Method, device and equipment for displaying vehicle scheduling condition

Abstract

The invention provides a vehicle scheduling condition display method, device and equipment, and is applied to the field of vehicle scheduling, and the method comprises the steps: collecting an intersection image of an intersection through a camera; the camera is arranged at an intersection. And screening out the vehicle contour information of the target vehicle at the current moment from the intersection picture. The target vehicle is any vehicle running at the intersection. And inputting the vehicle contour information into the trained vehicle contour recognition model to generate a vehicle display image of the target vehicle. And based on the vehicle display image, determining simulation position information of the target vehicle in the intersection display image of the intersection, and based on the simulation position information, displaying the vehicle display image in the intersection display image. The intersection display image is a simulation image corresponding to the intersection picture, the vehicle driving condition can be displayed in real time, and the efficiency and safety of traffic management are improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle dispatching, and in particular to a method, device and equipment for displaying vehicle dispatching conditions. Background Art

[0002] In modern urban traffic, the traffic volume at intersections is large, the types of vehicles are diverse, and traffic management is difficult. Traditional traffic monitoring systems can usually only provide static video images and cannot display the driving conditions and movement trajectories of vehicles in real time, making it difficult to meet the needs of traffic management and scheduling. Summary of the invention

[0003] The purpose of this application is to provide a method, device and equipment for displaying vehicle dispatch conditions, so as to display vehicle driving conditions in real time and improve the efficiency and safety of traffic management.

[0004] In a first aspect, an embodiment of the present application provides a method for displaying vehicle dispatch conditions, the method comprising: using a camera to collect an intersection picture of an intersection. The camera is deployed at the intersection. The vehicle contour information of the target vehicle at the current moment is filtered out from the intersection picture. The target vehicle is any vehicle traveling at the intersection. The vehicle contour information is input into a trained vehicle contour recognition model to generate a vehicle display image of the target vehicle. Based on the vehicle display image, the simulated position information of the intersection display image of the target vehicle at the intersection is determined, and based on the simulated position information, the vehicle display image is displayed on the intersection display image. The intersection display image is a simulated image corresponding to the intersection picture.

[0005] A possible implementation method is to filter out the vehicle profile information of the target vehicle at the current moment from the intersection picture, including: extracting the vehicle profile information from the intersection picture to obtain a plurality of vehicle profile information to be processed. Performing a similarity comparison on the plurality of vehicle profile information to be processed to determine the similarity between the plurality of vehicle profile information to be processed. When the similarity is less than a similarity threshold, determining the plurality of vehicle profile information to be processed corresponding to the similarity as the vehicle profile information.

[0006] In a possible implementation, the vehicle contour information is input into a trained vehicle contour recognition model to generate a vehicle display image of a target vehicle, including: inputting the vehicle contour information into the trained vehicle contour recognition model, determining a plurality of vehicle sub-images corresponding to the target vehicle and a combination relationship between the plurality of vehicle sub-images, and combining the plurality of vehicle sub-images using the combination relationship to generate a vehicle display image of the target vehicle.

[0007] A possible implementation method is to input the vehicle contour information into a trained vehicle contour recognition model, determine multiple vehicle sub-images corresponding to the target vehicle and the combination relationship between the multiple vehicle sub-images, including: splitting the vehicle contour information to obtain multiple pixel regions of the vehicle contour information and the splitting relationship between the multiple pixel regions. Input the multiple pixel regions into the trained vehicle contour recognition model, determine the target feature corresponding to each pixel region and the feature probability of the target feature corresponding to each pixel region. Determine the vehicle sub-image corresponding to the pixel region based on the target feature and the feature probability of the target feature, and determine the combination relationship between the multiple vehicle sub-images based on the splitting relationship between the multiple pixel regions.

[0008] A possible implementation method is to determine the simulated position information of the intersection display image of the target vehicle at the intersection based on the vehicle display image, including: obtaining the position coordinates of multiple preset positions in a preset area in the intersection picture and the pixel position coordinates of multiple preset pixel positions in a preset pixel area in the intersection display image. The preset pixel area is the area corresponding to the preset area displayed in the intersection display image. The preset pixel position is the position corresponding to the preset position displayed in the intersection display image. Based on the position coordinates and the pixel position coordinates, determine the perspective conversion coefficient of the intersection picture perspective conversion to the intersection display image. Based on the vehicle contour information, determine the vehicle position information of the target vehicle in the intersection picture. Based on the vehicle position information and the perspective conversion coefficient, determine the simulated position information.

[0009] In a possible implementation, based on the simulated position information, the vehicle display image is displayed on the intersection display image, including: determining the center position of the vehicle display image according to the vehicle display image. When the center position enters a preset pixel area of ​​the intersection display image, the vehicle display image is displayed on the intersection display image based on the simulated position information.

[0010] In a possible implementation, the method further includes: when it is detected that the vehicle display image is different from the historical vehicle display image determined at the previous moment of the current moment, obtaining the current traffic flow information of the intersection. The historical vehicle display image includes the historical simulated position information of the target vehicle in the historical vehicle display image. According to the traffic flow information, the simulated position information and the historical simulated position information, the motion trajectory of the target vehicle is determined. The motion trajectory is used to simulate the target vehicle traveling from the historical simulated position information to the simulated position information, and the simulation result is displayed on the intersection display image.

[0011] In a second aspect, an embodiment of the present application provides a device for displaying vehicle dispatch status, the device comprising: a collection module, a screening module, a generation module, and a display module.

[0012] The acquisition module is used to collect the intersection images of the intersection using the camera. The camera is deployed at the intersection.

[0013] The screening module is used to screen out the vehicle profile information of the target vehicle at the current moment from the intersection picture. The target vehicle is any vehicle traveling at the intersection.

[0014] The generation module is used to input the vehicle contour information into the trained vehicle contour recognition model to generate a vehicle display image of the target vehicle.

[0015] The display module is used to determine the simulated position information of the intersection display image of the target vehicle at the intersection based on the vehicle display image, and display the vehicle display image on the intersection display image based on the simulated position information. The intersection display image is a simulated image corresponding to the intersection screen.

[0016] In a third aspect, an embodiment of the present application provides a display device for vehicle dispatching conditions, which has the function of implementing the display method for vehicle dispatching conditions of the first aspect or any possible implementation method. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, the computer can execute the method for displaying vehicle dispatch conditions of the above-mentioned first aspect or any possible implementation method.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for displaying vehicle dispatch conditions of the first aspect or any possible implementation method.

[0019] Among them, the technical effects brought about by any design method in the second to fifth aspects can be referred to the technical effects brought about by different possible implementation methods in the first aspect or different possible implementation methods in the second aspect or different possible implementation methods in the third aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A structural schematic diagram of a vehicle dispatching status display system provided in an embodiment of the present application;

[0022] Figure 2 A flow chart of a method for displaying vehicle dispatching conditions provided in an embodiment of the present application;

[0023] Figure 3 A structural schematic diagram of a vehicle dispatching status display device provided in an embodiment of the present application;

[0024] Figure 4 A structural schematic diagram of a vehicle dispatch status display system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0027] At present, in modern urban traffic, the traffic flow at intersections is large, the types of vehicles are diverse, and traffic management is difficult. Traditional traffic monitoring systems can usually only provide static video images and cannot display the driving conditions and movement trajectories of vehicles in real time, making it difficult to meet the needs of traffic management and scheduling.

[0028] Based on this, an embodiment of the present application provides a method for displaying vehicle scheduling conditions, the method comprising: using a camera to collect an intersection picture of an intersection. The camera is deployed at the intersection. The vehicle contour information of the target vehicle at the current moment is filtered out from the intersection picture. The target vehicle is any vehicle traveling at the intersection. The vehicle contour information is input into a trained vehicle contour recognition model to generate a vehicle display image of the target vehicle. Based on the vehicle display image, the simulated position information of the intersection display image of the target vehicle at the intersection is determined, and based on the simulated position information, the vehicle display image is displayed on the intersection display image. The intersection display image is a simulated image corresponding to the intersection picture.

[0029] The method for displaying vehicle dispatch status provided in the embodiment of the present application collects real-time images of the intersection through a camera, filters out vehicle contour information of the target vehicle from the image, generates a vehicle display image using a trained vehicle contour recognition model, and displays the vehicle display image on a simulated image corresponding to the intersection image. This method can monitor and dynamically display the traffic conditions at the intersection in real time, and can facilitate users such as traffic management departments to promptly understand the traffic conditions at the intersection so as to make quick responses.

[0030] The solution provided by the embodiment of the present application will be described in detail below with reference to specific drawings.

[0031] On the one hand, the solution shown in the embodiment of the present application can be executed by a vehicle dispatching status display system. Figure 1 As shown, the vehicle dispatching situation display system 100 may include at least one camera 101 , a vehicle dispatching device 102 , and a display device 103 .

[0032] The cameras 101 are deployed at intersections or road sections to capture the road traffic conditions in real time. These cameras can provide high-definition video streams for collecting real-time intersection images.

[0033] The vehicle dispatching device 102 is used to support functions such as vehicle profile information extraction and recognition, vehicle position determination, traffic flow analysis, motion trajectory simulation, and virtual traffic scene generation based on the intersection image captured by the camera 101.

[0034] The display device 103 is used to present the virtual traffic scene generated by the vehicle dispatching device 102. The display device 103 can be a large display screen installed in the traffic management center for traffic management personnel to monitor traffic conditions in real time. The display device 103 can also be a mobile application connected to the Internet for the public to view the traffic conditions in a specific area.

[0035] On the one hand, the embodiment of the present application provides a method for displaying vehicle dispatching conditions, which can be deployed by Figure 1 The vehicle dispatching situation display system 100 shown is executed. Figure 2 As shown, the method may include the following steps.

[0036] S201, using a camera to collect images of an intersection.

[0037] Among them, cameras are deployed at intersections.

[0038] For example, cameras can be deployed at strategic locations at intersections to ensure coverage of the entire intersection. The cameras have high resolution and good low-light performance to ensure clear video footage is captured in all weather and lighting conditions.

[0039] In one possible implementation, a camera collects video images of the intersection in real time and transmits the video stream to a vehicle dispatching device.

[0040] S202, filter out the vehicle profile information of the target vehicle at the current moment from the intersection picture. The target vehicle is any vehicle traveling at the intersection.

[0041] In a possible implementation, vehicle profile information is extracted from the intersection image to obtain a plurality of vehicle profile information to be processed. Similarity comparison is performed on the plurality of vehicle profile information to be processed to determine the similarity between the plurality of vehicle profile information to be processed. When the similarity is less than a similarity threshold, the plurality of vehicle profile information to be processed corresponding to the similarity is determined to be vehicle profile information.

[0042] The vehicle profile information may include vehicle logo information, color information, type information (such as trucks, cars, SUVs, special vehicles, etc.), size information (large vehicles, medium vehicles, small vehicles, etc.), shape information, license plate information (license plate color, license plate position, license plate number, etc.), etc. This application is not limited to this.

[0043] For example, the outline information of the vehicle is slowly extracted from the intersection using image processing techniques, such as edge detection, background subtraction, etc. This process can separate the outline of the vehicle from the complex intersection picture and provide basic data for subsequent recognition and processing.

[0044] Then, the extracted multiple vehicle profile information to be processed is compared for similarity to determine the similarity between them. The similarity comparison can be achieved by calculating the overlapping area, shape similarity and other indicators between the profiles.

[0045] When the similarity is less than a preset similarity threshold, it is determined that the profile information belongs to different vehicles. The selection of the similarity threshold can be adjusted according to the actual application scenario to ensure accuracy and robustness.

[0046] S203, inputting the vehicle contour information into the trained vehicle contour recognition model to generate a vehicle display image of the target vehicle.

[0047] In a possible implementation, the vehicle contour information is input into a trained vehicle contour recognition model to determine a plurality of vehicle sub-images corresponding to the target vehicle and a combination relationship between the plurality of vehicle sub-images.

[0048] Specifically, the vehicle contour information is split to obtain a plurality of pixel regions of the vehicle contour information and a splitting relationship between the plurality of pixel regions. The plurality of pixel regions are input into a trained vehicle contour recognition model to determine a target feature corresponding to each pixel region and a feature probability of the target feature corresponding to each pixel region. Based on the target feature and the feature probability of the target feature, a vehicle sub-image corresponding to the pixel region is determined, and based on the splitting relationship between the plurality of pixel regions, a combination relationship between the plurality of vehicle sub-images is determined.

[0049] The multiple vehicle sub-images are combined using the combination relationship to generate a vehicle display image of the target vehicle.

[0050] Exemplarily, the extracted vehicle profile information is input into a trained vehicle profile recognition model. The vehicle profile recognition model may be a deep learning model, such as a convolutional neural network (CNN), which can recognize different types of vehicles and generate detailed vehicle display images. The vehicle profile recognition model determines multiple vehicle sub-images corresponding to the target vehicle and their combination relationships by analyzing the profile information.

[0051] The vehicle profile information is split into multiple pixel areas, and the splitting relationship between these pixel areas is determined. The multiple pixel areas are input into the vehicle profile recognition model to determine the target features and feature probabilities corresponding to each pixel area. For example, if it is determined that there are pixels with SUV features in the pixel area, the feature probability of the SUV features in the pixel area will increase. At the same time, if it is determined that there are pixels with car features in the pixel area, the feature probability of the car features will also increase. Finally, the target features and feature probabilities corresponding to each information in the pixel area are obtained.

[0052] It should be noted that the feature probability is related to the similarity of the pixel points of the target feature, the training set of the vehicle contour recognition model, and the number of retrieval matches. Finally, the vehicle contour recognition model will return the feature with the highest feature probability in the pixel area as the target feature.

[0053] The vehicle sub-image corresponding to each pixel region is determined according to the target features and feature probabilities, and the combination relationship between multiple vehicle sub-images is determined according to the splitting relationship between multiple pixel regions.

[0054] For example, a 2.5D vehicle sub-image is generated by returning vehicle logo features, color features, type features, size features, shape features, and license plate features, and the combination relationship between vehicle sub-images is determined through the splitting relationship between multiple pixel areas to combine multiple vehicle sub-images to generate a 2.5D vehicle display image of the target vehicle, and the vehicle license plate number information is filled into the vehicle display image.

[0055] S204, based on the vehicle display image, determine the simulated position information of the intersection display image of the target vehicle at the intersection, and based on the simulated position information, display the vehicle display image on the intersection display image. The intersection display image is a simulated image corresponding to the intersection screen.

[0056] The image displayed at the intersection is an animation that simulates the real intersection and is restored in proportion.

[0057] Specifically, the intersection display image can be obtained by taking multiple shots of the intersection using a drone in the air. For example, the drone flight path is first planned. According to the size and shape of the real intersection, the drone flight path is planned to ensure that the flight path can cover the entire real intersection. The drone flies along the planned path and takes multiple high-resolution photos at a preset height and angle. There is a certain overlap between each photo, which can ensure the accuracy of subsequent stitching.

[0058] Then, use image processing algorithms (such as SIFT, SURF, etc.) to extract the key feature points of each photo, and then match the feature points in adjacent photos to obtain matching results, which can include the relative position relationship between all photos. Then use the matching results to stitch multiple photos into a panoramic image. Stitching and smoothing the stitched images to eliminate stitching lines and discontinuities can ensure a natural transition of the overall image. Select several reference points with known distances in the real intersection as the basis for scale correction.

[0059] The image scale is then calculated based on the actual distance of the reference point and the pixel distance in the stitched image. The calculated scale is applied to the entire stitched image to ensure the consistency and approximation of the scale of the entire image. Finally, the stitched image is imported into the vehicle dispatching display system to restore the scale of the real intersection.

[0060] The intersection display image can simulate and display all the equipment in the real intersection, such as gates, traffic lights, LED screens, gun cameras and ball cameras, etc.

[0061] Specifically, when the intersection display image simulates and displays the equipment in the real intersection, the corresponding animation can be displayed based on the equipment. For example, barrier animation (the barrier animation can be that the barrier sends real-time signal changes to the vehicle dispatch display system, and the vehicle dispatch display system determines the state change of the barrier according to the real-time signal changes, thereby generating the barrier animation), signal light animation (the signal light animation can be the color change of the signal light, the countdown digital jump of the color change of the signal light, the signal light animation is that the signal light sends real-time signal changes to the vehicle dispatch display system, and the vehicle dispatch display system determines the state change of the signal light according to the real-time signal changes, thereby generating the signal light animation), LED screen animation (the LED screen animation can display the content that needs to be displayed, the LED screen animation is that the LED screen sends real-time signal changes to the vehicle dispatch display system, and the vehicle dispatch display system generates the LED screen animation according to the real-time signal changes) and vehicle animation (for example, a vehicle display image, and the vehicle display image can carry the license plate number information of the target vehicle)

[0062] Furthermore, users can interact with the devices displayed in the intersection display image by clicking, for example, they can directly control all the devices in the real intersection by clicking. For example, clicking on the camera can enlarge the camera's current monitoring screen, clicking on the barrier can control the barrier to rise or fall, clicking on the signal light can control the color change of the signal light and the specific countdown number of the signal light color change, and clicking on the LED screen can edit the content so that the LED screen displays the corresponding specific content.

[0063] A possible implementation method is to obtain the position coordinates of multiple preset positions in a preset area in the intersection picture and the pixel position coordinates of multiple preset pixel positions in a preset pixel area in the intersection display image. The preset pixel area is the area corresponding to the preset area displayed in the intersection display image. The preset pixel position is the position corresponding to the preset position displayed in the intersection display image. According to the position coordinates and the pixel position coordinates, the perspective conversion coefficient of the intersection picture perspective conversion to the intersection display image is determined. According to the vehicle contour information, the vehicle position information of the target vehicle in the intersection picture is determined. According to the vehicle position information and the perspective conversion coefficient, the simulation position information is determined.

[0064] Exemplarily, the position coordinates of multiple preset positions in a preset area in the intersection picture, and the pixel position coordinates of multiple preset pixel positions in a preset pixel area in the intersection display image are obtained. The preset pixel area is an area displayed in the intersection display image corresponding to the preset area, and the preset pixel position is a position displayed in the intersection display image corresponding to the preset position. Based on the position coordinates and the pixel position coordinates, the perspective conversion coefficient of the intersection picture perspective conversion to the intersection display image is calculated. The perspective conversion coefficient is used to convert the vehicle position in the real world into the position in the virtual scene. Based on the vehicle contour information, the vehicle position information of the target vehicle in the intersection picture is determined. Based on the vehicle position information and the perspective conversion coefficient, the simulated position information of the target vehicle in the intersection display image is determined.

[0065] In a possible implementation, the center position of the vehicle display image is determined based on the vehicle display image. When the center position enters a preset pixel area of ​​the intersection display image, the vehicle display image is displayed on the intersection display image based on the simulated position information.

[0066] Exemplarily, the center position of the vehicle display image is determined according to the vehicle display image. When the center position enters a preset pixel area of ​​the intersection display image, the vehicle display image is displayed in the intersection display image based on the simulated position information.

[0067] For example, based on the intersection display image, the coordinates (x, y values) of the four corners of the intersection display image are specified, with the upper left corner being (0, 0), the x value increases as you go east, and the y value increases as you go south, and the x and y values ​​of the lower right corner are determined by the real distance between the upper left and lower right corners. For example, assuming that the point in the lower right corner is actually 40 meters east and 45 meters south of the point in the upper left corner, and the scale is 1:100, then the coordinates of the lower right corner are (40*100, 45*100). Because the scale of the entire image is approximate (the real distance represented by the same length on the edge and the middle image is approximate), the corresponding coordinates of the device can be directly obtained based on the position of the device in the image, and the range displayed in the image is also the entirety of the real-life display of the scheduling.

[0068] Then select the ground points around the intersection and before entering the intersection as anchor points, and directly obtain the coordinates of the anchor points through the graph. In the gun camera, by marking at least 4 anchor points on the screen and connecting them to form a closed image, the coordinate transformation is performed using perspective transformation according to the coordinates of the anchor points in the combined image and the coordinates of the anchor points in the screen (according to the coordinates of the 4 anchor points in the two coordinate systems, the conversion coordinate relationship matrix can be calculated, and then the coordinates of one coordinate system in the other coordinate system can be calculated using the left relationship matrix of the transformation). The coordinates of any point in the real picture of the intersection can be determined when the coordinates are converted to the image displayed at the intersection (the premise is that this point must be in the closed image formed by the anchor points. Since the anchor points correspond to ground points, any point in the closed image is on the ground. Only then does the coordinate transformation make sense. The perspective transformation can be used to deal with the problem of inconsistent scales in the picture, that is, the real distances represented by the same length are inconsistent). Then the center position of the vehicle display image is determined. When the center position is in the closed image formed by the anchor points, the vehicle positioning calculation and the appearance of the vehicle animation will be triggered. After the coordinates of the midpoint in the combined image are calculated, they are sent to the large screen, and the large screen displays the vehicle image at the coordinates.

[0069] Further, when it is detected that the vehicle display image is different from the historical vehicle display image determined at the last moment of the current moment, the current traffic flow information of the intersection is obtained. The historical vehicle display image includes the historical simulated position information of the target vehicle in the historical vehicle display image. The motion trajectory of the target vehicle is determined based on the traffic flow information, the simulated position information and the historical simulated position information. The motion trajectory is used to simulate the target vehicle traveling from the historical simulated position information to the simulated position information, and the simulation result is displayed on the intersection display image.

[0070] Exemplarily, when it is detected that the vehicle display image at the current moment is different from the historical vehicle display image at the previous moment, the current traffic flow information of the intersection is obtained. The historical vehicle display image includes the historical simulated position information of the target vehicle in the historical vehicle display image. The motion trajectory of the target vehicle is determined based on the traffic flow information, the current simulated position information and the historical simulated position information. The motion trajectory is used to simulate the process of the target vehicle traveling from the historical simulated position information to the current simulated position information, and the simulation result is displayed in the intersection display image. This process can provide a more intuitive vehicle motion trajectory to help traffic management personnel better understand the traffic conditions.

[0071] For example, during the movement of a vehicle, the coordinates and time of the vehicle in the image displayed at the intersection can be used. The coordinate difference and time difference between two consecutive times can be used to infer the movement trajectory of the vehicle, plus the time difference. Among them, the vehicle display image moves the coordinate difference within the time difference. The large screen and the combined image are in the same proportion. The speed of the vehicle display image on the large screen can be used to represent the speed of the real vehicle. The speed of the vehicle display image does not calculate the real speed.

[0072] The method for displaying vehicle dispatch status provided in the embodiment of the present application collects real-time images of the intersection through a camera, filters out vehicle contour information of the target vehicle from the image, generates a vehicle display image using a trained vehicle contour recognition model, and displays the vehicle display image on a simulated image corresponding to the intersection image. This method can monitor and dynamically display the traffic conditions at the intersection in real time, and can facilitate users such as traffic management departments to promptly understand the traffic conditions at the intersection so as to make quick responses.

[0073] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the working principle of the device. It is understandable that in order to realize the above functions, the display device of the vehicle dispatch situation includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0074] The embodiment of the present application can divide the functional modules of the display device of the vehicle dispatching situation according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or software functional module.

[0075] It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. Figure 3 A possible schematic diagram of the composition of the display device for the vehicle dispatching situation involved in the above-mentioned embodiment is shown. Figure 3 As shown, the display device 300 for vehicle dispatching conditions may include: a collection module 301 , a screening module 302 , a generation module 303 , and a display module 304 .

[0076] The acquisition module 301 is used to support the display device 300 of the vehicle dispatching situation to execute Figure 2 S201 in the method for displaying the vehicle dispatching situation is shown.

[0077] The screening module 302 is used to support the display device 300 of the vehicle dispatching situation to execute Figure 2 S202 in the method for displaying the vehicle dispatching situation is shown.

[0078] Generating module 303, used to support the display device 300 of vehicle dispatching situation to execute Figure 2 S203 in the method for displaying the vehicle dispatching situation is shown.

[0079] Display module 304, used to support the display device 300 of the vehicle dispatching situation to execute Figure 2 S204 in the method for displaying the vehicle dispatching situation is shown.

[0080] In a possible implementation, the device can also be used to extract vehicle profile information from the intersection image to obtain multiple pieces of vehicle profile information to be processed. The multiple pieces of vehicle profile information to be processed are compared for similarity to determine the similarity between the multiple pieces of vehicle profile information to be processed. When the similarity is less than a similarity threshold, the multiple pieces of vehicle profile information to be processed corresponding to the similarity are determined to be vehicle profile information.

[0081] In a possible implementation, the device can also be used to input vehicle contour information into a trained vehicle contour recognition model, determine multiple vehicle sub-images corresponding to the target vehicle and the combination relationship between the multiple vehicle sub-images, and combine the multiple vehicle sub-images using the combination relationship to generate a vehicle display image of the target vehicle.

[0082] In a possible implementation, the device can also be used to split the vehicle contour information to obtain multiple pixel areas of the vehicle contour information and the splitting relationship between the multiple pixel areas. The multiple pixel areas are input into the trained vehicle contour recognition model to determine the target feature corresponding to each pixel area and the feature probability of the target feature corresponding to each pixel area. Based on the target feature and the feature probability of the target feature, the vehicle sub-image corresponding to the pixel area is determined, and based on the splitting relationship between the multiple pixel areas, the combination relationship between the multiple vehicle sub-images is determined.

[0083] In a possible implementation, the device can also be used to obtain the position coordinates of multiple preset positions in a preset area in the intersection picture and the pixel position coordinates of multiple preset pixel positions in a preset pixel area in the intersection display image. The preset pixel area is the area corresponding to the preset area displayed in the intersection display image. The preset pixel position is the position corresponding to the preset position displayed in the intersection display image. Based on the position coordinates and the pixel position coordinates, the perspective conversion coefficient of the intersection picture perspective conversion to the intersection display image is determined. Based on the vehicle contour information, the vehicle position information of the target vehicle in the intersection picture is determined. Based on the vehicle position information and the perspective conversion coefficient, the simulation position information is determined.

[0084] In a possible implementation, the device can also be used to determine the center position of the vehicle display image based on the vehicle display image. When the center position enters a preset pixel area of ​​the intersection display image, the vehicle display image is displayed on the intersection display image based on the simulated position information.

[0085] In a possible implementation, the device can also be used to obtain the current traffic flow information at the intersection when it is detected that the vehicle display image is different from the historical vehicle display image determined at the previous moment of the current moment. The historical vehicle display image includes the historical simulated position information of the target vehicle in the historical vehicle display image. The motion trajectory of the target vehicle is determined based on the traffic flow information, the simulated position information and the historical simulated position information. The motion trajectory is used to simulate the target vehicle traveling from the historical simulated position information to the simulated position information, and the simulation result is displayed on the intersection display image.

[0086] It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0087] The vehicle dispatching status display device 300 provided in the embodiment of the present application is used to perform the above Figure 2 The method for displaying the vehicle dispatching situation shown can therefore achieve the same effect as the method for displaying the vehicle dispatching situation described above.

[0088] The embodiment of the present application also provides a vehicle dispatch status display device, which can execute the vehicle dispatch status display method and related steps in the above method embodiment.

[0089] The embodiment of the present application also provides a computer-readable storage medium on which instructions are stored. When the instructions are executed, the vehicle dispatch status display method and related steps in the above method embodiment are executed.

[0090] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer executes the method for displaying the vehicle dispatching situation and related steps in the above method embodiment.

[0091] In some embodiments, the methods described herein may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or encoded on other non-transitory media or articles of manufacture.

[0092] The embodiment of the present application also provides a vehicle dispatching status display system 400, such as Figure 4 As shown, the vehicle dispatching status display system 400 includes at least one processor 401 and at least one interface circuit 402 .

[0093] As an example, when the vehicle dispatching status display system 400 includes a processor and an interface circuit, the processor may be Figure 4 The processor 401 shown in the solid line frame (or the processor 401 shown in the dotted line frame) may be Figure 4 The interface circuit 402 shown in the solid line frame (or the interface circuit 402 shown in the dotted line frame) is shown in the solid line frame. When the vehicle dispatching status display system 400 includes two processors and two interface circuits, the two processors include Figure 4 The processor 401 shown in the solid line frame and the processor 401 shown in the dotted line frame, the two interface circuits include Figure 4 The interface circuit 402 shown in the solid line frame and the interface circuit 402 shown in the dotted line frame are not limited to this.

[0094] The processor 401 and the interface circuit 402 may be interconnected via a line. For example, the interface circuit 402 may be used to receive a signal. In another example, the interface circuit 402 may be used to send a signal to another device (e.g., the processor 401). For example, the interface circuit 402 may read a computer instruction stored in a memory and send the computer instruction to the processor 401. The processor 401 executes the instruction and implements the various steps in the above embodiments in combination with the input and output devices, such as implementing Figure 2 The various steps performed in the method embodiment shown. Of course, the vehicle dispatching status display system may also include other discrete components, which are not specifically limited in the embodiment of the present application.

[0095] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0096] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0098] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0099] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0100] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for displaying vehicle dispatching conditions, characterized in that: The method comprises: Using a camera to collect images of an intersection; the camera is deployed at the intersection; Filtering the vehicle profile information of the target vehicle at the current moment from the intersection picture; the target vehicle is any vehicle traveling at the intersection; Inputting the vehicle contour information into a trained vehicle contour recognition model to generate a vehicle display image of the target vehicle; Based on the vehicle display image, the simulated position information of the target vehicle in the intersection display image of the intersection is determined, and based on the simulated position information, the vehicle display image is displayed in the intersection display image; the intersection display image is a simulated image corresponding to the intersection screen.

2. The method according to claim 1, characterized in that The step of filtering out the vehicle profile information of the target vehicle at the current moment from the intersection picture includes: Extracting vehicle profile information from the intersection image to obtain a plurality of vehicle profile information to be processed; Performing a similarity comparison on the plurality of vehicle profile information to be processed to determine the similarity between the plurality of vehicle profile information to be processed; When the similarity is less than a similarity threshold, the plurality of to-be-processed vehicle profile information corresponding to the similarity is determined as the vehicle profile information.

3. The method according to claim 1, characterized in that The step of inputting the vehicle contour information into a trained vehicle contour recognition model to generate a vehicle display image of the target vehicle includes: Inputting the vehicle contour information into a trained vehicle contour recognition model to determine a plurality of vehicle sub-images corresponding to the target vehicle and a combination relationship between the plurality of vehicle sub-images; The plurality of vehicle sub-images are combined using the combination relationship to generate a vehicle display image of the target vehicle.

4. The method according to claim 3, characterized in that The step of inputting the vehicle contour information into a trained vehicle contour recognition model to determine a plurality of vehicle sub-images corresponding to the target vehicle and a combination relationship between the plurality of vehicle sub-images includes: Splitting the vehicle contour information to obtain a plurality of pixel regions of the vehicle contour information and a splitting relationship between the plurality of pixel regions; Inputting the plurality of pixel regions into a trained vehicle contour recognition model to determine a target feature corresponding to each pixel region and a feature probability of the target feature corresponding to each pixel region; The vehicle sub-image corresponding to the pixel region is determined according to the target feature and the feature probability of the target feature, and the combination relationship between the multiple vehicle sub-images is determined according to the splitting relationship between the multiple pixel regions.

5. The method according to claim 1, characterized in that The step of determining the simulated position information of the target vehicle at the intersection display image based on the vehicle display image includes: Acquire the position coordinates of a plurality of preset positions in a preset area in the intersection picture and the pixel position coordinates of a plurality of preset pixel positions in a preset pixel area in the intersection display image; the preset pixel area is an area corresponding to the preset area and displayed in the intersection display image; the preset pixel position is a position corresponding to the preset position and displayed in the intersection display image; Determining a perspective conversion coefficient of perspective conversion of the intersection picture to the intersection display image according to the position coordinates and the pixel position coordinates; Determining the vehicle position information of the target vehicle in the intersection picture according to the vehicle profile information; The simulated position information is determined according to the vehicle position information and the perspective conversion coefficient.

6. The method according to claim 1, characterized in that The step of displaying the vehicle display image on the intersection display image based on the simulated position information includes: Determining a center position of the vehicle display image according to the vehicle display image; When the center position enters a preset pixel area of ​​the intersection display image, the vehicle display image is displayed on the intersection display image based on the simulated position information.

7. The method according to claim 1, characterized in that The method further comprises: When it is detected that the vehicle display image is different from the historical vehicle display image determined at the previous moment of the current moment, the current traffic flow information of the intersection is acquired; the historical vehicle display image includes the historical simulated position information of the target vehicle in the historical vehicle display image; Determining the movement trajectory of the target vehicle according to the traffic flow information, the simulated position information and the historical simulated position information; The motion trajectory is used to simulate the target vehicle traveling from the historical simulated position information to the simulated position information, and the simulation result is displayed on the intersection display image.

8. A display device for vehicle dispatching, characterized in that: The device comprises: A collection module, used to collect the intersection picture of the intersection by using a camera; the camera is deployed at the intersection; A screening module, used to screen out the vehicle profile information of the target vehicle at the current moment from the intersection picture; the target vehicle is any vehicle traveling at the intersection; A generating module, used for inputting the vehicle contour information into a trained vehicle contour recognition model to generate a vehicle display image of the target vehicle; A display module is used to determine the simulated position information of the target vehicle in the intersection display image based on the vehicle display image, and display the vehicle display image in the intersection display image based on the simulated position information; the intersection display image is a simulated image corresponding to the intersection picture.

9. A vehicle dispatching status display device, characterized in that: The vehicle dispatching situation display device includes a processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the vehicle dispatching situation display method described in any one of claims 1-7.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by the processor, the machine-executable instructions prompt the processor to implement the method for displaying vehicle dispatch conditions according to any one of claims 1 to 7.

Images