Vehicle access security management method, device, system and storage medium

Abstract

This application relates to a method, apparatus, system, and storage medium for vehicle entry and exit safety management. The method includes: acquiring real-time images of the garage entrance and exit area; analyzing the real-time images using a pre-trained detection model to segment the vehicle outline; calculating the distance between the vehicle outline points and a target object based on the vehicle outline; issuing a collision warning when the distance is less than or equal to a set threshold; and simultaneously marking the collision warning point on the real-time image. This application solves the problems of unintuitive and ineffective vehicle entry and exit collision warnings, thus improving the effectiveness of vehicle entry and exit collision warnings.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence monitoring, and in particular to a method, apparatus, system, and storage medium for vehicle entry and exit security management. Background Technology

[0002] With the development of society, cars have become commonplace in households. Many residential garage and parking lot entrances are equipped with barriers. These barriers are flanked by walls or concrete platforms. Since garage entrance roads are generally narrow, vehicles often scrape against the concrete platforms and walls when passing through the barriers, or even collide with them, causing damage. This is especially common among novice drivers. To avoid damage to vehicles and public facilities, providing collision warnings is an important means of preventing vehicles from scraping and colliding with barriers.

[0003] In related technologies, collision warning mainly involves installing sensors in parking garages to sense distance and alert drivers when entering or leaving the garage. However, the placement of sensor devices varies depending on the environment, making installation and design complex. When vehicle windows are closed, drivers may not hear the alarm, potentially leading to a collision. This warning method is not intuitive, and when a collision causes damage to the vehicle or pillar, video recording is not available, making it impossible to preserve evidence. In other words, related technologies suffer from poor effectiveness of collision warning devices for vehicle entry and exit from parking garages.

[0004] There is currently no effective solution to the problem of poor effectiveness of collision warning devices for vehicles entering and exiting parking spaces in related technologies. Summary of the Invention

[0005] This embodiment provides a method, device, system, and storage medium for vehicle entry and exit safety management, in order to solve the problem of poor effectiveness of collision warning devices for vehicle entry and exit in related technologies.

[0006] Firstly, this embodiment provides a method for vehicle entry and exit security management, the method comprising:

[0007] Acquire real-time images of the garage entrance / exit area.

[0008] The real-time image is analyzed using a pre-trained detection model to segment the vehicle's outline. Based on the vehicle's outline, the distance between the vehicle's outline points and the target object is calculated.

[0009] When the distance is less than or equal to a set threshold, a collision warning is issued, and a collision warning point is marked on the real-time image.

[0010] Send the real-time image.

[0011] In some embodiments, the step of analyzing the real-time image using a pre-trained detection model, segmenting the vehicle's outline, and calculating the distance between the vehicle's outline points and the target object based on the vehicle's outline includes:

[0012] The real-time image of the vehicle is collected and fed into the target detection model to obtain the vehicle region image. The vehicle region image is then fed into the segmentation model to obtain the contour point set of the vehicle. The contour point set and the preset marker line segment are fed into the functional model, and the functional model calculates the pixel distance between the contour points and the marker line segment. The vehicle region image includes the vehicle.

[0013] In some embodiments, the step of feeding the contour point set and a preset marker line segment into a functional model, wherein the functional model calculates the pixel distance between the contour points and the marker line segment, includes:

[0014] Set the endpoint coordinates of the marked line segment, traverse the contour point set of the vehicle, and input the coordinates of the contour points in the contour point set of the vehicle between the ordinates of the endpoints of the marked line segment into the functional model to obtain the pixel distance from the contour point to the marked line segment.

[0015] In some embodiments, traversing the contour point set includes: selecting a portion of the contour points in the contour point set to traverse based on the positional relationship between the set marker line segment and the center point coordinates of the vehicle in the image.

[0016] In some embodiments, traversing the set of vehicle partial contour points includes:

[0017] The vehicle contour point set is divided into a left contour point set and a right contour point set;

[0018] Take the intersection point of the straight line parallel to the horizontal axis passing through the center point and the straight line containing the marked line segment. If the x-coordinate of the intersection point is greater than or equal to the x-coordinate of the center point of the vehicle in the image, then traverse the right contour point set of the vehicle; otherwise, traverse the left contour point set of the vehicle. The x-coordinate values ​​of the contour points in the left contour point set are less than the x-coordinate of the center point of the vehicle in the image, and the x-coordinate values ​​of the contour points in the right contour point set are greater than or equal to the x-coordinate of the center point of the vehicle in the image.

[0019] In some embodiments, the method includes: determining the vertical distance from each contour point to the marked line segment and the magnitude of the set threshold; when the vertical distance is less than or equal to the set threshold, issuing a collision warning and simultaneously marking and displaying the contour point on the real-time image.

[0020] Secondly, this embodiment provides a vehicle entry and exit security management device, the device comprising:

[0021] The acquisition module acquires real-time images of the garage entrance and exit area;

[0022] The calculation module uses a pre-trained detection model to analyze the real-time image, segment the vehicle outline, and calculate the distance between the vehicle outline points and the target object.

[0023] The warning module issues a collision warning when the distance is less than or equal to a set threshold, and simultaneously marks the collision warning point on the real-time image.

[0024] The sending module transmits the real-time image.

[0025] Thirdly, this embodiment provides a vehicle entry and exit security management system, the system comprising:

[0026] The video recording device, the processing device, and the image display device are provided; wherein the video recording device is connected to the image display device through the processing device.

[0027] The video recording device is used to collect videos of vehicles entering and leaving the warehouse;

[0028] The image display device is used to display the real-time image sent by the processing device;

[0029] The processing equipment is used to implement the vehicle entry and exit security management method described in the first aspect above.

[0030] Fourthly, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the vehicle entry and exit security management method described in the first aspect above.

[0031] Fifthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the vehicle entry and exit security management method described in the first aspect above.

[0032] Compared with related technologies, the vehicle entry and exit safety management method, device, system and storage medium provided in this embodiment acquires real-time images of the garage entrance and exit area, analyzes the real-time images using a preset trained detection model, segments the vehicle outline, calculates the distance between the vehicle outline points and the target object, and issues a collision warning when the distance is less than or equal to a set threshold. At the same time, the collision warning point is marked on the real-time image, which solves the problem of poor effectiveness of vehicle entry and exit collision warning in related technologies and achieves the technical effect of intuitive vehicle warning.

[0033] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0035] Figure 1 This is a hardware structure block diagram of the terminal of the vehicle entry and exit security management method in this embodiment.

[0036] Figure 2 This is a flowchart of the vehicle entry and exit security management method in this embodiment.

[0037] Figure 3 This is a schematic diagram of the vehicle area image in this embodiment.

[0038] Figure 4 This is a flowchart of the vehicle entry and exit safety management method according to a preferred embodiment.

[0039] Figure 5 This is a schematic diagram of the vehicle entry and exit safety management system of this preferred embodiment.

[0040] Figure 6 This is a flowchart of the processing of the trained detection model in the surveillance camera of this preferred embodiment.

[0041] Figure 7 This is a schematic diagram of the real-time image after segmentation model in this preferred embodiment.

[0042] Figure 8 This is a structural block diagram of the vehicle entry and exit safety management device in this embodiment.

[0043] Figure 9 This is a structural block diagram of the vehicle entry and exit safety management system in this embodiment. Detailed Implementation

[0044] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0045] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0046] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the vehicle entry and exit security management method in this embodiment. (See diagram for example.) Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0047] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the vehicle entry and exit security management method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0048] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0049] This embodiment provides a method for vehicle entry and exit security management. Figure 2 This is a flowchart of the vehicle entry and exit security management method in this embodiment, such as... Figure 2 As shown, the process includes the following steps:

[0050] Step S201: Obtain real-time images of the garage entrance / exit area;

[0051] Specifically, acquire a real-time image of the garage entrance / exit area;

[0052] Furthermore, obtaining real-time images of the garage entrance and exit area can be achieved by taking photos one by one with a camera, or by capturing real-time video with a camera and selecting frames of real-time images from them.

[0053] Step S202: Analyze the real-time image using a pre-trained detection model, segment the vehicle outline, and calculate the distance between the vehicle outline points and the target object based on the vehicle outline.

[0054] Specifically, the pre-trained detection model is used to process and analyze the real-time images of the garage entrance and exit area, segment the vehicle outline, obtain the vehicle outline point set, and calculate the shortest line segment distance between each outline point in the outline point set and the target object.

[0055] Furthermore, another method for calculating the distance between the vehicle's outline points and the target object is to determine the line segment closest to the vehicle's outline by detecting the target object, and then calculate the distance of that line segment as the distance between the vehicle's outline points and the target object.

[0056] Furthermore, the target object is the object that the vehicle avoids colliding with; in this embodiment, it can specifically be a concrete barrier gate or a wall.

[0057] Step S203: When the distance is less than or equal to a set threshold, a collision warning is issued, and a collision warning point is marked on the real-time image.

[0058] Specifically, when the distance between the vehicle's outline and the target object is less than or equal to a set threshold, a collision warning is issued, and the outline points that are less than or equal to the set threshold are marked on the real-time image.

[0059] Step S204: Send real-time images.

[0060] Specifically, when no collision warning occurs, the acquired real-time image is sent; when a collision warning occurs, a real-time image is sent that marks contour points at a distance less than or equal to a set threshold.

[0061] Furthermore, the live image is sent to an external display or monitor.

[0062] Through the above steps, real-time images are acquired and processed and analyzed using a pre-trained detection model to segment the vehicle's outline. The distance between the vehicle's outline points and the target object is calculated. When the distance is less than or equal to a set threshold, a collision warning is issued and marked on the real-time image, which is then sent in real time. This collision warning process continues throughout the dynamic process of the vehicle entering and leaving the parking lot, ensuring that the driver receives a clear warning, including both audible and visual real-time images. The driver can adjust the vehicle's direction at any time based on the real-time images. Furthermore, when the vehicle is too close to the target object, the collision warning point will automatically appear on the real-time image to assist the driver in adjusting the steering wheel. Compared to existing technologies that only rely on sensor ranging and audible warnings, this method improves the effectiveness of collision warnings.

[0063] In some embodiments, a pre-trained detection model is used to analyze real-time images, segment the vehicle's outline, and calculate the distance between the vehicle's outline points and the target object based on the vehicle's outline, including:

[0064] The real-time images of the vehicles are collected and fed into the target detection model to obtain the vehicle region image. The vehicle region image is then fed into the segmentation model. The contour point set segmented by the segmentation model and the preset marker line segments are fed into the functional model. The functional model calculates the pixel distance between the contour points and the marker line segments. The vehicle region image includes the vehicles.

[0065] Specifically, the real-time images of the vehicles are fed into the target detection model. The target detection model processes the real-time images to obtain a vehicle region image containing a detection box that encloses the vehicles in the image. The vehicle region image is then processed by a segmentation model to segment the vehicle contours and obtain a set of vehicle contour points. The set of contour points and preset marker line segments are then fed into the functional model, which calculates the pixel distance between the contour points and the marker line segments.

[0066] Furthermore, the marked line segment is a line segment in the model where the target object is located. The marked line segment can be multiple or a single line. Multiple marked line segments can exist independently or be connected to form a polyline segment. Alternatively, both individual marked line segments and polyline segments formed by multiple marked line segments can coexist. When calculating the distance, only the distance between a certain marked line segment and the contour point is considered in each calculation.

[0067] Furthermore, the object detection model, segmentation model, and functional model do not necessarily need to be distinguished in terms of physical structure or software algorithm. As long as the functions of the three models are included and the corresponding effects are achieved, it is acceptable. For example, it can be a certain model that first detects the target object, processes the target object to obtain a region covering the target object, then segments and identifies the region to obtain the outline of the target object, and then obtains the outline point set of the target object. Finally, it calculates the distance based on the outline point set of the target object and the preset marked line segments.

[0068] Furthermore, object detection can detect vehicle bounding boxes. Segmentation based on these bounding boxes can reduce the computational load of the algorithm and improve the accuracy of the segmentation model.

[0069] In some embodiments, the set of contour points segmented by the segmentation model and preset marker line segments are fed into the functional model, and the functional model calculates the pixel distance between the contour points and the marker line segments, including:

[0070] Set the endpoint coordinates of the marked line segment, traverse the contour point set of the vehicle, and input the coordinates of the contour points in the contour point set of the vehicle between the ordinates of the endpoints of the marked line segment into the functional model to obtain the pixel distance from the contour point to the marked line segment.

[0071] Specifically, set the endpoint coordinates of the marked line segment as A(Ax, Ay) and B(Bx, By), traverse the set of contour points of the vehicle {(X1, Y1), (X2, Y2), …, (Xm, Ym)}, and send the contour point coordinates where Ay < Ym < By into the functional model. Set the equation of the marked line segment as AX + BY + C = 0, then the pixel distance from the contour point (Xm, Ym) to the marked line segment is:

[0072]

[0073] In some of these embodiments, traversing the set of contour points includes: selecting and traversing some of the contour points in the set of contour points according to the positional relationship between the set marked line segment and the center point coordinates of the vehicle in the image. [[ID=�]]

[0074] In some of these embodiments, traversing some of the contour points in the set of vehicle contour points includes dividing the set of vehicle contour points into a left contour point set and a right contour point set. Specifically, reference can be made to Figure 3 , 300 is the detection frame of the vehicle in the image, 310 is the center point of the vehicle in the image, 320 is the left contour of the vehicle in the image, and 330 is the right contour of the vehicle in the image; take the intersection point of the line passing through the center point parallel to the horizontal axis and the line where the marked line segment is located. If the abscissa of the intersection point is greater than or equal to the abscissa of the center point of the vehicle in the image, then traverse the right contour point set of the vehicle, otherwise traverse the left contour point set of the vehicle, where the abscissa of the contour points in the left contour point set is less than the abscissa of the center point of the vehicle in the image, and the abscissa of the contour points in the right contour point set is greater than or equal to the abscissa of the center point of the vehicle in the image.

[0075] Specifically, define the center point coordinates of the vehicle in the image as (Ox, Oy), substitute Oy into the equation of the marked line segment AX + BY + C = 0, and solve for X’ = -(C + BOy) / A. If X’ is greater than Ox, then traverse the right contour point set of the vehicle, otherwise traverse the left contour point set of the vehicle, where the abscissa values of the contour points in the left contour point set are less than Ox, and the abscissa values of the contour points in the right contour point set are greater than or equal to Ox.

[0076] Further, the contour points whose abscissa values are equal to the abscissa Ox of the center point of the vehicle in the image can also be divided into the left contour point set, or some can be divided into the left contour point set and some can be divided into the right contour point set.

[0077] In some of these embodiments, judge the size relationship between the vertical distance from each contour point to the marked line segment and the set threshold. When the vertical distance is less than or equal to the set threshold, issue a collision warning and at the same time mark and display this contour point on the image.

[0078] Specifically, the vertical distance from each contour point to the marked line segment is compared with a set threshold. When the vertical distance is less than or equal to the set threshold, a collision warning is issued, and the contour points with a vertical distance less than or equal to the threshold are marked and displayed on the image.

[0079] In some of these embodiments, real-time images are stored when a vehicle collision occurs.

[0080] Specifically, when a vehicle collides with a target object, an image of the collision is stored so that relevant personnel can review the accident.

[0081] The present embodiment will now be described and illustrated through preferred embodiments.

[0082] Figure 4 This is a flowchart of a preferred embodiment of a vehicle entry and exit security management method, which is applied to, for example... Figure 5 The vehicle entry and exit security management system shown includes a wall (4), a barrier gate (5), an LCD display (6), and a surveillance camera (7). Figure 3 and Figure 4 As shown, the method specifically includes the following steps:

[0083] Step S301: Install a surveillance camera 7 vertically at a position 3m (3 meters) or more directly above the garage entrance / exit;

[0084] Specifically, the installation angle can be adjusted using the gyroscope built into the monitoring camera 7. When the pitch angle read from the gyroscope is 0, the camera is perpendicular to the ground.

[0085] Step S302: Mark polylines along the edges of wall 4 and gate 5 on the image, calculate and record the equation of each line segment: AnX+BnY+Cn=0 (n=1,2,3…).

[0086] Step S303: Set the collision warning pixel distance threshold L.

[0087] Step S304: Take a frame of image and send it to the target detection algorithm to identify whether there is vehicle 3 in the image. If no vehicle 3 is identified, this step ends and the next frame of image is taken. If vehicle 3 is identified, calculate the minimum pixel distance between the contour point of vehicle 3 and the marked polyline. When the minimum pixel distance is less than or equal to L, a collision warning is issued.

[0088] Specifically, such as Figure 6 As shown, the surveillance camera 7 has a built-in intelligent algorithm. It takes a frame of image and sends it to the target detection algorithm, which is a YOLO deep learning algorithm, and can detect the approaching vehicle 3.

[0089] Further, when it is detected that a vehicle 3 enters, the built-in voice module of the monitoring camera 7 broadcasts a voice prompt of "Garage entrance, please slow down", and at this time, the coordinates (x1, y1), (x2, y2) of the vehicle 3 in the image are recorded.

[0090] Further, the coordinates (x1, y1), (x2, y2) of the vehicle 3 in the image are the diagonal vertex coordinates of the detection frame of the vehicle determined by target detection. The detection frame covers the vehicle in the image, specifically a rectangle. Once the diagonal vertex coordinates are determined, the position of the detection frame can be determined.

[0091] Further, the above vehicle coordinates (x1, y1), (x2, y2) and the image are sent into an instance segmentation algorithm, which can segment the coordinates of each contour point of the vehicle. Let the contour point set be:

[0092] {(X1, Y1), (X2, Y2), …, (Xm, Ym)}.

[0093] Further, as Figure 7 shown, where 1 is the segmented vehicle contour, 2 is the barrier gate, AB is a line segment marked along the cement platform of the barrier gate in step S302, and the coordinates are (Ax, Ay), (Bx, By). Traverse the contour point set, and send the contour point coordinates where Ay < Ym < By into the function algorithm, which is used to calculate the perpendicular distance from the contour point to the line segment. Assuming the equation of the line segment AB is AX + BY + C = 0, the minimum pixel distance from the contour point (Xm, Ym) to the line segment AB is:

[0094]

[0095] Further, traversing the contour point set includes: selecting some contour points in the contour point set according to the positional relationship between the set marked line segment and the center point coordinates of the vehicle in the image.

[0096] Further, traversing some contour points in the vehicle contour point set includes dividing the vehicle contour point set into a left contour point set and a right contour point set. Define the center point coordinates of the vehicle in the image as (Ox, Oy), substitute Oy into the equation AX + BY + C = 0 of the marked line segment, and solve for X' = -(C + BOy) / A. If X' is greater than Ox, traverse the right contour point set of the vehicle; otherwise, traverse the left contour point set of the vehicle, where the abscissa values of the contour points in the left contour point set are less than Ox, and the abscissa values of the contour points in the right contour point set are greater than or equal to Ox.

[0097] Further, judge the size of the perpendicular distance d(m) from each contour point of the vehicle to each marked line segment and the preset collision warning distance threshold L. When d(m) ≤ L, the built-in voice module of the camera broadcasts a collision warning and marks the contour point in red on the image and projects it on the liquid crystal monitor.

[0098] Step S305: This frame ends, go to step S304.

[0099] In this embodiment, a vehicle entry and exit safety management device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated here. The following terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0100] Figure 8 is the structural block diagram of the vehicle entry and exit safety management device of this embodiment, as Figure 8 shown, this device includes: an acquisition module 10, a calculation module 20, an early warning module 30, and a sending module 40,

[0101] The acquisition module 10 is used to acquire real-time images of the garage entrance and exit area;

[0102] The calculation module 20 is used to analyze the real-time image by using a preset trained detection model, segment the contour of the vehicle, and calculate the distance between the vehicle contour points and the target object;

[0103] Specifically, when the calculation module 20 receives the real-time image of the vehicle, it uses the preset trained detection model to process and analyze the real-time image of the garage entrance and exit area, segments the contour of the vehicle, obtains the set of vehicle contour points, and calculates the shortest line segment distance between each contour point in the contour point set and the target object.

[0104] Specifically, set the endpoint coordinates of the marked line segment as A(Ax, Ay) and B(Bx, By), traverse the contour point set, take the contour point coordinates with Ay < Ym < By and send them into the function model. Set the equation of the marked line segment as AX + BY + C = 0, then the pixel distance from the contour point (Xm, Ym) to the marked line segment is:

[0105]

[0106] The early warning module 30 is used to issue a collision warning when the pixel distance between the vehicle contour points and the target object is less than or equal to the set threshold, and at the same time mark and display the contour points with a distance less than or equal to the set threshold on the image.

[0107] The sending module 40 is used to send real-time images.

[0108] Specifically, when there is no collision warning, the acquired real-time image is sent; when a collision warning occurs, the real-time image with the contour points marked with a distance less than or equal to the set threshold on the real-time image is sent.

[0109] The vehicle entry and exit safety management device provided in this embodiment acquires real-time images of the garage entrance and exit area using the acquisition module 10. The calculation module 20 analyzes the real-time images using a preset trained detection model, segments the vehicle outline, and calculates the pixel distance between the vehicle outline points and the target object based on the vehicle outline. The warning module 30 issues a collision warning when the pixel distance reaches a set threshold, and simultaneously marks the collision warning points on the real-time image. This solves the problems of unintuitive and ineffective vehicle entry and exit collision warnings, and improves the effectiveness of vehicle entry and exit collision warnings.

[0110] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0111] This embodiment also provides a vehicle entry and exit security management system. Figure 9 This is a structural block diagram of the vehicle entry and exit security management system of this embodiment, as shown below. Figure 9 As shown, the system includes a video capture device 50, a processing device 60, and an image display device 70. The video capture device is used to capture video of vehicles entering and leaving the warehouse, the image display device is used to display real-time images of vehicles entering and leaving the warehouse, and the processing device 60 is used to execute the steps in any of the above method embodiments, including:

[0112] S801, the processing device 60 acquires real-time images of the garage entrance / exit area sent by the video recording device;

[0113] S802, the processing device 60 analyzes the real-time image using a preset trained detection model, segments the outline of the vehicle, and calculates the distance between the outline points of the vehicle and the target object based on the outline of the vehicle.

[0114] Specifically, the processing device 60 sends the real-time images of the vehicles it has acquired to the target detection model. The target detection model processes the real-time images to obtain a vehicle region image containing a detection box that encloses the vehicles in the image. The vehicle region image is then processed by a segmentation model to segment the vehicle contours and obtain a set of vehicle contour points. The set of contour points and preset marker line segments are then sent to the functional model, which calculates the pixel distance between the contour points and the marker line segments.

[0115] Specifically, set the coordinates of the marked line segment as A(Ax, Ay) and B(Bx, By). Traverse the set of contour points, and send the coordinates of the contour points where Ay < Ym < By into the functional model. Set the equation of the marked line segment as AX + BY + C = 0. Then, the minimum pixel distance from the contour point (Xm, Ym) to the marked line segment is:

[0116]

[0117] Further, traversing the set of contour points includes: selecting some contour points in the set of traversed contour points according to the positional relationship between the set marked line segment and the center point coordinates of the vehicle in the image.

[0118] Further, traversing some contour points in the set of vehicle contour points includes dividing the set of vehicle contour points into a left contour point set and a right contour point set. Define the center point coordinates of the vehicle in the image as (Ox, Oy). Substitute Oy into the equation AX + BY + C = 0 of the marked line segment, and solve for X’ = -(C + BOy) / A. If X’ is greater than Ox, traverse the right contour point set of the vehicle; otherwise, traverse the left contour point set of the vehicle, where the abscissa values of the contour points in the left contour point set are less than Ox, and the abscissa values of the contour points in the right contour point set are greater than or equal to Ox.

[0119] S803. When the pixel distance from the contour point (Xm, Ym) to the marked line segment reaches the set threshold L, the processing device 60 issues a collision warning and at the same time marks and displays this contour point on the real-time image.

[0120] Specifically, when the distance between the contour point of the vehicle and the target object is less than or equal to the set threshold L, the processing device 60 issues a collision warning and at the same time marks the contour points with a distance less than or equal to the set threshold on the real-time image.

[0121] S804. The processing device 60 projects the real-time image onto the image display device.

[0122] Specifically, when no collision warning occurs, the processing device 60 projects the acquired real-time image onto the image display device. When a collision warning occurs, the processing device 60 projects the real-time image with the contour points marked with a distance less than or equal to the set threshold on the real-time image. In this embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0123] Optionally, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0124] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0125] S1, acquire real-time images of the garage entrance / exit area.

[0126] S2 uses a pre-trained detection model to analyze real-time images, segment the vehicle's outline, and calculate the distance between the vehicle's outline points and the target object based on the vehicle's outline.

[0127] S3, when the distance is less than or equal to the set threshold L, a collision warning is issued, and a collision warning point is marked on the real-time image.

[0128] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0129] Furthermore, in conjunction with the vehicle entry and exit security management method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the vehicle entry and exit security management methods described in the above embodiments.

[0130] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0131] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0132] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for safe management of vehicle entry and exit from a warehouse, characterized in that, The method includes: Acquire real-time images of the garage entrance / exit area; The real-time image is analyzed using a pre-trained detection model to segment the vehicle's outline and obtain the vehicle's outline point set. The set of contour points and the preset marked line segments are fed into a functional model, which calculates the pixel distance between the contour points and the marked line segments, including: Set the endpoint coordinates of the marked line segment, traverse the contour point set of the vehicle, and input the coordinates of the contour points in the contour point set of the vehicle between the ordinates of the endpoints of the marked line segment into the functional model to obtain the pixel distance between the contour point and the marked line segment. The step of traversing the contour point set of the vehicle includes: selecting a portion of the contour points in the contour point set to traverse based on the positional relationship between the set marker line segment and the center point coordinates of the vehicle in the image. The step of traversing a portion of the contour points in the contour point set includes: dividing the contour point set into a left contour point set and a right contour point set; taking the intersection point of a straight line parallel to the horizontal axis passing through the center point and the straight line containing the marked line segment; if the x-coordinate of the intersection point is greater than or equal to the x-coordinate of the center point of the vehicle in the image, then traversing the right contour point set; otherwise, traversing the left contour point set, wherein the x-coordinate of the contour points in the left contour point set is less than the x-coordinate of the center point of the vehicle in the image, and the x-coordinate of the contour points in the right contour point set is greater than or equal to the x-coordinate of the center point of the vehicle in the image. When the pixel distance is less than or equal to a set threshold, a collision warning is issued, and a collision warning point is marked on the real-time image. Send the real-time image.

2. The method according to claim 1, characterized in that, The step of analyzing the real-time image using a pre-trained detection model to segment the vehicle's outline and obtain a set of vehicle outline points includes: The real-time images of the vehicle are collected and fed into a target detection model to obtain a vehicle region image. The vehicle region image is then fed into a segmentation model to obtain a set of contour points of the vehicle. The vehicle region image includes the vehicle.

3. The method according to claim 1, characterized in that, The method includes: determining the vertical distance from each contour point to the marked line segment and the size of the set threshold; when the vertical distance is less than or equal to the set threshold, issuing a collision warning and simultaneously marking and displaying the contour point on the real-time image.

4. A vehicle entry and exit safety management device, characterized in that, The device includes: The acquisition module acquires real-time images of the garage entrance and exit area; The calculation module analyzes the real-time image using a pre-trained detection model, segments the vehicle's outline, and obtains a set of outline points for the vehicle. The set of outline points and a pre-set marker line segment are then fed into a functional model, which calculates the pixel distance between the outline points and the marker line segment. The calculation module is also used to set the endpoint coordinates of the marked line segment, traverse the contour point set of the vehicle, and input the coordinates of the contour points in the contour point set of the vehicle between the endpoint coordinates of the marked line segment into the functional model to obtain the pixel distance from the contour point to the marked line segment. The calculation module is also used to select and traverse a portion of the contour points in the contour point set based on the positional relationship between the set marked line segment and the center point coordinates of the vehicle in the image. The calculation module is further configured to divide the contour point set into a left contour point set and a right contour point set; take the intersection point of the straight line parallel to the horizontal axis passing through the center point and the straight line containing the marked line segment; if the x-coordinate of the intersection point is greater than or equal to the x-coordinate of the center point of the vehicle in the image, then traverse the right contour point set; otherwise, traverse the left contour point set, wherein the x-coordinate of the contour point in the left contour point set is less than the x-coordinate of the center point of the vehicle in the image, and the x-coordinate of the contour point in the right contour point set is greater than or equal to the x-coordinate of the center point of the vehicle in the image. The warning module issues a collision warning when the pixel distance is less than or equal to a set threshold, and marks the collision warning point on the real-time image. The sending module transmits the real-time image.

5. A vehicle entry and exit security management system, characterized in that, The system includes: a video recording device, a processing device, and an image display device; wherein the video recording device is connected to the image display device through the processing device; The video recording device is used to collect videos of vehicles entering and leaving the warehouse; The image display device is used to display real-time images sent by the processing device; The processing equipment is used to perform the vehicle entry and exit security management method according to any one of claims 1 to 3.

6. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the vehicle entry and exit security management method according to any one of claims 1 to 3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle entry and exit security management method according to any one of claims 1 to 3.

Images