Automobile full-scene chassis global investigation method and system

Abstract

The embodiment of the invention provides an automobile full-scene chassis global investigation method and system, and the method comprises the steps: obtaining vehicle bottom information, and generating a moving path based on the vehicle bottom information; collecting a vehicle bottom image and a vehicle bottom point cloud in real time in a moving process according to the moving path, and performing real-time error compensation based on the vehicle bottom image and the vehicle bottom point cloud; carrying out image splicing on the vehicle bottom image and the vehicle bottom point cloud according to the acquisition timestamp, calculating a global error of the spliced vehicle bottom image and the vehicle bottom point cloud, and carrying out global compensation based on the global error; and fusing the globally compensated vehicle bottom image and the vehicle bottom point cloud to generate a three-dimensional model, performing damage detection based on the three-dimensional model, determining damage information and outputting report data.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle data acquisition, and particularly to a method and system for full-scenario chassis global survey of an automobile. Background Art

[0002] At present, in vehicle collision accidents, due to the difficulty in detecting the vehicle bottom, the research demand for vehicle bottom collision accidents is gradually increasing. Especially for new energy vehicles, battery packs are usually arranged at the bottom, and the damage of the battery pack has a great impact on the safety of the vehicle.

[0003] However, currently, for the survey of vehicle bottom damage, the vehicle is usually lifted for inspection, which requires special lifting equipment. It is impossible to conveniently inspect the bottom, and it is a potential safety hazard for personnel to reach the vehicle bottom, which is not conducive to in-depth investigation. Summary of the Invention

[0004] In view of the problems existing in the prior art, an embodiment of the present invention provides a method and system for full-scenario chassis global survey of an automobile.

[0005] An embodiment of the present invention provides a method for full-scenario chassis global survey of an automobile, the method comprising: Obtaining vehicle bottom information, and generating a movement path based on the vehicle bottom information; During the movement according to the movement path, the vehicle bottom image and vehicle bottom point cloud are collected in real time, and real-time error compensation is performed based on the vehicle bottom image and vehicle bottom point cloud, the real-time error compensation including: path movement compensation, attitude compensation, and dynamic error compensation; The vehicle bottom images and vehicle bottom point clouds are stitched according to the acquisition time stamps, the global error of the stitched vehicle bottom images and vehicle bottom point clouds is calculated, and global compensation is performed based on the global error; The vehicle bottom image and vehicle bottom point cloud after global compensation are fused to generate a three-dimensional model, damage detection is performed based on the three-dimensional model, and damage information is determined and report data is output.

[0006] In one of the embodiments, the method further comprises: Path movement compensation, collecting the ground height in real time, adjusting the movement trajectory and the angles of the camera module and the laser scanner based on the ground height, so that the vehicle bottom image and vehicle bottom point cloud are maintained at a unified angle during the movement; Attitude compensation, monitoring the rotational angular velocity, acceleration, and displacement of the movable survey device, calculating the device attitude information, calculating the rotation matrix and translation vector based on the attitude information, and converting the vehicle bottom image and vehicle bottom point cloud into the world coordinate system; Dynamic error compensation, extract feature points between adjacent frames of the vehicle bottom image and the vehicle bottom point cloud, and align the image and the point cloud through a frame-by-frame matching algorithm.

[0007] In one embodiment, the method further includes: Cumulative error compensation, correct the global error by minimizing the reprojection error for the vehicle bottom image and the vehicle bottom point cloud; Fusion error compensation, align and project the vehicle bottom image into the point cloud space, fill in missing frames through an interpolation algorithm, and use the point cloud data to correct the depth information in the projected vehicle bottom image.

[0008] In one embodiment, the method further includes: Identify environmental feature points, classify regions based on the environmental feature points, construct a map of the vehicle bottom according to the region classification results, and generate a movement path according to the map information of the vehicle bottom map.

[0009] In one embodiment, the method further includes: Detect the damaged area in the three-dimensional model, identify the geometric features and texture features of the damaged area, identify the total volume of the damaged area based on the geometric features, and identify the damage type in combination with the texture features.

[0010] An embodiment of the present invention provides an automotive full-scenario chassis global survey system, the system includes: An acquisition module, configured to acquire vehicle bottom information and generate a movement path based on the vehicle bottom information; A collection module, configured to, during the movement according to the movement path, collect the vehicle bottom image and the vehicle bottom point cloud in real time, and perform real-time error compensation based on the vehicle bottom image and the vehicle bottom point cloud, the real-time error compensation including: path movement compensation, attitude compensation, and dynamic error compensation; A splicing module, configured to splice the vehicle bottom image and the vehicle bottom point cloud according to the acquisition timestamp, calculate the global error of the spliced vehicle bottom image and the vehicle bottom point cloud, and perform global compensation based on the global error; A detection module, configured to fuse the vehicle bottom image and the vehicle bottom point cloud after global compensation, generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine damage information and output report data.

[0011] In one embodiment, the system further includes: A path movement compensation module, configured to collect the ground height in real time, adjust the movement trajectory and the angles of the camera module and the laser scanner based on the ground height, so that the vehicle bottom image and the vehicle bottom point cloud are maintained at a unified angle during the movement; An attitude compensation module, which is used to monitor the rotational angular velocity, acceleration and displacement of the movable exploration device, calculate the device attitude information, calculate the rotation matrix and translation vector based on the attitude information, and transform the vehicle bottom image and the vehicle bottom point cloud into the world coordinate system; A dynamic error compensation module, which is used to extract the feature points between adjacent frames of the vehicle bottom image and the vehicle bottom point cloud, and align the image and the point cloud through a frame-by-frame matching algorithm.

[0012] In one embodiment, the system further includes: An accumulated error compensation module, which is used to correct the global error of the vehicle bottom image and the vehicle bottom point cloud by minimizing the reprojection error; A fusion error compensation module, which is used to align and project the vehicle bottom image into the point cloud space, fill in the missing frames through an interpolation algorithm, and use the point cloud data to correct the depth information in the projected vehicle bottom image.

[0013] An embodiment of the present invention provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program codes; The processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in one or more embodiments.

[0014] An embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned full-scenario chassis global exploration method for vehicles are implemented.

[0015] In view of the above, in one or more embodiments of this specification, obtain the vehicle bottom information, generate a movement path based on the vehicle bottom information; during the movement according to the movement path, collect the vehicle bottom image and the vehicle bottom point cloud in real time, and perform real-time error compensation based on the vehicle bottom image and the vehicle bottom point cloud; splice the vehicle bottom image and the vehicle bottom point cloud according to the acquisition timestamp, calculate the global error of the spliced vehicle bottom image and the vehicle bottom point cloud, and perform global compensation based on the global error; fuse the vehicle bottom image and the vehicle bottom point cloud after global compensation to generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine the damage information and output the report data. In this way, it is possible to quickly and accurately detect accidents of the damaged condition of the vehicle bottom at the collision scene in a timely manner, and at the same time avoid the safety hazards of manual participation. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of a method for full-scenario chassis global survey of an automobile provided by an embodiment of this specification.

[0018] Figure 2 It is a schematic structural diagram of a full-scenario chassis global survey system of an automobile provided by an embodiment of this specification.

[0019] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of this specification. Detailed implementation manners

[0020] Now, the subject matter described herein will be discussed with reference to example embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein, and is not a limitation on the protection scope, applicability, or examples set forth in the claims. The functions and arrangements of the elements discussed can be changed without departing from the protection scope of the content of this specification. Each example can omit, substitute, or add various processes or components as needed. For example, the described method can be executed in a different order from the described order, and each step can be added, omitted, or combined. Additionally, the features described relative to some examples can also be combined in other examples.

[0021] As used herein, the term "including" and its variants represent open terms, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. can refer to different or the same objects. Other definitions, whether explicit or implicit, may be included below. Unless explicitly specified in the context, the definition of a term is consistent throughout the specification.

[0022] As Figure 1 shown, an embodiment of the present invention provides a method for full-scenario chassis global survey of an automobile, including: Step S102, obtaining vehicle bottom information and generating a moving path based on the vehicle bottom information.

[0023] Specifically, before collecting data on the vehicle bottom using a movable inspection device, the camera module and radar module of the movable inspection device can be used to scan the vehicle bottom and the ground environment, and route planning can be performed based on the vehicle bottom conditions and the ground environment. Among them, the route planning can be based on key feature points in the environment, such as tire edge points, chassis structural components, and special points in the environment (such as bumps, certain feature objects, etc.). Then, through deep learning algorithms, such as semantic segmentation algorithms, the ground features are classified to distinguish flat areas, passable but uneven areas, and obstacle areas. After determining each area, through a map construction algorithm, such as the SLAM algorithm, the data is constructed into a local map of the vehicle bottom, and the optimal movement path of the device is generated based on the map information. The optimal movement path should ensure coverage of all target areas. Moreover, during the movement of the device along the optimal movement path, it should move at a uniform speed in different areas as much as possible, so as to further improve the accuracy of the image compensation step in the subsequent steps.

[0024] In addition, the movable inspection device not only has a camera module and a radar module for path planning, but also calibration modules such as a camera calibration module, a scanner module, a gyroscope, and an inertial navigation device should be configured. In addition, for the dim environment at the vehicle bottom, a supplementary lighting module can also be included, which can adjust the supplementary lighting intensity according to the environmental brightness during the inspection process to ensure the image quality.

[0025] Step S104, during the movement according to the movement path, the vehicle bottom image and the vehicle bottom point cloud are collected in real time, and real-time error compensation is performed based on the vehicle bottom image and the vehicle bottom point cloud. The real-time error compensation includes: path movement compensation, attitude compensation, and dynamic error compensation.

[0026] Specifically, during the process of collecting the vehicle bottom image by the device according to the movement path, it not only includes collecting the vehicle bottom images of different areas (such as the central area, the edge area) of the vehicle bottom through the multi-view camera module of the device, but also includes the vehicle bottom point cloud data generated by scanning with a three-dimensional scanning module, such as a laser scanner. During the multi-angle scanning by multiple scanners, the spatial coordinates and reflection intensity of each point are recorded.

[0027] Furthermore, during the process of collecting the vehicle bottom image, the device will perform error compensation on the vehicle bottom image and the vehicle bottom point cloud in real time based on the calibration module. Among them, the real-time error compensation includes path movement compensation, attitude compensation, and dynamic error compensation, including: Path movement compensation: During the movement of the device, the ground may be uneven (such as slopes, potholes), resulting in tilting or height changes of the device during movement. The compensation scheme can be to collect the ground height changes in real time through a radar module during the device movement, and adjust the movement trajectory of the device according to the ground height map to keep it as horizontal as possible. If the road surface height changes greatly, the angles of the camera and laser scanner can also be adjusted to keep their original postures, ensuring that the captured images and point clouds maintain a unified angle.

[0028] Attitude compensation: During the movement of the device, changes in the pitch angle, yaw angle or roll angle may occur due to ground friction, vibration, etc., resulting in geometric distortion (such as stretching, twisting) in the captured images and point cloud data. The compensation scheme can be to calculate accurate attitude information through the Kalman filter algorithm by monitoring the rotational angular velocity, acceleration and displacement of the device, calculate the rotation matrix and translation vector of the current frame according to the attitude information, and transform the image and point cloud data from the device coordinate system to the world coordinate system to eliminate the influence of attitude changes.

[0029] Dynamic error compensation: During the process of multi-view image and point cloud stitching of the device, due to the incomplete accuracy of the device movement trajectory, the stitching result may deviate (such as misalignment in the overlapping area). The compensation method can be to extract the feature points between adjacent frames and align the images and point clouds through a frame-by-frame matching algorithm.

[0030] Step S106: Stitch the vehicle bottom image and vehicle bottom point cloud according to the acquisition timestamp, calculate the global error of the stitched vehicle bottom image and vehicle bottom point cloud, and perform global compensation based on the global error.

[0031] Specifically, after the device operation is completed, stitch the collected vehicle bottom image and vehicle bottom point cloud according to the acquisition timestamp. An image stitching algorithm based on feature points can be used to align multi-view images (including point clouds) and fuse the overlapping areas to generate a preliminary panoramic view of the vehicle bottom (and a 3D model generated based on point cloud data). Calculate the global error of the stitched vehicle bottom image and vehicle bottom point cloud. The global error includes cumulative error and fusion error.

[0032] Cumulative error is the superimposed error (such as drift error, time synchronization error) that inevitably occurs during the data acquisition process. The cumulative error will cause a certain deviation between the finally generated three-dimensional model and the actual shape of the vehicle bottom. After calculating the deviation between the stitching result and the actual shape, the corresponding cumulative error compensation can be to use the Bundle Adjustment algorithm to globally optimize all image and point cloud data. By minimizing the reprojection error (i.e., the deviation between the image feature points and the projected points of the point cloud), the global error is corrected. It is also possible to approximate the vehicle bottom as a plane through plane fitting, and by adjusting the position and pose of the point cloud data, make it better conform to the plane constraint.

[0033] Fusion error is due to the fact that images and point clouds come from different sensors, and there may be spatial and temporal inconsistencies. Eliminating the error can lay a foundation for subsequent fusion steps. The corresponding fusion error compensation can be to project the image data into the point cloud space to ensure their spatial alignment. For temporally inconsistent data, interpolation algorithms (such as linear interpolation) are used to fill in the missing frames, and then the depth information in the image is corrected using the point cloud data to ensure that the fused model has high-precision geometric details.

[0034] Step S108: Fuse the vehicle bottom image and the vehicle bottom point cloud after global compensation to generate a three-dimensional model, and perform damage detection based on the three-dimensional model to determine the damage information and output the report data.

[0035] Specifically, fuse the globally compensated vehicle bottom image and the vehicle bottom point cloud to generate a three-dimensional model of the vehicle bottom. The fusion process can, for example, extract the key feature points in the image and the point cloud through deep learning algorithms, and then align the image and the point cloud through the feature point matching algorithm. Further, map the color information in the image onto the point cloud model to generate a three-dimensional model with real textures. After generating the three-dimensional model, the damaged areas in the three-dimensional model can be automatically marked for damage detection. This includes extracting the geometric features (such as depth, curvature) and texture features (such as color changes) of the damaged areas, and then based on the point cloud data, measuring the size (length, width, depth) and area of the damaged areas, using the volume integral algorithm to calculate the total volume of the damaged areas, and combining the texture features to determine the damage type, such as dents, cracks, scratches, deformations, etc. Based on the damaged areas, summarize the corresponding damage information (including the damaged areas, damage types, and severity) to generate the corresponding full-scenario chassis global inspection report data of the vehicle for the user to determine the damage situation of the vehicle bottom.

[0036] In addition, the fusion of the under-vehicle image and the under-vehicle point cloud may include a hierarchical feature fusion architecture, such as including three-layer fusion: bottom-layer fusion: realizing rough registration of pixel-point cloud through SURF feature point matching; middle-layer fusion: adopting an improved ICP algorithm (introducing normal vector constraint) for fine registration; high-layer fusion: constructing a Voxel-Pixel joint feature space and using a three-dimensional convolutional neural network to realize texture-geometry joint optimization.

[0037] A method for full-scenario chassis global survey of a vehicle provided by an embodiment of the present invention includes obtaining vehicle bottom information and generating a moving path based on the vehicle bottom information; during the movement according to the moving path, collecting an under-vehicle image and an under-vehicle point cloud in real time, and performing real-time error compensation based on the under-vehicle image and the under-vehicle point cloud; splicing the under-vehicle image and the under-vehicle point cloud according to the acquisition timestamp, calculating the global error of the spliced under-vehicle image and under-vehicle point cloud, and performing global compensation based on the global error; fusing the under-vehicle image and the under-vehicle point cloud after global compensation to generate a three-dimensional model, performing damage detection based on the three-dimensional model, determining damage information and outputting report data. This can quickly and accurately detect accidents of the damaged condition of the vehicle bottom at the collision scene in a timely manner, and at the same time avoid potential safety hazards caused by manual participation.

[0038] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a full-scenario chassis global survey system for a vehicle provided by an embodiment of the present application. As Figure 2 shown, the system includes: An acquisition module S202, configured to obtain vehicle bottom information and generate a moving path based on the vehicle bottom information; A collection module S204, configured to collect an under-vehicle image and an under-vehicle point cloud in real time during the movement according to the moving path, and perform real-time error compensation based on the under-vehicle image and the under-vehicle point cloud, where the real-time error compensation includes: path movement compensation, attitude compensation, and dynamic error compensation; A splicing module S206, configured to splice the under-vehicle image and the under-vehicle point cloud according to the acquisition timestamp, calculate the global error of the spliced under-vehicle image and under-vehicle point cloud, and perform global compensation based on the global error; A detection module S208, configured to fuse the under-vehicle image and the under-vehicle point cloud after global compensation to generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine damage information and output report data.

[0039] In another embodiment, a full-scenario chassis global survey system for a vehicle further includes: A path movement compensation module, configured to collect the ground height in real time, adjust the movement trajectory and the angles of the camera module and the laser scanner based on the ground height, so that the under-vehicle image and the under-vehicle point cloud are maintained at a unified angle during the movement; The attitude compensation module is used to monitor the rotational angular velocity, acceleration and displacement of the movable exploration device, calculate the device attitude information, calculate the rotation matrix and translation vector based on the attitude information, and transform the underbody image and underbody point cloud into the world coordinate system; The dynamic error compensation module is used to extract the feature points between adjacent frames of the underbody image and underbody point cloud, and align the image and point cloud through a frame-by-frame matching algorithm.

[0040] In another embodiment, an automotive full-scenario chassis global exploration system further includes: The cumulative error compensation module is used to correct the global error of the underbody image and underbody point cloud by minimizing the reprojection error; The fusion error compensation module is used to align and project the underbody image into the point cloud space, fill in the missing frames through an interpolation algorithm, and use the point cloud data to correct the depth information in the projected underbody image.

[0041] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented by means of software and / or hardware. The "units" and "modules" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0042] Each processing unit and / or module of the embodiments of the present application can be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or can be implemented by software that executes the functions described in the embodiments of the present application.

[0043] See Figure 3 , which shows a schematic structural diagram of an electronic device related to the embodiments of the present application. This electronic device can be used to implement Figure 1 the method in the embodiments shown. As Figure 3 shown, the electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0044] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0045] Among them, the user interface 303 may include a display screen (Display), a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0046] Among them, the network interface 304 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).

[0047] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire electronic device 300 through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305, it executes various functions of the terminal 300 and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0048] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. The memory 305 may optionally also be at least one storage device located far from the aforementioned processor 301. As Figure 3 shown, the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0049] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 301 can be used to call the interactive application program generated based on images stored in the memory 305 and specifically perform the following operations: obtain the information of the bottom of the vehicle, generate a moving path based on the information of the bottom of the vehicle; during the movement according to the moving path, collect the bottom image and the bottom point cloud of the vehicle in real time, and perform real-time error compensation based on the bottom image and the bottom point cloud of the vehicle; splice the bottom image and the bottom point cloud of the vehicle according to the acquisition timestamp, calculate the global error of the spliced bottom image and the bottom point cloud of the vehicle, and perform global compensation based on the global error; fuse the bottom image and the bottom point cloud of the vehicle after global compensation to generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine the damage information and output the report data.

[0050] The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. Among them, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nano-systems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0051] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0052] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0053] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some service interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0054] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0055] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0056] If the above-mentioned 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 computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), external hard drives, magnetic disks, or optical discs, etc., all of which can store program codes.

[0057] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc.

[0058] The specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An all-scenario chassis global exploration method for automobiles, characterized in that, Applied to a movable exploration device, the method includes: Obtain the information of the vehicle bottom, and generate a moving path based on the vehicle bottom information; During the movement according to the moving path, collect the vehicle bottom image and vehicle bottom point cloud in real time, and perform real-time error compensation based on the vehicle bottom image and vehicle bottom point cloud. The real-time error compensation includes: path movement compensation, attitude compensation, and dynamic error compensation; Stitch the vehicle bottom image and vehicle bottom point cloud according to the acquisition timestamp, calculate the global error of the stitched vehicle bottom image and vehicle bottom point cloud, and perform global compensation based on the global error; Fuse the vehicle bottom image and vehicle bottom point cloud after global compensation to generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine the damage information and output the report data.

2. The method according to claim 1, wherein The real-time error compensation includes: Path movement compensation: Collect the ground height in real time, adjust the movement trajectory and the angles of the camera module and the laser scanner based on the ground height, so that the vehicle bottom image and vehicle bottom point cloud are maintained at a unified angle during the movement; Attitude compensation: Monitor the rotational angular velocity, acceleration, and displacement of the movable exploration device, calculate the device attitude information, calculate the rotation matrix and translation vector based on the attitude information, and transform the vehicle bottom image and vehicle bottom point cloud into the world coordinate system; Dynamic error compensation: Extract the feature points between adjacent frames of the vehicle bottom image and vehicle bottom point cloud, and align the image and point cloud through a frame-by-frame matching algorithm.

3. The method according to claim 1, characterized in that The global compensation includes: Cumulative error compensation: Correct the global error by minimizing the reprojection error for the vehicle bottom image and vehicle bottom point cloud; Fusion error compensation: Align and project the vehicle bottom image into the point cloud space, fill in the missing frames through an interpolation algorithm, and use the point cloud data to correct the depth information in the projected vehicle bottom image.

4. The method according to claim 1, wherein The generation of the moving path based on the vehicle bottom information includes: Identify the environmental feature points, classify the regions based on the environmental feature points, construct a vehicle bottom map according to the region classification result, and generate a moving path according to the map information of the vehicle bottom map.

5. The method according to claim 1, wherein The damage detection based on the three-dimensional model includes: Detect the damaged area in the three-dimensional model, identify the geometric features and texture features of the damaged area, identify the total volume of the damaged area based on the geometric features, and identify the damage type in combination with the texture features.

6. An all-scenario vehicle chassis full-domain inspection system, characterized in that The system includes; An acquisition module, which is used to obtain the vehicle bottom information and generate a moving path based on the vehicle bottom information; A collection module, which is used to collect the vehicle bottom image and vehicle bottom point cloud in real time during the movement according to the moving path, and perform real-time error compensation based on the vehicle bottom image and vehicle bottom point cloud. The real-time error compensation includes: path movement compensation, attitude compensation, and dynamic error compensation; A stitching module, which is used to stitch the vehicle bottom image and vehicle bottom point cloud according to the acquisition timestamp, calculate the global error of the stitched vehicle bottom image and vehicle bottom point cloud, and perform global compensation based on the global error; A detection module, which is used to fuse the vehicle bottom image and vehicle bottom point cloud after global compensation to generate a three-dimensional model, perform damage detection based on the three-dimensional model, determine the damage information and output the report data.

7. The system according to claim 6, characterized in that, The system further includes: A path movement compensation module, configured to collect the ground height in real time, adjust the movement trajectory and the angles of the camera module and the lidar scanner based on the ground height, so that the bottom image of the vehicle and the bottom point cloud of the vehicle are maintained at a unified angle during movement; An attitude compensation module, configured to monitor the rotational angular velocity, acceleration and displacement of the movable exploration device, calculate the device attitude information, calculate a rotation matrix and a translation vector based on the attitude information, and transform the bottom image of the vehicle and the bottom point cloud of the vehicle into the world coordinate system; A dynamic error compensation module, configured to extract feature points between adjacent frames of the bottom image of the vehicle and the bottom point cloud, and align the image and the point cloud through a frame-by-frame matching algorithm.

8. The system according to claim 6, wherein The system further includes: An accumulated error compensation module, configured to correct the global error by minimizing the reprojection error of the bottom image of the vehicle and the bottom point cloud; A fusion error compensation module, configured to align and project the bottom image of the vehicle into the point cloud space, fill in missing frames through an interpolation algorithm, and correct the depth information in the bottom image of the vehicle after projection using the point cloud data.

9. An electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is configured to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1-5 is implemented.

Images