitoring and acquisition module is used to obtain the entry video of the vehicle entering the parking lot and feed it back to the vehicle data acquisition module, including the following steps:

[0012] Capture entry video of vehicles entering the parking lot;

[0013] Extract one frame from the entry video at a certain interval to obtain a number of selected frames;

[0014] Grayscale several selected frames to obtain grayscale frames Gt(x,y);

[0015] The grayscale frame Gt(x,y) is fed back to the vehicle data acquisition module.

[0016] Preferably, the vehicle data acquisition module is used to detect the headlight spacing and the light angle difference of the vehicle according to the entry video and feed back to the vehicle parking space matching module, including the following steps:

[0017] Use the canny edge detection method to locate the contour Ci of the headlight on the grayscale frame Gt(x,y);

[0018] The headlight region Bt(x,y) is extracted from the grayscale frame Gt(x,y) by threshold segmentation. Where T is the brightness threshold;

[0019] The light spot is located by the headlight area Bt(x,y) and the headlight contour Ci and the headlight coordinate X is obtained by the centroid method c =|Ci|∑ (x,y)∈Ci X, Y c =|Ci|∑ (x,y)∈Ci Y;

[0020] The coordinates of the left headlight are set as (X L ,Y L ), the coordinates of the right headlight are (X R ,Y R );

[0021] Determine the Euclidean distance between the left and right headlights as d l ights =(X R -X L ) 2 +(Y R -Y L ) 2 ;

[0022] Import the focal length f of the entrance camera and set the distance from the entrance camera to the vehicle to be constant at D, and you can get the headlight spacing of the vehicle

[0023] Set the coordinates of the entrance camera to (X camera ,Y camera ), calculate the vehicle's light angle difference using the headlight light formula

[0024] Set the headlight spacing D real The light angle difference Δθ is fed back to the vehicle parking space matching module.

[0025] Preferably, the vehicle monitoring and acquisition module includes a parking space camera, which is used to be arranged above the parking space, and the parking space camera is used to collect parking images after the vehicle is parked in the parking space.

[0026] Preferably, the vehicle monitoring collection module is used to collect parking images after the vehicle is parked in the parking space and feed them back to the vehicle parking space matching module, including the following steps:

[0027] Capture the parking scene after the vehicle parks in the parking space;

[0028] Grayscale the parking image;

[0029] The grayscaled parking image is fed back to the vehicle parking space matching module.

[0030] Preferably, the vehicle parking space matching module is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and determine the risk of scratching the vehicle when parking, including the following steps:

[0031] Extract the angle difference Δθ of the left and right headlights of the vehicle in the grayscale parking image photo ;

[0032] The angle difference Δθ of the left and right headlights of the vehicle in the parking image photo Compared with the light angle difference Δθ of the vehicle detected by the entry video, if Δθ photo ≤Δθ, the vehicle is considered to be parked straight, otherwise, the vehicle is considered to be parked diagonally.

[0033] Preferably, the vehicle parking space matching module is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and judge the risk of scratching the vehicle when parking, and also includes the following steps:

[0034] If the output result is that the vehicle is parked at an angle, it is considered that there is a high risk of scratching;

[0035] If the output result is that the vehicle is parked straight, the coordinates of the left and right headlights of the vehicle in the grayscale processing parking picture are extracted, the size of the parking space is imported into the parking picture to form the coordinates of the parking space, and the headlight spacing D of the vehicle in the parking picture is calculated. photo , the distance from the left headlight of the vehicle to the left border of the parking space L photo , and the distance R from the right headlight of the vehicle to the left border of the parking space photo The parking space dimensions include L space and W space ;

[0036] judge When the judgment result is 1, the output result is that the vehicle is parked straight on the side of the road, and it is determined that there is a medium risk of scratching. When the judgment result is 0, the output result is that the vehicle is parked straight in the center, and it is determined that there is a low risk of scratching.

[0037] The present invention has the following beneficial effects:

[0038] The present invention can detect the parking condition of the vehicle through the lights of the left and right headlights of the vehicle in the case of dim ambient light in an underground parking lot, especially when a vehicle with dark, gray or dark silver paint is parked in the parking space, and can detect and analyze the situation where the vehicle is parked incorrectly or not centered, and then output the risk of the vehicle being scratched in the parking space. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 It is a structural block diagram of the present invention.

[0041] 1. Entrance monitoring and acquisition module; 2. Vehicle data acquisition module; 3. Vehicle monitoring and acquisition module; 4. Vehicle parking space matching module. DETAILED DESCRIPTION

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] An intelligent parking lot management system, such as Figure 1 As shown, it includes an entrance monitoring and acquisition module 1, a vehicle data acquisition module 2, a vehicle monitoring and acquisition module 3, and a vehicle parking space matching module 4. The entrance monitoring and acquisition module 1 includes an entrance camera, which is used to be set at the entrance of the parking lot, and the entrance camera is used to obtain the entry video of the vehicle entering the parking lot. The vehicle monitoring and acquisition module 3 includes a parking space camera, which is used to be set above the parking space, and the parking space camera is used to collect the parking picture after the vehicle is parked in the parking space. The output end of the entrance monitoring and acquisition module 1 is coupled to the input end of the vehicle data acquisition module 2, and the output ends of the vehicle data acquisition module 2 and the vehicle monitoring and acquisition module 3 are both coupled to the input end of the vehicle parking space matching module 4.

[0049] Among them, the entrance monitoring and acquisition module 1 is used to obtain the entry video of the vehicle entering the parking lot and feed it back to the vehicle data acquisition module 2, the vehicle data acquisition module 2 is used to detect the vehicle's headlight spacing and the vehicle's light angle difference based on the entry video and feed it back to the vehicle parking space matching module 4, the vehicle monitoring and acquisition module 3 is used to collect the parking picture after the vehicle is parked in the parking space and feed it back to the vehicle parking space matching module 4, the vehicle parking space matching module 4 is used to receive the vehicle's headlight spacing, the vehicle's light angle difference and the parking picture, and judge the risk of vehicle parking scratches.

[0050] The present invention is suitable for the poorly lit environment of underground parking lots, especially for parking spaces with dark, gray or dark silver vehicles. It is a solution for monitoring the parking status of vehicles through the vehicle lights. The present invention can detect whether the vehicle is parked properly, including whether it is parked incorrectly or not centered, and then analyze and evaluate the potential risk of the vehicle being scratched in the parking space. By using the lights on the left and right sides of the vehicle as reference points, the present invention can accurately analyze the parking position of the vehicle, thereby outputting a risk assessment of the possible scratches suffered by the vehicle in the parking space. This innovative method not only improves the safety management level of the parking lot, but also provides additional security for car owners to ensure the safety of the vehicle during parking.

[0051] Preferably, the entrance monitoring and acquisition module 1 is used to obtain the entry video of the vehicle entering the parking lot and feed it back to the vehicle data acquisition module 2, including the following steps:

[0052] Capture entry video of vehicles entering the parking lot;

[0053] Extract one frame from the entry video at a certain interval to obtain a number of selected frames;

[0054] Grayscale several selected frames to obtain grayscale frames Gt(x,y);

[0055] The grayscale frame Gt(x,y) is fed back to the vehicle data acquisition module 2.

[0056] Through the above steps, the entrance monitoring and acquisition module 1 can take a picture of the vehicle when the vehicle passes through the parking lot entrance and enters the parking lot, and process the entry video of the vehicle into the parking lot in advance, thereby reducing the computing burden required by the vehicle data acquisition module 2 and speeding up the working efficiency of the entire system.

[0057] Preferably, the vehicle data acquisition module 2 is used to detect the headlight spacing and the light angle difference of the vehicle according to the entry video and feed back to the vehicle parking space matching module 4, including the following steps:

[0058] Use the canny edge detection method to locate the contour Ci of the headlight on the grayscale frame Gt(x,y);

[0059] The headlight area Bt(x,y) is extracted from the grayscale frame Gt(x,y) by threshold segmentation. Where T is the brightness threshold;

[0060] The light spot is located by the headlight area Bt(x,y) and the headlight contour Ci and the headlight coordinate X is obtained by the centroid method c =|Ci|∑ (x,y)∈Ci X, Y c =|Ci|∑ (x,y)∈Ci Y;

[0061] The coordinates of the left headlight are set as (X L ,Y L ), the coordinates of the right headlight are (X R ,Y R );

[0062] Determine the Euclidean distance between the left and right headlights as d l ights =(X R -X L ) 2 +(Y R -Y L ) 2 ;

[0063] Import the focal length f of the entrance camera and set the distance from the entrance camera to the vehicle to be constant at D, and you can get the headlight spacing of the vehicle

[0064] Set the coordinates of the entrance camera to (X camera ,Y camera ), calculate the vehicle's light angle difference using the headlight light formula

[0065] Set the headlight spacing D real The light angle difference Δθ is fed back to the vehicle parking space matching module 4 .

[0066] Through the above steps, the vehicle data acquisition module 2 can obtain the headlight spacing and the light angle difference of the vehicle based on the entry video of the vehicle entering the parking lot after being processed by the entrance monitoring acquisition module 1, and match and judge the situation of subsequent vehicles parked in the parking space through the headlight spacing and the light angle difference of the vehicle, and also reduce the burden of calculations performed by the subsequent vehicle parking space matching module 4, thereby speeding up the working efficiency of the entire system. In addition, through the above steps, the parameters of different vehicles can be distinguished, and even multiple vehicles entering at the same time can be distinguished by the parameters.

[0067] Preferably, the vehicle monitoring and acquisition module 3 is used to collect parking images after the vehicle is parked in the parking space and feed them back to the vehicle parking space matching module 4, including the following steps:

[0068] Capture the parking scene after the vehicle parks in the parking space;

[0069] Grayscale the parking image;

[0070] The grayscaled parking picture is fed back to the vehicle parking space matching module 4 .

[0071] Through the above steps, the vehicle monitoring and acquisition module 3 can take pictures of the vehicle and the parking space after the vehicle is parked in the parking space. At the same time, the parking picture after the vehicle is parked in the parking space is processed in advance, which reduces the calculation burden required by the vehicle parking space matching module 4 and improves the working efficiency of the entire system.

[0072] Preferably, the vehicle parking space matching module 4 is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and determine the risk of scratching the vehicle when parking, including the following steps:

[0073] Extract the angle difference Δθ of the left and right headlights of the vehicle in the grayscale parking image photo ;

[0074] The angle difference Δθ of the left and right headlights of the vehicle in the parking image photo Compared with the light angle difference Δθ of the vehicle detected by the entry video, if Δθ photo ≤Δθ, the vehicle is considered to be parked straight, otherwise, the vehicle is considered to be parked diagonally;

[0075] If the output result is that the vehicle is parked at an angle, it is considered that there is a high risk of scratching;

[0076] If the output result is that the vehicle is parked straight, the coordinates of the left and right headlights of the vehicle in the grayscale processing parking picture are extracted, the size of the parking space is imported into the parking picture to form the coordinates of the parking space, and the headlight spacing D of the vehicle in the parking picture is calculated. photo , the distance from the left headlight of the vehicle to the left border of the parking space L photo , and the distance R from the right headlight of the vehicle to the left border of the parking space photo , parking space dimensions include L space and W space ;

[0077] judge When the judgment result is 1, the output result is that the vehicle is parked straight on the side of the road, and it is determined that there is a medium risk of scratching. When the judgment result is 0, the output result is that the vehicle is parked straight in the center, and it is determined that there is a low risk of scratching.

[0078] Through the above steps, it is possible to more accurately compare the angle difference of the left and right headlights of the vehicle in the parking screen with the angle difference of the vehicle light extracted from the entry video, so as to more intuitively judge whether the vehicle is parked diagonally. Since the diagonal parking of the vehicle itself has a higher risk of scratching than the vehicle parked straight, it is directly classified as having a high risk of scratching. In addition, the vehicle is parked in the parking space, but whether the vehicle is parked in the center is judged by judging whether the left and right distances of the vehicle and the left and right distances of the parking space are balanced through the coordinates of the left and right headlights of the vehicle, the size of the parking space, the distance between the headlights of the vehicle in the parking screen, the distance from the left headlight of the vehicle to the left frame of the parking space, and the distance from the right headlight of the vehicle to the left frame of the parking space. If they are balanced, it is considered that the vehicle is parked straight in the center and the risk of being scratched is low. Otherwise, it means that the vehicle is parked straight by the side. Compared with the vehicle parked straight in the center, the vehicle parked straight by the side is significantly higher, so it is classified as a medium risk of scratching.

[0079] 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. An intelligent parking lot management system, characterized in that: The invention comprises an entrance monitoring and acquisition module (1), a vehicle data acquisition module (2), a vehicle monitoring and acquisition module (3), and a vehicle parking space matching module (4), wherein the output end of the entrance monitoring and acquisition module (1) is coupled to the input end of the vehicle data acquisition module (2), and the output ends of the vehicle data acquisition module (2) and the vehicle monitoring and acquisition module (3) are both coupled to the input end of the vehicle parking space matching module (4), wherein the entrance monitoring and acquisition module (1) is used to obtain an entry video of a vehicle entering a parking lot and feed it back to the vehicle data acquisition module (2), wherein the vehicle data acquisition module (2) is used to detect the headlight spacing of the vehicle and the light angle difference of the vehicle according to the entry video and feed it back to the vehicle parking space matching module (4), wherein the vehicle monitoring and acquisition module (3) is used to collect a parking picture after the vehicle is parked in the parking space and feed it back to the vehicle parking space matching module (4), wherein the vehicle parking space matching module (4) is used to receive the headlight spacing of the vehicle and the light angle difference of the vehicle and the parking picture, and judge the risk of scratching the vehicle when parking.

2. The intelligent parking lot management system according to claim 1, characterized in that: The entrance monitoring and acquisition module (1) comprises an entrance camera, which is arranged at the entrance of the parking lot and is used to obtain an entrance video of a vehicle entering the parking lot.

3. The intelligent parking lot management system according to claim 1, characterized in that: The entrance monitoring and acquisition module (1) is used to obtain the entry video of the vehicle entering the parking lot and feed it back to the vehicle data acquisition module (2), and comprises the following steps: Capture entry video of vehicles entering the parking lot; Extract one frame from the entry video at a certain interval to obtain a number of selected frames; Grayscale several selected frames to obtain grayscale frames Gt(x,y); The grayscale frame Gt(x,y) is fed back to the vehicle data acquisition module (2).

4. The intelligent parking lot management system according to claim 3, characterized in that: The vehicle data acquisition module (2) is used to detect the headlight spacing and the light angle difference of the vehicle according to the entry video and feed back to the vehicle parking space matching module (4), comprising the following steps: Use the canny edge detection method to locate the contour Ci of the headlight on the grayscale frame Gt(x,y); The headlight region Bt(x,y) is extracted from the grayscale frame Gt(x,y) by threshold segmentation. Where T is the brightness threshold; The light spot is located by the headlight area Bt(x,y) and the headlight contour Ci and the headlight coordinate X is obtained by the centroid method c =|Ci|∑ (x,y)∈Ci X, Y c =|Ci|∑ (x,y)∈Ci Y; The coordinates of the left headlight are set as (X L ,Y L ), the coordinates of the right headlight are (X R ,Y R ); Determine the Euclidean distance between the left and right headlights as d lights =(X R -X L ) 2 +(Y R -Y L ) 2 ; Import the focal length f of the entrance camera and set the distance from the entrance camera to the vehicle to be constant at D, and you can get the headlight spacing of the vehicle Set the coordinates of the entrance camera to (X camera ,Y camera ), calculate the vehicle's light angle difference using the headlight light formula Set the headlight spacing D real The light angle difference Δθ is fed back to the vehicle parking space matching module (4).

5. The intelligent parking lot management system according to claim 1, characterized in that: The vehicle monitoring and acquisition module (3) comprises a parking space camera, which is arranged above the parking space and is used to collect parking images after the vehicle is parked in the parking space.

6. The intelligent parking lot management system according to claim 4, characterized in that: The vehicle monitoring and acquisition module (3) is used to collect parking images after the vehicle is parked in the parking space and feed them back to the vehicle parking space matching module (4), comprising the following steps: Capture the parking scene after the vehicle parks in the parking space; Grayscale the parking image; The grayscale processed parking picture is fed back to the vehicle parking space matching module (4).

7. The intelligent parking lot management system according to claim 6, characterized in that: The vehicle parking space matching module (4) is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and to determine the risk of scratching the vehicle when parking, and comprises the following steps: Extract the angle difference Δθ of the left and right headlights of the vehicle in the grayscale parking image photo ; The angle difference Δθ of the left and right headlights of the vehicle in the parking image photo Compared with the light angle difference Δθ of the vehicle detected by the entry video, if Δθ photo ≤Δθ, the vehicle is considered to be parked straight, otherwise, the vehicle is considered to be parked diagonally.

8. The intelligent parking lot management system according to claim 7, characterized in that: The vehicle parking space matching module (4) is used to receive the headlight spacing of the vehicle, the light angle difference of the vehicle and the parking picture, and to determine the risk of scratching the vehicle when parking, and also includes the following steps: If the output result is that the vehicle is parked at an angle, it is considered that there is a high risk of scratching; If the output result is that the vehicle is parked straight, the coordinates of the left and right headlights of the vehicle in the grayscale processing parking picture are extracted, the size of the parking space is imported into the parking picture to form the coordinates of the parking space, and the headlight spacing D of the vehicle in the parking picture is calculated. photo , the distance from the left headlight of the vehicle to the left border of the parking space L photo , and the distance R from the right headlight of the vehicle to the left border of the parking space photo The parking space dimensions include L space and W space ; judge When the judgment result is 1, the output result is that the vehicle is parked straight on the side of the road, and it is determined that there is a medium risk of scratching. When the judgment result is 0, the output result is that the vehicle is parked straight in the center, and it is determined that there is a low risk of scratching.

Images