A method and device for testing obstacle recognition function of an intelligent driving system on a vehicle

Abstract

The application provides a kind of vehicle-mounted intelligent driving system obstacle identification function test method and device, related to automatic driving technical field, which comprises: adopting wave-transparent material to make three-dimensional pedestal, three-dimensional pedestal includes multiple surfaces;Establish the mapping relationship between aging degree and physical properties, determine the physical properties of different surfaces based on the mapping relationship, physical properties include radar cross section and contrast;According to physical properties, radar reflection layer with different radar cross sections and visual texture layer with different visual textures are respectively arranged on each surface of three-dimensional pedestal to generate obstacles with different aging degrees on different surfaces;Using obstacles, the obstacle identification function of vehicle-mounted intelligent driving system is tested. By using the above vehicle-mounted intelligent driving system obstacle identification function test method and device, the functional test efficiency and test scene coverage when testing the vehicle-mounted intelligent driving system are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to a test method and apparatus for obstacle recognition function of an in-vehicle intelligent driving system. Background Technology

[0002] In the closed-course testing of intelligent connected vehicle combined driving assistance systems, obstacle recognition is a core testing component. Among these, cardboard boxes left on the road are a common obstacle and a typical test scenario. Intelligent driving systems primarily rely on fusion perception using cameras and millimeter-wave radar. Currently, two main methods are used for dealing with cardboard box obstacles: one is to use standard cardboard boxes, i.e., directly purchasing brand-new, clean corrugated cardboard boxes; the other is to use ISO standard target objects, which are uniformly sized target objects made of foam or inflatable materials with standard high-contrast textures printed on their surfaces. When testing obstacle recognition functionality, the obstacle is typically fixed to a trailer platform or placed stationary in the center of the lane, and the test vehicle approaches at different speeds to test whether the system triggers an alarm or brakes.

[0003] However, while existing obstacles are highly standardized, they are mostly in a brand-new state, which brings a series of problems: On the one hand, the uniform surface color and clear outline of brand-new obstacles cannot simulate obstacles of different aging stages, making it easy for visual recognition algorithms to overfit and leading to obstacle recognition errors; on the other hand, the constant dielectric constant and moisture content of brand-new obstacles lack material variation, making them easy for radar recognition algorithms to filter out as road clutter and miss detection. These problems mean that when testing the obstacle recognition function of intelligent driving systems, if it is necessary to test the obstacle recognition function in different new and old states, it is necessary to repeatedly move and change props, resulting in low functional testing efficiency and poor test scenario coverage. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a testing method and apparatus for the obstacle recognition function of an in-vehicle intelligent driving system, so as to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, embodiments of this application provide a testing method for the obstacle recognition function of an in-vehicle intelligent driving system, including: A three-dimensional base is made of a wave-transparent material, and the three-dimensional base includes multiple surfaces; Establish a mapping relationship between aging degree and physical properties, and determine the physical properties of different surfaces based on the mapping relationship. The physical properties include radar cross section and visual texture. Based on physical properties, radar reflective layers with different radar cross-sections and visual texture layers with different contrasts are set on each surface of the three-dimensional base to generate obstacles with different aging degrees on different surfaces. The obstacle recognition function of the in-vehicle intelligent driving system was tested using obstacles.

[0006] In an optional implementation, the obstacle recognition test includes at least one of the following: obstacle recognition test under a camera target recognition algorithm, and obstacle recognition test under a radar target recognition algorithm.

[0007] In an optional implementation, the step of determining the physical properties of the obstacle surface based on the mapping relationship includes: setting continuously increasing surface identifiers for multiple surfaces of the three-dimensional base; and determining the physical properties of each surface based on the mapping relationship in a manner that the degree of aging gradually increases with the increase of surface identifiers.

[0008] In an optional implementation, the step of setting radar reflective layers with different radar cross sections and visual texture layers with different contrasts on each surface of the three-dimensional base according to physical properties includes: attaching radar reflective materials with different first surface coverage rates to each surface in a manner that gradually decreases as the surface marking increases, so as to generate radar reflective layers with different radar cross sections on each surface of the three-dimensional base; and setting different aging textures on each radar reflective layer in a manner that gradually decreases as the contrast increases as the surface marking increases, so as to generate a visual texture surface layer on the radar reflective layer.

[0009] In an optional implementation, the step of attaching radar reflective materials with different first surface coverage rates to each surface in a manner that gradually decreases as the surface marking increases, in order to generate a radar reflective layer on the surface of the three-dimensional base, includes: when the surface marking meets a set threshold condition, attaching a radar-absorbing material with a second surface coverage rate that increases as the surface marking increases to the surface of the radar reflective material.

[0010] In an optional implementation, the step of setting different aging textures on each radar reflection layer to generate a visual texture surface layer on the radar reflection layer, in accordance with the principle that the contrast gradually decreases as the surface marking increases, includes: acquiring target images of real obstacles at different aging levels, extracting histogram features of the target images; generating texture maps at different aging levels based on the histogram features, and attaching the texture maps at different aging levels to the radar reflection layer to generate a visual texture layer.

[0011] In an optional implementation, before testing the obstacle recognition function of the vehicle-mounted intelligent driving system using obstacles, the method further includes: measuring the radar cross-sectional area of ​​different surfaces of the obstacle in a microwave anechoic chamber to see if they meet a preset cross-sectional area requirement, so as to perform obstacle recognition testing on the vehicle-mounted intelligent driving system when the preset cross-sectional area requirement is met.

[0012] In an optional implementation, before testing the obstacle recognition function of the vehicle-mounted intelligent driving system using obstacles, the method further includes: measuring whether the contrast of different surfaces of the obstacle meets a preset contrast requirement under a standard light source, so as to perform obstacle recognition testing on the vehicle-mounted intelligent driving system when the preset contrast requirement is met.

[0013] In an optional implementation, the step of testing the obstacle recognition function of the vehicle-mounted intelligent driving system using obstacles includes: setting each surface of the obstacle toward the oncoming vehicle direction in sequence for multiple rounds of testing to evaluate the obstacle recognition function of the vehicle-mounted intelligent driving system under different aging conditions.

[0014] Secondly, embodiments of this application also provide a testing device for the obstacle recognition function of an in-vehicle intelligent driving system, the device comprising: The base fabrication module is used to fabricate a three-dimensional base using wave-transparent materials. The three-dimensional base includes multiple surfaces. The mapping relationship determination module is used to establish the mapping relationship between aging degree and physical properties, and to determine the physical properties of different surfaces based on the mapping relationship. The physical properties include radar cross section and contrast. The obstacle generation module is used to set radar reflection layers with different radar cross sections and visual texture layers with different contrasts on each surface of the three-dimensional base according to physical properties, so as to generate obstacles with different aging degrees on different surfaces. The functional testing module is used to test the obstacle recognition function of the in-vehicle intelligent driving system using obstacles.

[0015] The embodiments of this application bring the following beneficial effects: This application provides a testing method and apparatus for obstacle recognition function of an in-vehicle intelligent driving system. It can simulate different degrees of aging of objects using an obstacle, and each surface of the obstacle has its own radar cross-section and contrast. This avoids the problem of repeatedly testing the same function, improves testing efficiency, and can cover a variety of testing scenarios. Compared with existing testing methods for obstacle recognition function of in-vehicle intelligent driving systems, this application solves the problems of low functional testing efficiency and poor testing scenario coverage when testing the obstacle recognition function of intelligent driving systems.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart is shown illustrating a test method for the obstacle recognition function of an in-vehicle intelligent driving system provided in an embodiment of this application; Figure 2 A flowchart illustrating the steps for generating the radar reflection layer and visual texture layer provided in the embodiments of this application is shown; Figure 3 This invention provides a schematic diagram of the structure of a test device for the obstacle recognition function of an in-vehicle intelligent driving system according to an embodiment of this application. Figure 4 A schematic diagram of the structure of the electronic device provided in the embodiments of this application is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0020] To facilitate understanding of this embodiment, the following describes each of the exemplary steps provided in this embodiment using the test method for obstacle recognition function of the in-vehicle intelligent driving system provided in this application embodiment as an example of its application to an autonomous driving test system.

[0021] Please see Figure 1 , Figure 1 This is a flowchart illustrating a testing method for obstacle recognition function of an in-vehicle intelligent driving system provided in an embodiment of this application. Figure 1 As shown in the embodiments of this application, the test method for obstacle recognition function of an in-vehicle intelligent driving system includes: Step S101: A three-dimensional base is made using a wave-transparent material.

[0022] A three-dimensional base can refer to a base with a regular shape, and a three-dimensional base includes multiple surfaces.

[0023] As an example, a three-dimensional base can be a hexahedral base, such as a cube base, in which case the three-dimensional base includes six independent surfaces.

[0024] In one embodiment, rigid foam or plastic can be used to make the three-dimensional base, and the size of the three-dimensional base meets the preset size requirements, for example, the three-dimensional base is made into a cube base of 60cm×60cm×60cm.

[0025] Step S102: Establish a mapping relationship between aging degree and physical properties, and determine the physical properties of each surface based on the mapping relationship.

[0026] Physical properties include the radar cross-section (RCS) of the radar reflector layer and the contrast of the visual texture layer.

[0027] Taking the above example, the three-dimensional base includes six surfaces, and the degree of aging is divided into six levels from brand new to extremely old. The six levels are: Level 1 aging degree, which is used to characterize brand new condition; Level 2 aging degree, which is used to characterize slight aging; Level 3 aging degree, which is used to characterize mild aging including stains and damage; Level 4 aging degree, which is used to characterize moderate aging including moisture / water immersion; Level 5 aging degree, which is used to characterize severe aging including breakage or tearing; and Level 6 aging degree, which is used to characterize extreme aging.

[0028] In one embodiment, as the degree of aging increases, the contrast and radar cross section decrease continuously.

[0029] For example: at the first level of aging, the contrast of the visual texture layer is set to be in the first percentage range (e.g., greater than 80%); at the second level of aging, the contrast of the visual texture layer is set to be in the second percentage range (80%~70%), and the second percentage range is smaller than the first percentage range, and so on, setting the numerical range of contrast for each level of aging.

[0030] For example, at the first level of aging, the radar cross-section of the radar reflector is set to be in the first cross-sectional area range (e.g., -5dBsm to 0dBsm); at the second level of aging, the radar cross-section of the radar reflector is set to be in the second cross-sectional area range (e.g., -8dBsm to -5dBsm), and the second cross-sectional area range is generally smaller than the first cross-sectional area range, and so on, setting the cross-sectional area range corresponding to the radar cross-section for each level of aging.

[0031] In one embodiment, when determining the physical properties of each surface of the three-dimensional base, continuously increasing surface identifiers can be set for multiple surfaces of the three-dimensional base, and the physical properties of each surface can be determined based on the mapping relationship in a manner that the degree of aging gradually increases with the increase of the surface identifier.

[0032] For example, if the six surfaces of the three-dimensional base are labeled as 1 to 6, then surface 1 corresponds to the first level of aging, the contrast of surface 1 is in the first percentage range and the radar cross-section is in the first cross-sectional area range; surface 2 corresponds to the second level of aging, the contrast of surface 2 is in the second percentage range and the radar cross-section is in the second cross-sectional area range, and so on, the physical properties of each surface can be determined.

[0033] Step S103: According to physical properties, radar reflection layers with different radar cross sections and visual texture layers with different contrasts are respectively set on each surface of the three-dimensional base to generate obstacles with different aging degrees on different surfaces.

[0034] The following reference Figure 2 This section will introduce the generation process of the radar reflection layer and the visual texture layer.

[0035] Figure 2 A flowchart illustrating the steps for generating the radar reflection layer and visual texture layer provided in the embodiments of this application is shown, such as... Figure 2 As shown, the steps for generating the radar reflection layer and the visual texture layer include: Step S1031: Following the principle that the first surface coverage gradually decreases as the surface marking increases, radar reflective materials with different first surface coverage are attached to each surface to generate radar reflective layers with different radar cross-sections on each surface of the three-dimensional base.

[0036] The first surface coverage rate can refer to the coverage rate of radar-reflecting material on a certain surface. The first surface coverage rate is used to distinguish it from the second surface coverage rate.

[0037] Specifically, a smooth radar-reflecting material with 100% coverage is attached to surface 1, maximizing the radar cross-section. A smooth radar-reflecting material with 70% coverage is attached to surface 2, where radar waves partially penetrate and partially reflect, resulting in a weakened echo intensity. Striped or fragmented radar-reflecting material with 50% coverage is attached to surface 3, simulating the discontinuous reflective surface after a cardboard box is damaged. This process continues, with the coverage gradually decreasing as the surface markings increase, until the coverage reaches zero. The radar-reflecting material can be aluminum foil; when the coverage is below 100%, perforations can be made in the aluminum foil.

[0038] In one embodiment, when the surface markings meet a set threshold condition, a radar-absorbing material with an increasing second surface coverage is attached to the surface of the radar-reflecting material as the surface markings increase.

[0039] The second surface coverage rate can refer to the coverage rate of the absorbing material on a certain surface.

[0040] For example: when the surface markings are greater than or equal to 4, the set threshold condition is determined to be met; when the surface markings are less than 4, the set threshold condition is determined not to be met. When the surface markings meet the set threshold condition, a radar-absorbing sponge with an increasing second surface coverage is attached to the surface of the radar-reflecting material as the surface markings increase.

[0041] In one embodiment, while reducing the coverage of the first surface of the radar-reflecting material and increasing the coverage of the second surface of the absorbing material, different coverage patterns of different materials on different surfaces can also be set.

[0042] For example, on surface 5, the radar reflective material coverage pattern is required to include collapse and wrinkles; on surface 3, the radar reflective material coverage pattern is required to include strips or fragments.

[0043] Step S1032: In accordance with the principle of gradually decreasing contrast as the surface marking increases, different aging textures are set on each radar reflection layer to generate a visual textured surface layer on the radar reflection layer.

[0044] Specifically, multiple target images of real obstacles at different aging levels are acquired beforehand, and the RGB histogram features of each target image are extracted. Then, the RGB histogram features are copied onto matte paper by printing to generate texture maps at different aging levels. Finally, following a pattern where the contrast gradually decreases as the surface marking increases, the texture maps at different aging levels are attached to the corresponding radar reflection layers to generate visual texture layers. For example, the contrast of each texture map is determined, and the texture map with the highest contrast is attached to the radar reflection layer corresponding to surface 1, the texture map with the second highest contrast is attached to the radar reflection layer corresponding to surface 2, and so on.

[0045] In one embodiment, in addition to contrast, visual feature requirements are also set for texture maps attached to different surfaces.

[0046] For example: the texture image affixed to surface 1 must have visual characteristics including standard kraft paper color, high saturation, and sharp edges; the texture image affixed to surface 2 must have visual characteristics including a slight whitening; the texture image affixed to surface 3 must have visual characteristics including stained spots and a grayish-white color; the texture image affixed to surface 4 must have visual characteristics including dark water stains; the texture image affixed to surface 5 must have visual characteristics including torn textures and irregular outlines; and the texture image affixed to surface 6 must have a completely black surface. Step S104: Using obstacles, test the obstacle recognition function of the vehicle intelligent driving system.

[0047] The obstacle was placed in the center of the lane on a closed test road, and each surface of the obstacle was set to face the oncoming traffic direction in turn for multiple rounds of testing to evaluate the obstacle recognition function of the onboard intelligent driving system under different aging conditions.

[0048] For example: First, with surface 1 facing the oncoming traffic, test the obstacle recognition function of the vehicle intelligent driving system when the vehicle is approaching the obstacle at a speed of 60 km / h, and record the recognition distance and whether braking is required; Second, rotate the obstacle by 90° so that surface 2 faces the oncoming traffic, and test the obstacle recognition function of the vehicle intelligent driving system at this time, recording the recognition distance and whether braking is required; and so on, with surfaces 3, 4, 5, and 6 facing the oncoming traffic respectively, test the obstacle recognition function of the vehicle intelligent driving system when different surfaces face the oncoming traffic, record the recognition distance and whether braking is required, and compare the changes in the perception confidence of the vehicle intelligent driving system under different aging conditions.

[0049] In one embodiment, the obstacle recognition test includes at least one of the following: obstacle recognition test under a visual recognition algorithm, and obstacle recognition test under a target recognition algorithm.

[0050] For example, when testing the obstacle recognition function of an in-vehicle intelligent driving system, the obstacle recognition function under the target recognition algorithm of the camera can be tested separately, or the obstacle recognition function under the target recognition algorithm of the millimeter-wave radar can be tested separately, or both the target recognition algorithm and the obstacle recognition function under the target recognition algorithm can be tested simultaneously.

[0051] In one embodiment, before testing the obstacle recognition function of the in-vehicle intelligent driving system using obstacles, the radar reflection layer and visual texture layer of the obstacle can be detected to determine whether they meet the test requirements.

[0052] For example, using the substitution method in a microwave anechoic chamber, an obstacle is placed at the center of a turntable. A vector network analyzer scans the obstacle within the 76GHz-79GHz frequency band. Using a standard triangular corner reflector as a reference, the average radar cross-section (RCS) of each surface of the obstacle is calculated. The RCS of different surfaces of the obstacle is then measured to ensure it meets the preset RCS requirement. If the RCS of each surface falls within its corresponding RCS range, it is considered to meet the preset RCS requirement; if the RCS of any surface does not fall within its corresponding RCS range, it is considered to fail to meet the preset RCS requirement. When the preset RCS requirement is met, obstacle recognition testing is performed on the in-vehicle intelligent driving system. The preset RCS requirement may refer to the RCS requirement in aging simulation.

[0053] Using a luminance meter under a D65 standard light source, the average luminance coefficient of the textured region on each surface of the obstacle was measured. The Michelson contrast ratio of the average luminance coefficient to that of a standard asphalt road surface was calculated. Based on the Michelson contrast ratio, the contrast ratio of different surfaces of the obstacle was measured to see if it met the preset contrast ratio requirements. If the contrast ratio of each surface was within its corresponding percentage range, it was determined to meet the preset contrast ratio requirements; if the contrast ratio of any surface was not within its corresponding range, it was determined to fail to meet the preset contrast ratio requirements. When the preset contrast ratio requirements were met, obstacle recognition tests were performed on the onboard intelligent driving system.

[0054] The testing method for obstacle recognition function of vehicle intelligent driving system provided in this application embodiment can simulate different degrees of aging of objects through an obstacle, and each surface of the obstacle has its own radar cross section and visual texture. This avoids the problem of repeatedly testing the same function, improves testing efficiency, and can cover a variety of test scenario requirements. It solves the problems of low functional testing efficiency and poor test scenario coverage when testing the obstacle recognition function of intelligent driving system.

[0055] Based on the same inventive concept, this application also provides a test device for the obstacle recognition function of an in-vehicle intelligent driving system, which corresponds to the test method for the obstacle recognition function of the in-vehicle intelligent driving system. Since the principle of the device in this application is similar to the test method for the obstacle recognition function of the in-vehicle intelligent driving system described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0056] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a test device for obstacle recognition function of an in-vehicle intelligent driving system provided in an embodiment of this application. Figure 3As shown, the testing device 200 for the obstacle recognition function of the in-vehicle intelligent driving system includes: The base fabrication module 201 is used to fabricate a three-dimensional base using a wave-transparent material. The three-dimensional base includes multiple surfaces. The mapping relationship determination module 202 is used to establish a mapping relationship between aging degree and physical properties, and to determine the physical properties of different surfaces based on the mapping relationship. The physical properties include radar cross section and contrast. The obstacle generation module 203 is used to set radar reflection layers with different radar cross sections and visual texture layers with different contrasts on each surface of the three-dimensional base according to physical properties, so as to generate obstacles with different aging degrees on different surfaces. Functional test module 204 is used to test the obstacle recognition function of the in-vehicle intelligent driving system using obstacles.

[0057] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 300 includes a processor 310, a memory 320, and a bus 330.

[0058] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate via the bus 330. When the machine-readable instructions are executed by the processor 310, they can perform the operations described above. Figure 1 The steps of the test method for the obstacle recognition function of the vehicle intelligent driving system in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0059] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 The steps of the test method for the obstacle recognition function of the vehicle intelligent driving system in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0060] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0062] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0063] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0064] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, 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 this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A test method for obstacle recognition function of an in-vehicle intelligent driving system, characterized in that, include: A three-dimensional base is made of a wave-transparent material, and the three-dimensional base includes multiple surfaces; Establish a mapping relationship between aging degree and physical properties, and determine the physical properties of different surfaces based on the mapping relationship. The physical properties include radar cross section and contrast. According to the physical properties, radar reflective layers with different radar cross-sections and visual texture layers with different contrasts are respectively set on each surface of the three-dimensional base to generate obstacles with different aging degrees on different surfaces. The obstacle recognition function of the in-vehicle intelligent driving system was tested using the aforementioned obstacle. The step of setting radar reflective layers with different radar cross-sections and visual texture layers with different contrasts on each surface of the three-dimensional base according to the physical properties includes: Radar reflective materials with different first surface coverage are attached to each surface in a manner that gradually decreases as the surface marking increases, so as to generate radar reflective layers with different radar cross-sections on each surface of the three-dimensional base. The surface marking refers to the continuously increasing markings set for multiple surfaces of the three-dimensional base. Different aging textures are applied to each radar reflection layer in such a manner that the contrast gradually decreases as the surface markings increase, so as to generate a visual textured surface layer on the radar reflection layer.

2. The method according to claim 1, characterized in that, The obstacle recognition function test includes at least one of the following: Obstacle recognition tests using camera-based target recognition algorithms and radar-based target recognition algorithms.

3. The method according to claim 1, characterized in that, The step of determining the physical properties of different surfaces based on the mapping relationship includes: Surface markings that are continuously increasing are provided on multiple surfaces of the three-dimensional base; The physical properties of each surface are determined based on the mapping relationship, in a manner that the degree of aging gradually increases with the increase of the surface markings.

4. The method according to claim 1, characterized in that, The method further includes: When the surface markings meet a set threshold condition, a radar-absorbing material with an increasing second surface coverage is attached to the surface of the radar-reflecting material as the surface markings increase.

5. The method according to claim 1, characterized in that, The step of setting different aging textures on each radar reflection layer in a manner that gradually decreases in contrast as the surface marking increases, to generate a visual textured surface layer on the radar reflection layer, includes: Acquire target images of real obstacles at different aging levels, and extract histogram features from the target images; Based on the histogram features, texture maps with different aging levels are generated, and the texture maps with different aging levels are attached to the radar reflection layer to generate a visual texture layer.

6. The method according to claim 1, characterized in that, Before testing the obstacle recognition function of the in-vehicle intelligent driving system using the aforementioned obstacle, the following steps are also included: In a microwave anechoic chamber, the radar cross-sectional area of ​​different surfaces of the obstacle is measured to determine whether it meets the preset cross-sectional area requirements, so as to perform obstacle recognition test on the vehicle intelligent driving system when it meets the preset cross-sectional area requirements.

7. The method according to claim 1, characterized in that, Before testing the obstacle recognition function of the in-vehicle intelligent driving system using the aforementioned obstacle, the following steps are also included: Under a standard light source, the contrast of different surfaces of the obstacle is measured to see if they meet the preset contrast requirements, so that the vehicle intelligent driving system can be tested for obstacle recognition when the preset contrast requirements are met.

8. The method according to claim 1, characterized in that, The step of testing the obstacle recognition function of the vehicle intelligent driving system using the obstacle includes: Multiple tests were conducted by sequentially setting each surface of the obstacle toward the direction of oncoming traffic to evaluate the obstacle recognition function of the in-vehicle intelligent driving system under different aging conditions.

9. A testing device for obstacle recognition function of an in-vehicle intelligent driving system, characterized in that, include: A base fabrication module is used to fabricate a three-dimensional base using a wave-transparent material, the three-dimensional base comprising multiple surfaces; The mapping relationship determination module is used to establish a mapping relationship between aging degree and physical properties, and to determine the physical properties of different surfaces based on the mapping relationship. The physical properties include radar cross section and contrast. An obstacle generation module is used to set radar reflection layers with different radar cross sections and visual texture layers with different contrasts on each surface of the three-dimensional base according to the physical properties, so as to generate obstacles with different aging degrees on different surfaces. The functional testing module is used to test the obstacle recognition function of the in-vehicle intelligent driving system using the obstacle. The obstacle generation module is specifically used for: Radar reflective materials with different first surface coverage are attached to each surface in a manner that gradually decreases as the surface marking increases, so as to generate radar reflective layers with different radar cross-sections on each surface of the three-dimensional base. Different aging textures are set on each radar reflection layer in such a way that the contrast gradually decreases as the surface markings increase, so as to generate a visual textured surface layer on the radar reflection layer. The surface markings refer to the continuously increasing markings set on multiple surfaces of the three-dimensional base.

Images