Adaptive scene reconstruction implementation method, system, terminal and storage medium

Abstract

The application discloses an ADAS adaptive scene reconstruction implementation method, system, terminal and storage medium, and comprises the following steps: presetting a first speed threshold V1 and a second speed threshold V2 of a vehicle, wherein the second speed threshold V2 is greater than the first speed threshold V1; presetting an initial perspective angle P of ADAS visual display of the vehicle; identifying and acquiring the number of obstacles of a target lane; judging whether the number of obstacles exceeds an obstacle number threshold, if yes, further judging whether the relative speed of the vehicle and a target vehicle is within a set value range, if yes, judging whether the vehicle speed V is within the first speed threshold V1 and the second speed threshold V2, if yes, performing scene reconstruction of ADAS visual display, and the application can solve the front vehicle overlapping problem of driving assistance.

Description

Technical Field

[0001] This invention belongs to the field of ADAS (Advanced Driver Assistance Systems) autonomous driving, and more specifically, relates to the implementation method, device system, terminal and storage medium of ADAS adaptive scene reconstruction. Background Technology

[0002] Cars have become a necessity in life, and driving safety is a common concern. Now, Advanced Driver Assistance Systems (ADAS) have become a standard feature in smart cockpits. They acquire road data through cameras, radar, and other means and present it in real time in a visual form on the center console to assist drivers in driving safely.

[0003] ADAS (Advanced Driver Assistance Systems) typically reconstructs road scenes from the driver's perspective using a fixed perspective angle to present road conditions and warnings. The ADAS visual display maintains a fixed perspective angle, using the same viewpoint regardless of vehicle speed or road conditions. However, in congested traffic, this perspective can cause visual overlap of vehicles ahead, preventing the driver from accurately identifying the status of vehicles ahead based solely on the information displayed on the center console. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper presents an ADAS adaptive scene reconstruction implementation method, device system, terminal, and storage medium to resolve the problem of overlapping vehicles in front during driver assistance.

[0005] In a first aspect, embodiments of this application provide an implementation method for ADAS adaptive scene reconstruction, including: presetting a first speed threshold V1 and a second speed threshold V2 for the vehicle, wherein the second speed threshold V2 is greater than the first speed threshold V1;

[0006] The initial perspective angle P of the ADAS visual display of this vehicle is preset;

[0007] Identify and obtain the number of obstacles in the target lane;

[0008] Determine whether the number of obstacles exceeds the obstacle number threshold. If it does, further determine whether the relative speed between the vehicle and the target vehicle is within the set value range. If so, determine whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, perform scene reconstruction for ADAS visual display.

[0009] As one possible implementation, the scene reconstruction for ADAS visual display further includes:

[0010] The perspective angle changes with the vehicle speed V and the trend of change is consistent, and the scene is reconstructed based on the perspective angle.

[0011] As one possible implementation, identifying and acquiring the number of obstacles in the target lane further includes:

[0012] Obtain the obstacle ratio and image visual data of the target lane;

[0013] The obstacle proportions and image visual data are uploaded to the system sample database, which contains obstacle feature information for people, two-wheeled vehicles, small cars, and large vehicles.

[0014] The obstacle proportions and image visual data are compared with the samples in the system's sample database to identify obstacle features.

[0015] As one possible implementation, when the number of obstacles is less than an obstacle number threshold, the initial perspective angle P of the ADAS visual display remains unchanged.

[0016] As one possible implementation, the ADAS visual display scene reconstruction is performed when the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2 and the duration is greater than a preset time.

[0017] As one possible implementation, the perspective angle changes proportionally from the initial perspective angle P to 0, following the change from the second velocity threshold V2 to the first velocity threshold V1, where V1 <V<V2。

[0018] As one possible implementation, when the vehicle speed V is less than the first speed threshold V1, the perspective angle of the ADAS visual display remains unchanged at 0.

[0019] Secondly, this application also provides an implementation system for ADAS adaptive scene reconstruction, including:

[0020] An initialization unit is used to preset a first speed threshold V1 and a second speed threshold V2 for the vehicle, wherein the second speed threshold V2 is greater than the first speed threshold V1; and to preset the initial perspective angle P of the ADAS visual display for the vehicle.

[0021] The identification unit is used to identify and obtain the number of obstacles in the target lane;

[0022] The judgment unit is used to determine whether the number of obstacles exceeds the obstacle number threshold. If it does, it further determines whether the relative speed between the vehicle and the target vehicle is within a set value range. If so, it determines whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, it performs scene reconstruction for ADAS visual display.

[0023] Thirdly, embodiments of this application provide a terminal, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the ADAS adaptive scene reconstruction implementation method as described above.

[0024] Thirdly, embodiments of this application provide a computer storage medium storing computer program instructions; when the computer program instructions are executed by a processor, they implement the above-described ADAS adaptive scene reconstruction method.

[0025] The ADAS adaptive scene reconstruction method and system of this application do not require any hardware changes. They only use software to change the perspective angle of the road reconstruction scene by setting the speed and target obstacle threshold, thereby solving the problem of overlapping of the vehicle in front in driving assistance. Attached Figure Description

[0026] Figure 1 This is a flowchart of the ADAS adaptive scene reconstruction implementation method of the present invention.

[0027] Figure 2 This is a hardware architecture diagram of the ADAS adaptive scene reconstruction implementation method of the present invention.

[0028] Figure 3A This is a scene reconstruction effect diagram of the ADAS visual display implemented in this invention.

[0029] Figure 3B This is a perspective angle diagram of the ADAS visual display implemented in this invention.

[0030] Figure 3C This is a top-down view of the ADAS visual display implemented in this invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that this invention is a system method for quantitative assessment and evaluation; the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0032] Existing technologies use a fixed perspective angle to present road vehicle conditions and warnings. Because the perspective angle of the ADAS visual display is fixed, the same display perspective is used for different vehicle speeds and road conditions. For example, in traffic congestion, the perspective presentation will cause the visual overlap of the vehicles in front, making it impossible for the driver to accurately identify the status of the vehicles in front through the information presented on the center console.

[0033] To address the aforementioned issues, in a first aspect, this application provides an ADAS adaptive scene reconstruction method. This method identifies and obtains the number of obstacles in a target lane, determines whether the number of obstacles exceeds an obstacle number threshold, and if so, further determines whether the relative speed between the vehicle and the target vehicle is within a set range. If so, it determines whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, it performs ADAS visual display scene reconstruction.

[0034] Reference Figure 1 , Figure 1 This is a flowchart illustrating the implementation method of ADAS adaptive scene reconstruction according to the present invention. Specifically, it may include the following steps:

[0035] Step S100: Preset a first speed threshold V1 and a second speed threshold V2 for the vehicle, wherein the second speed threshold V2 is greater than the first speed threshold V1, and preset the initial perspective angle P of the ADAS visual display for the vehicle.

[0036] In one example, taking a road data acquisition device with a measurable range of 90m as an example; setting the first speed threshold V1 = 5km / h and the second speed threshold V2 = 30km / h; setting the threshold for large target obstacles M = 6 based on the low-speed safe driving distance; the basic perspective angle (initial perspective angle) of the ADAS visual display is P, and the full top-down angle is 0, referring to... Figures 3A-3C .

[0037] Step S200, identifying and obtaining the number of obstacles in the target lane, specifically includes: Step S210 obtaining the obstacle ratio and image visual data of the target lane; Step S220 uploading the obstacle ratio and image visual data to the system sample database, which contains obstacle feature information of people, two-wheeled vehicles, small cars, and large vehicles; Step S230 comparing the obstacle ratio and image visual data with the samples in the system sample database to identify obstacle features.

[0038] In this embodiment, the road data acquisition device uses hardware such as millimeter-wave radar and binocular cameras to acquire the obstacle ratio and image visual data of the target lane, and uploads it to the system sample database for obstacle feature comparison. The system sample database contains obstacle information for people, two-wheeled vehicles, small cars, and large vehicles. In this embodiment, only the identified large obstacles (large and small vehicles) are included in the target obstacle quantity determination range. People and two-wheeled vehicles are smaller and are not included in the quantity determination.

[0039] Reference Figure 2 , Figure 2 This is a hardware architecture diagram of the ADAS adaptive scene reconstruction implementation method of this invention. The road data acquisition device obtains road status data and obstacle information through radar, cameras, and satellite navigation data; the speed data acquisition device collects the vehicle's speed CAN signal and the target vehicle's speed CAN signal; the speed sensor collects and uploads vehicle speed information; the ESC controller receives the speed information and transmits it to the IVI (In-Vehicle Infotainment) system; and the central control display screen displays the effect of scene reconstruction after IVI is applied.

[0040] Step S300: Determine whether the number of obstacles exceeds the obstacle number threshold. If it does, further determine whether the relative speed between the vehicle and the target vehicle is within the set value range. If so, determine whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, perform scene reconstruction for ADAS visual display.

[0041] In this embodiment, the scene reconstruction for ADAS visual display includes: the perspective angle changes with the vehicle speed V and the trend of change is consistent, and scene reconstruction is performed based on the perspective angle. It also includes performing ADAS visual display scene reconstruction when the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2 for a duration greater than a preset time.

[0042] In this embodiment, when the number of target obstacles does not reach the obstacle number threshold M, the ADAS visual display perspective angle remains unchanged at P, and the scene reconstruction of the ADAS visual display is not performed at this time.

[0043] When the number of target obstacles is greater than or equal to the threshold M, first, it is necessary to determine whether the relative speed between the host vehicle and the target vehicle is within the set value range. If so, the speed of the host vehicle is obtained. In an example, the speed data acquisition device collects the CAN signals of the speeds of the host vehicle and the target vehicle and determines that the relative speed is within the set value range, and uploads the speed V of the host vehicle to the IVI system through the speed sensor. Specifically, in step S300, on the basis that the number of obstacles exceeds the obstacle number threshold, the following condition 1 needs to be satisfied to start the scene reconstruction of the ADAS visual display:

[0044] Condition 1: When the speed V of the host vehicle is greater than the first speed threshold V1 and less than the second speed threshold V2, where V1 < V < V2, the reconstruction of the ADAS perspective scene is performed. Specifically, the perspective angle P to 0 changes proportionally with the speed threshold V2 to V1. The perspective angle of the ADAS visual display changes from P to 0 based on the change in the speed V of the vehicle, and the scene reconstruction is performed based on this perspective.

[0045] To prevent the jump of the scene reconstruction at the speed threshold critical point, on the basis of satisfying condition 1, the following condition 3 needs to be satisfied:

[0046] Condition 3: When the duration for which the speed of the current vehicle satisfies condition 1 (V1 < V < V2) is greater than 1 s, the reconstruction of the ADAS perspective scene is performed. In the actual application scenario, the ESC controller converts the pulses of the collected speed sensor, and updates the speed of the current vehicle every 10 ms. The speed of the current vehicle changes in real time. When the speed is at the speed threshold critical point, the scene reconstruction is frequently performed. To prevent the jump of the scene reconstruction at the speed threshold critical point, condition 3 is added. When the above conditions are satisfied, the IVI system will present the scene reconstruction of the ADAS visual information through the central control display screen.

[0047] In step S300, on the basis that the number of obstacles exceeds the obstacle number threshold, if the speed V of the host vehicle is less than or equal to the first speed threshold, i.e., V ≤ V1, the perspective angle of the ADAS visual display remains 0 without change.

[0048] In step S300, on the basis that the number of obstacles does not exceed the obstacle number threshold, the perspective angle of the ADAS visual display remains P unchanged.

[0049] In the second aspect of the present application, based on the above-mentioned implementation method of the ADAS adaptive scene reconstruction, in an embodiment of the present application, a system for implementing the ADAS adaptive scene reconstruction is further disclosed, including:

[0050] An initialization unit for presetting the first speed threshold V1 and the second speed threshold V2 of the host vehicle, where the second speed threshold V2 is greater than the first speed threshold V1; and presetting the initial perspective angle P of the ADAS visual display of the host vehicle.

[0051] The identification unit is used to identify and obtain the number of obstacles in the target lane;

[0052] The judgment unit is used to determine whether the number of obstacles exceeds the obstacle number threshold. If it does, it further determines whether the relative speed between the vehicle and the target vehicle is within a set value range. If so, it determines whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, it performs scene reconstruction for ADAS visual display.

[0053] In this embodiment, the scene reconstruction for ADAS visual display further includes:

[0054] The perspective angle changes with the vehicle speed V and the trend of change is consistent, and the scene is reconstructed based on the perspective angle.

[0055] In this embodiment, identifying and acquiring the number of obstacles in the target lane further includes: acquiring the obstacle ratio and image visual data of the target lane; uploading the obstacle ratio and image visual data to the system sample database, which contains obstacle feature information of people, two-wheeled vehicles, small cars, and large vehicles; and comparing the obstacle ratio and image visual data with the samples in the system sample database to identify the obstacle features.

[0056] In the implementation method of ADAS adaptive scene reconstruction, the more specific implementation process of the identification unit and the judgment unit can be found in the above-mentioned ADAS adaptive scene reconstruction implementation system, which will not be repeated here in this embodiment.

[0057] The above system and method embodiments correspond to the method embodiments and have the same technical effects. For detailed descriptions, please refer to the method embodiments. The system embodiments are derived from the method embodiments; detailed descriptions can be found in the method embodiment section, and will not be repeated here. Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0058] Based on the above method embodiments, a third aspect of this application provides a terminal, including: one or more processors;

[0059] A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method described above.

[0060] Based on the above method embodiments, a fourth aspect of this application provides a computer storage medium for implementation. The computer storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the ADAS adaptive scene reconstruction implementation methods in the above embodiments.

[0061] The ADAS adaptive scene reconstruction method and system of this application do not require any hardware changes. They only use software to change the perspective angle of the road reconstruction scene by setting the speed and target obstacle threshold, thereby solving the problem of overlapping of the vehicle in front in driving assistance.

[0062] Those skilled in the art will understand that the modules in the system of the embodiments can be distributed in the system of the embodiments as described in the embodiments, or they can be located in one or more systems different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for implementing ADAS adaptive scene reconstruction, characterized in that, Includes the following steps: The vehicle has a first speed threshold V1 and a second speed threshold V2, wherein the second speed threshold V2 is greater than the first speed threshold V1. The initial perspective angle P of the ADAS visual display of this vehicle is preset; Identify and obtain the number of obstacles in the target lane; Determine whether the number of obstacles exceeds the obstacle number threshold. If it does, further determine whether the relative speed between the vehicle and the target vehicle is within the set value range. If so, determine whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, perform scene reconstruction for ADAS visual display. The scene reconstruction for ADAS visual display further includes: The perspective angle changes with the vehicle speed V and the trend of change is consistent, and the scene is reconstructed based on the perspective angle.

2. The ADAS adaptive scene reconstruction implementation method as described in claim 1, characterized in that, The process of identifying and acquiring the number of obstacles in the target lane further includes: Obtain the obstacle ratio and image visual data of the target lane; The obstacle proportions and image visual data are uploaded to the system sample database, which contains obstacle feature information for people, two-wheeled vehicles, small cars, and large vehicles. The obstacle proportions and image visual data are compared with the samples in the system's sample database to identify obstacle features.

3. The ADAS adaptive scene reconstruction implementation method as described in claim 1, characterized in that, When the number of obstacles is less than the obstacle number threshold, the initial perspective angle P of the ADAS visual display remains unchanged.

4. The ADAS adaptive scene reconstruction implementation method as described in claim 1, characterized in that, The scene reconstruction for ADAS visual display is performed when the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2 and the duration is greater than a preset time.

5. The ADAS adaptive scene reconstruction implementation method as described in claim 4, characterized in that, The perspective angle changes proportionally from the initial perspective angle P to 0, following the change from the second velocity threshold V2 to the first velocity threshold V1, where V1 <V<V2。 6. The ADAS adaptive scene reconstruction implementation method as described in claim 1, characterized in that, When the number of obstacles exceeds the obstacle number threshold and the vehicle speed V is less than the first speed threshold V1, the perspective angle of the ADAS visual display remains unchanged at 0.

7. A system for implementing ADAS adaptive scene reconstruction, characterized in that, include: An initialization unit is used to preset a first speed threshold V1 and a second speed threshold V2 for the vehicle, wherein the second speed threshold V2 is greater than the first speed threshold V1. The initial perspective angle P of the ADAS visual display of this vehicle is preset; The identification unit is used to identify and obtain the number of obstacles in the target lane; The judgment unit is used to determine whether the number of obstacles exceeds the obstacle number threshold. If it does, it further determines whether the relative speed between the vehicle and the target vehicle is within a set value range. If so, it determines whether the vehicle speed V is within the range of the first speed threshold V1 and the second speed threshold V2. If so, it performs scene reconstruction for ADAS visual display. The scene reconstruction for ADAS visual display further includes: the perspective angle changes with the vehicle speed V and the change trend is consistent, and scene reconstruction is performed based on the perspective angle.

8. A terminal, comprising: One or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the ADAS adaptive scene reconstruction method as described in any one of claims 1-6.

9. A computer storage medium storing computer program instructions; when executed by a processor, the computer program instructions implement the ADAS adaptive scene reconstruction method as described in any one of claims 1-6.

Images