WO2023066232A1

WO2023066232A1 - Three-dimensional scanning and imaging method and system for vehicle, and computer device and storage medium

Info

Publication number: WO2023066232A1
Application number: PCT/CN2022/125861
Authority: WO
Inventors: 鄂文轩; 周子策
Original assignee: 北京魔鬼鱼科技有限公司
Priority date: 2021-10-18
Filing date: 2022-10-18
Publication date: 2023-04-27
Also published as: CN114088041A

Abstract

A three-dimensional scanning and imaging method for a vehicle. The method comprises: establishing a unified three-dimensional coordinate system according to an operating environment in which a vehicle is located (S11); performing, by means of an imaging device, motion scanning on the vehicle parked in a parking area, so as to obtain appearance image data of the vehicle at different moments, and uniformly presenting the appearance image data in the three-dimensional coordinate system (S12); and aggregating the appearance image data presented in the unified coordinate system, so as to form complete three-dimensional image data of the appearance of the vehicle (S13).

Description

Vehicle three-dimensional scanning imaging method, system, computer equipment and storage medium

Cross References to Related Applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on October 18, 2021, with the application number CN202111210901.X and the application title "Method and System for Three-Dimensional Scanning and Imaging of Vehicles", the entire contents of which are incorporated herein by reference. Applying.

technical field

The present application belongs to the technical field of image recognition, and in particular relates to a vehicle three-dimensional scanning imaging method, system, computer equipment and storage medium.

Background technique

With the development of urban modernization, automatic car washing services have been widely demanded by the society.

In the field of automatic car washing, it is necessary to identify and image the shape of the vehicle to form subsequent path planning. Most of the current 3D imaging methods have problems such as poor imaging data quality and high cost. For example: tube imaging: only two-dimensional data, and the resolution is limited by the principle of the tube can not be too high, high cost; fixed position imaging: single or multiple ranging or imaging sensors (ranging sensor , ordinary camera, three-dimensional camera, lidar), the sensor’s incident angle and range are not ideal, the cost is extremely high, the data accuracy and resolution of the ranging sensor and ordinary camera are poor, and the resolution is low; space roaming imaging: SLAM imaging, low precision, Poor data consistency, poor angle of incidence and range. However, poor incident angle and poor range will easily lead to poor imaging accuracy and poor imaging quality.

Contents of the invention

In a first aspect, an embodiment of the present application provides a vehicle three-dimensional scanning imaging method, the method comprising:

Establish a unified three-dimensional coordinate system according to the operating environment of the vehicle;

Motion scanning of the vehicles parked in the parking area by the imaging device to obtain the image data of the vehicle's appearance at different times and present them in a unified three-dimensional coordinate system; and

The shape image data presented in the three-dimensional coordinate system is aggregated to form a complete three-dimensional image data of the vehicle.

In the second aspect, the embodiment of the present application provides a vehicle three-dimensional scanning imaging system, including:

The coordinate system establishment module is used to construct a unified three-dimensional coordinate system according to the structural layout in the working environment;

The image acquisition module is used to obtain the shape image data of the vehicle; wherein, the shape image data is obtained by scanning the outer side of the vehicle parked in the parking area through a variety of imaging devices; and

The image generation module is used to uniformly present the vehicle's outline image data acquired at different times in a three-dimensional coordinate system and perform data aggregation to form complete three-dimensional image data of the vehicle.

In a third aspect, an embodiment of the present application provides a computer device, which includes a memory and one or more processors, where computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the one or more processors, Causes one or more processors to perform the following steps:

In a fourth aspect, the embodiment of the present application provides one or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, one or more A processor performs the following steps:

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description, drawings, and claims.

Description of drawings

FIG. 1 is a schematic flowchart of a vehicle three-dimensional scanning imaging method according to an embodiment of the present application.

FIG. 2 is a structural diagram of a vehicle three-dimensional scanning imaging system according to an embodiment of the present application.

FIG. 3 is a schematic layout diagram of an imaging device according to an embodiment of the present application.

Figure 4 is an internal block diagram of a computer device in accordance with one or more embodiments.

Fig. 5 is a schematic diagram of an application environment of a vehicle three-dimensional scanning imaging method according to one or more embodiments.

Detailed ways

The following examples are only used to illustrate the technical solutions of the present application more clearly, but not to limit the protection scope of the present application. Certain terms are used, for example, in the description and claims to refer to particular components. Those skilled in the art should understand that hardware or software manufacturers may use different terms to refer to the same component. The specification and claims do not use the difference in name as the way to distinguish components, but use the difference in function of the components as the criterion for distinguishing. The subsequent descriptions in the specification are part of the implementation of the present application, but the descriptions are for the purpose of illustrating the general principles of the present application, and are not intended to limit the scope of the present application. The scope of protection of the present application should be defined by the appended claims.

The application will be further described below in conjunction with the accompanying drawings and specific embodiments.

An embodiment of the present application provides a three-dimensional scanning imaging method for a vehicle, which is used for acquiring vehicle shape features during a self-service car wash. Tracks are installed and fixed on the periphery of the parking area for cleaning. The track can be an elliptical track that surrounds the vehicle, or one or more linear tracks that are parallel or non-parallel along the length of the vehicle or other directions. The motion terminal of the track glide, the motion terminal can be a robot, a machine, or a module with simple functions such as imaging. The motion terminal comes with multiple and different types of sensors to scan the shape features of the vehicle in an all-round way. .

Referring to Fig. 1, the vehicle three-dimensional scanning imaging method may include step S101, step S102 and step S103.

Step S101: Establish a unified three-dimensional coordinate system according to the current environment structure where the vehicle is located.

Among them, establishing a three-dimensional coordinate system includes the following methods:

According to the structural layout of the working environment where the vehicle is located, determine a certain point in the structural layout as the coordinate origin, and at the same time determine the type and direction of the coordinate system; taking the car wash as an example, according to the size of the car wash, spatial structure layout, parking area and other factors , select a point in the space as the coordinate origin, and then determine the direction of the coordinate axes and the type of coordinates to establish a three-dimensional coordinate system, such as a three-dimensional Cartesian coordinate system. After establishing a unified coordinate system, the position data of all subsequent scanned image points will be calculated and judged in this coordinate system.

The structures in the environmental structure and the vehicle positions in the parking area are measured and calibrated to determine their coordinate points relative to the coordinate origin. After the coordinate system is selected, all static structures in the current environment structure and the subsequent vehicles entering the car wash have corresponding position coordinate points. Wherein, the selected structures may include tracks on the ground, lights on the walls, wall lines, parking lines and so on.

After the structure and parking position in the car wash room are calibrated, the image point position data actually scanned and imaged by the imaging device will be obtained later, based on the manually measured and calibrated structure and the coordinate point of the vehicle relative to the origin, which is consistent with the actual image point of the imaging device. The position data of an image point obtained by scanning is compared with the coordinate point of the origin. When there is an error between the two, the error range is preset in the imaging data and corrected, such as adjusting the rotation axis of the imaging device to adjust the imaging coordinates Points, such continuous corrections, make the coordinates of the two points as consistent as possible, thereby improving the accuracy of image recognition.

Step S102: The imaging device scans the motion of the vehicles parked in the parking area at different times to obtain the image data of the vehicle's appearance and present them in a unified coordinate system.

Wherein, motion scanning includes moving scanning, rotating scanning or a combination of both. Mobile scanning includes scanning in the horizontal direction, such as scanning in a straight line along the length of the vehicle or scanning in a circle or arc around the circumference of the vehicle body. Mobile scanning may also include scanning in the vertical direction, such as scanning when performing linear sliding in the vehicle height direction. Mobile scanning may also include oblique scanning, and the trajectory path of the imaging device is calculated and determined by the local computer or the background server, and its movement route is fixed and precise. During the moving scanning process, the imaging angle can also be rotated at the same time, and the image data formed during the moving process is essentially point cloud data. In the embodiment of the present application, some imaging devices scan and image in real time during motion. On the one hand, the imaging device is moving, and its position will change in the coordinate system, and the obtained imaging data is also determined based on the real-time positional relationship of the imaging device. The relationship between the movement displacement of the imaging device and time, and the positional relationship of the imaging device relative to the vehicle at a certain moment are corresponding to each other. Since the displacement of the imaging device is relatively definite and clear, the obtained vehicle imaging data is also relatively clearly.

In some optional implementations, the imaging device can acquire point cloud data of different parts of the vehicle from different angles at different times, and accumulate and superimpose the point cloud data, which significantly improves the resolution of the imaging aggregation data and also improves the imaging accuracy. The quality and imaging resolution are reduced from about 10cm of the original high-end lidar to less than 1cm, and the imaging accuracy is reduced from 2cm of the original high-end lidar to less than 1cm.

The acquisition of vehicle appearance features can be carried out through the cooperation of multiple different types of imaging devices. In some optional implementations, the imaging devices can include radar (such as laser radar, ultrasonic radar, millimeter wave radar, etc.), image sensor ( One or more of high-definition cameras, binocular or multi-eye cameras, TOF cameras, thermal imaging cameras, etc.), distance sensors.

In some optional embodiments, different types of imaging devices (that is, different types of sensors) can be used to collect independently at the same time, and each sensor has its own unique advantages. After fusion processing, data redundancy will be formed, from which better image feature points can be selected to reduce the defect that the imaging data of a single type of sensor is prone to missing or the imaging quality of a specific part of a pair of vehicles is poor, so as to be more complete. Capturing the complete features of the vehicle can also overcome the poor imaging quality of the vehicle's dark mirror surface.

When the sports terminal includes a machine, there can be one, two or more machines. There is a gap between the imaging sensor (ie, the sensor of the imaging device) and the vehicle body. It is better to install the imaging sensor at a height higher than the highest point of the vehicle body to avoid missing Roof imaging data, and better imaging angles when imaging other vehicle positions. In traditional technology, the incident source of the imaging sensor is in the direction of the vehicle's top view and side view, which is a vertical incidence, and imaging data cannot be captured in vertical parts such as the front and rear of the vehicle. When the imaging device in the embodiment of the present application scans at different positions of the vehicle body, the sensor is controlled to adjust different spatial attitudes. For example, when scanning following the shape of a car, ensure that the incident source is as close as possible to the normal line of the car. By controlling the running track of the sensor, the scanning that follows the shape of the vehicle can be completed. Specifically, during the continuous movement and/or rotation of the imaging sensors, at least at a certain moment, the incident angle of the radiation signal generated by one or more imaging sensors coincides with or approaches the normal of the vehicle surface. Taking sensors that actively transmit signals such as radars, distance sensors, and TOF (Time-of-Flight) cameras as examples, the incident signal is incident from the normal direction, and the reflected signal returns along the normal line, because it is nearly perpendicular to the surface of the object. Therefore, the reflection performance of the signal is the strongest, and there is the greatest possibility to obtain high-quality imaging data and ensure high accuracy and high confidence of the data. The specific performance is significantly improved available resolution, three-dimensional measurement accuracy, and the problem of dark mirrors is significantly improved. ; It is convenient for the precise planning of subsequent cleaning and air-drying trajectories. In addition, the imaging sensor is in the form of rotation and movement. Even if the signal source at a certain moment is not close to the normal of the vehicle shape, it will be close to the normal of the vehicle shape at the next moment or at other moments. line or coincident with the vehicle shape normal. The above-mentioned method overcomes the core problem of limited incident angle of the imaging sensor, cooperates with computer algorithms, significantly weakens the problem of dark mirrors, significantly improves the imaging coverage and imaging quality of the car body, and significantly improves the three-dimensional measurement accuracy.

In some embodiments, the image acquisition of the imaging device adopts a combination of global scanning and local scanning. Specifically, according to the division of work nature, it can be divided into main sensor and local sensor. The main sensor is responsible for the overall scanning of vehicle data, and the local sensor is responsible for scanning and imaging the area where the main sensor cannot accurately obtain data. The main sensor and the local sensor scan and image at the same time. The overall data is based on the scanning data of the main sensor. The main sensor should ensure the largest possible scanning coverage area, and the local sensor is responsible for the scanning data of special positions such as rearview mirrors and bumpers. When arranging, the installation height of the main sensor on the machine is usually relatively high, for example, it is located on the top of the moving machine to obtain a relatively good scanning area, and the location of the local sensor is mainly personalized according to the part to be scanned. For example, it can be arranged in the rearview mirror of a car, and the local sensor can also perform motion control (including movement, rotation, etc.).

In addition, in some optional implementation manners, after obtaining the shape image data of the vehicle, a filtering algorithm (such as a Kalman filtering algorithm) may be used to remove noise from the imaging data and retain high-quality data.

Step S103: Aggregating the outline image data presented in the three-dimensional coordinate system to form complete three-dimensional image data of the vehicle.

Since the imaging device is imaging in real time during motion, it is necessary to aggregate the vehicle shape image data acquired by the sensor from different angles at different times in a three-dimensional coordinate system, and finally form a complete three-dimensional image data of the vehicle, including the vehicle shape and various The location coordinates of the image points. According to the formed three-dimensional image data of the vehicle, the local computer or background server further calculates the cleaning path and air-drying path for the vehicle.

During image acquisition, the vehicle shape data acquired by imaging equipment often has missing or other abnormal problems, resulting in poor imaging effects, especially in dark mirrors (especially black mirrors) and car glass parts. To solve this problem, the acquired data can be further optimized to achieve a good imaging effect.

In some embodiments, optimizing the acquired shape image data includes the following methods:

The first way is to judge the continuity of the image data of the vehicle shape, and to perform fuzzy filling processing on the blank image area.

The vehicle shape has obvious continuity characteristics, and the continuity of the vehicle shape image data is used as the basis for judging whether the imaging data is complete. Among them, the continuity of the vehicle can be judged by outlier detection algorithm, region growing, or vehicle characteristics. Regional prior knowledge algorithm to judge. Outlier inspection is the process of finding out that its behavior is different from the expected object, including: outlier detection based on statistical methods, distance-based outlier inspection sum, density-based outlier inspection, etc., based on distance Take the outlier detection method as an example. It considers the neighborhood of a given radius of the object. If there are not enough other points in its neighborhood, it is considered an outlier, and the data that is obviously irregular is removed through the outlier test. . The region growing algorithm is to merge pixels with similar properties together, segment connected regions that do not have the same characteristics, and provide good boundary information and segmentation results. Exemplarily, for the scanned point cloud data, adjacent points are connected to form a grid, and the normal direction of the grid is calculated. The normal point cloud grids with the same direction have a high probability of belonging to the same object. The prior knowledge of the vehicle feature area is to first separate the different surface area properties of the vehicle through the feature model. If one of the areas is the front engine cover, it is judged that there is no large cavity in this area and it needs to be repaired. When it is judged that there is some discontinuity in the image data of the vehicle's shape, such as a hollow or blank area, it will perform fuzzy filling processing. The fuzzy filling can automatically generate an image for the blank area based on the interpolation filling algorithm.

Method 2: According to the symmetry characteristics of the vehicle, when the image data scanned on one side is detected to be defective, the qualified image data scanned on the other side is mirrored, and finally the complete 3D image data of the vehicle is synthesized. In some optional implementations, in response to detecting that the image data scanned from one side of the vehicle is defective, image processing is performed on qualified image data scanned from the other side, and finally the complete 3D image data of the vehicle is synthesized.

At present, most of the vehicles on the market are designed symmetrically. For example, the exterior rearview mirrors of automobiles will most likely not exist in isolation. Based on the above characteristics, when one side of the scan is defective, the mirror image replacement is performed using the scan result of the other side that is symmetrical. Specifically, through sensor motion scanning, it is judged whether the data is missing. If a certain part of the data is missing more seriously, but according to the central axis of the vehicle, look for the scanning result on the other side corresponding to the missing part. In actual operation, the hub data Imaging is the best in theory, so it is very convenient to use the contour data and coordinates on both sides as a reference, establish a symmetrical plane in the coordinate system, perform mirror replacement of left and right image data, and finally generate a complete 3D image data.

The third way is to establish a model database containing the complete shape of vehicles of different models, and construct a scene data model of structures and machinery in the current environment structure. When scanning the vehicle, locate the relative position of the vehicle in the current environment structure. When the vehicle scans If the image is still poor after optimization, the vehicle to be cleaned is replaced by a vehicle model of the same type in the model database at the current position. In addition, the historical scan data of the vehicle can also be stored. The stored historical scan data is at least the data reflecting the complete appearance characteristics of the vehicle, preferably the data of the complete appearance characteristics formed from the latest scan of the vehicle. When the vehicle has multiple scans, it can be Only keep one qualified scan data, and replace the previous scan data with the optimal scan data.

In some optional implementation manners, in response to the fact that the scanned vehicle shape image data is still determined to be bad after optimization processing, the following processing operations are performed: based on the established model database containing a large number of complete vehicle shapes of different models, according to the detected The model of the current vehicle is queried from the model database to replace the vehicle model data of the same model; or, query whether the current vehicle has historical scan data, and in response to the existence of historical scan data, select the corresponding vehicle model data from the historical scan data to replace .

The shape of the actual vehicle shall prevail. When the imaging quality cannot be optimized, or the corresponding standard cannot be reached after optimization, the shape data model of the same type of vehicle in the system database shall be directly replaced with the currently scanned data, or Query to find the corresponding data model from the previously scanned historical scan data of the vehicle. In this way, the background server directly takes the model data of the same type of vehicle in the model database or the model data in the historical scan data as the standard, and based on the queried vehicle The model data is used to plan the cleaning path and air-drying path.

The above three methods realize the optimization of the vehicle scanning data from different directions, wherein the above three methods can be performed independently, that is, directly select different optimization methods according to different situations, or cooperate with each other. For example, after the imaging scan is completed, the optimization of the first method is given priority, that is, the continuity of the image features of the vehicle shape is judged. If there are some discontinuities, the fuzzy filling process is directly performed. Basically, it can handle most of the scanning results; however, when there are large discontinuous parts, or the scanning quality of some areas is too poor, there are many faults, and fuzzy filling cannot be performed, the symmetrical optimization method in method 2 can be used. Of course, in the second method, the processing of the first method can also be carried out at the same time, for example, after the fuzzy filling of a certain part is performed on the side of the vehicle with a relatively good scanning result, and then the image data of the other side is obtained by mirroring based on this side; if in After the processing of method 1 and method 2, if still unable to obtain better imaging data, then consider method 3 to select similar vehicle models from the database or historical scan data for equivalent replacement.

In some optional implementation manners, an artificial intelligence model can also be constructed through big data, and continuously learn the advantages and disadvantages of different imaging devices or imaging data. Dynamic real-time scanning of vehicle appearance images, obtaining a large amount of scanning data, building an artificial intelligence model, learning and understanding the data defects existing in the machine imaging process, and making perfect and accurate predictions.

During the scanning imaging process, there will be more or less poor imaging effects, which may be related to the environment, such as light, temperature and humidity, or related to the scanning equipment itself, such as accuracy, angle , equipment parameters, etc., or have a relationship with the algorithm itself, such as filter parameters or filter models, through continuous scanning to obtain the shape image data of the vehicle, so that a large amount of scanning data can be obtained, based on these scanning data and results, an artificial intelligence model can be established , through continuous learning and understanding of the model, the defects of imaging equipment or imaging data can be excavated, and a set of parameter values with relatively accurate recognition rate can be calculated according to the results. Through the accumulation of big data, the parameters can be continuously adjusted and improved , and ultimately predict more accurate scan results.

A vehicle three-dimensional scanning imaging method disclosed in the embodiment of the present application can significantly improve the imaging accuracy and imaging quality by means of multi-sensor motion scanning in the same coordinate system. Improve the imaging quality, especially in the dark mirror and car glass, the imaging effect is better.

In some embodiments, the vehicle three-dimensional scanning method can be applied in the application environment shown in FIG. 5 . In FIG. 5 , the server 501 can execute the vehicle three-dimensional scanning method, for example, step S101 , step S102 and step S103 can be executed. Of course, the server 501 can also perform other more steps. The imaging device 502 can scan the vehicle in motion to obtain outline image data, and send the outline image data to the server 501 . In some optional implementation manners, the server 501 may also control the imaging device 502 to scan the vehicle for motion by sending a control signal.

In some of the above-mentioned embodiments, during the execution of the vehicle three-dimensional scanning imaging method, the resolution of the imaging data, the precision of the three-dimensional measurement and the imaging quality are improved through the motion scanning of multiple types of sensors.

In some of the above-mentioned embodiments, during the process of implementing the vehicle three-dimensional scanning imaging method, by adjusting the emission angle of the signal source of the sensor so that it can approach or coincide with the normal direction of the vehicle shape, the collected image data is clearer, Weaken dark specular issues.

In some of the above-mentioned embodiments, in the process of implementing the vehicle three-dimensional scanning imaging method, the effect of a method similar to high line beam lidar imaging accuracy and imaging quality and far lower cost is achieved or surpassed.

In some of the above-mentioned embodiments, in the process of executing the vehicle three-dimensional scanning imaging method, different types of optimizations are performed according to different situations through cooperation of different data optimization methods to form the best scanning imaging effect.

As shown in FIG. 2 , the embodiment of the present application provides a vehicle three-dimensional scanning imaging system 200 , which includes: a coordinate system establishment module 201 , an image acquisition module 202 , and an image generation module 203 .

The coordinate system establishment module 201 is configured to construct a unified three-dimensional coordinate system according to the structural layout of the working environment where the vehicle is located.

The image acquisition module 202 is used to acquire the image data of the vehicle's appearance. Wherein, the image acquisition module scans the outer side of the vehicle parked in the parking area through multiple different types of imaging devices. FIG. 3 is a schematic layout diagram of an imaging device in an embodiment of the present application. Exemplarily, the imaging device moves and scans in a horizontal direction along with machines A and B on slide rails on both sides.

The image generation module 203 is used for uniformly presenting the vehicle's outline image data acquired at different times in a three-dimensional coordinate system and performing data aggregation to form complete three-dimensional image data of the vehicle.

In order to improve the imaging quality, in some optional implementations, the vehicle three-dimensional scanning imaging system 200 may also include a data optimization module (not shown), which is used to judge the quality of the scanned outline image data and correct for optimization. The data optimization module may include: an image filling unit, a mirror image processing unit and a vehicle model replacement unit.

The image filling unit is used for performing fuzzy filling processing on blank image areas appearing in the scanned vehicle outline image data.

The mirror image processing unit is configured to, according to the symmetry characteristics of the vehicle, perform mirror image processing on the qualified image data obtained by scanning on the other side for replacement in response to detecting that the image data obtained by scanning on one side is defective. Wherein, the image processing unit can be used together with the graphic filling unit.

The vehicle model replacement unit includes a model database storing complete appearance features of different vehicle models and storing historical scanning data of the vehicle, for responding to the fact that the scanning imaging data of the current vehicle is still determined to be Bad, replace it with the model data of the same model vehicle in the model database, or select qualified model data from the historical scan data of the vehicle for replacement.

Of course, those skilled in the art should be able to understand that the various functional units in the above data optimization module can be performed independently or in cooperation with each other, but considering that there may be minor modifications or changes even in the same model, it is preferred to use the image Population cell processing, followed by mirror processing cells, and finally vehicle model replacement cells.

Due to the continuous scanning and imaging, the accumulation of big data has been formed. The system of the present application is also provided with a model building unit, which accumulates the shape image data of the vehicle acquired by dynamic real-time scanning of the machine equipment, and establishes an artificial intelligence model including the complete shape characteristics of the vehicle. By continuously learning the advantages and disadvantages of different imaging devices, improving the parameters of the imaging device or adjusting the filter parameters, and then improving the accuracy and scanning efficiency of image scanning.

For the specific limitations of the vehicle three-dimensional scanning imaging system 200, please refer to the above-mentioned limitations on the vehicle three-dimensional scanning imaging method, which will not be repeated here. Each module or unit in the above-mentioned vehicle three-dimensional scanning imaging system 200 may be fully or partially realized by software, hardware or a combination thereof. The above-mentioned modules or units may be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above modules.

The vehicle three-dimensional scanning imaging system in the embodiment of the present application may have the same technical effect as the vehicle three-dimensional scanning imaging method described in the foregoing embodiments, so details are not repeated here.

In some embodiments, an embodiment of the present application provides a computer device, including a memory and one or more processors, where computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the one or more processors, Make one or more processors execute the steps of the vehicle three-dimensional scanning imaging method in any one of the foregoing embodiments.

The computer device provided in the embodiment of the present application may be a server, and its internal structure diagram may be as shown in FIG. 4 . The computer device includes a processor, a memory, and a network interface connected through a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer readable instructions. The internal memory provides an environment for the execution of the operating system and computer readable instructions in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer-readable instructions are executed by the processor, the vehicle three-dimensional scanning imaging method in any embodiment herein can be implemented.

In some embodiments, the embodiments of the present application also provide one or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, a or a plurality of processors execute the steps of the vehicle three-dimensional scanning imaging method in any of the foregoing embodiments.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware. The aforementioned computer programs can be stored in a non-volatile computer-readable storage medium In this case, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any references to memory, storage, database or other media used in the various embodiments provided by the embodiments of the present disclosure may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

It is worth noting that the above are only some embodiments of the application, and do not limit the scope of patent protection of the application. equivalents are substituted. Therefore, all equivalent structural changes made by using the instructions and illustrations of this application, or directly or indirectly applied to other related technical fields are also included in the scope of this application.

Claims

A vehicle three-dimensional scanning imaging method, characterized in that it comprises:

Establish a unified three-dimensional coordinate system according to the operating environment of the vehicle;

Scanning the motion of the vehicles parked in the parking area through the imaging device, obtaining the image data of the vehicle's appearance at different times and presenting them in the unified three-dimensional coordinate system; and

The shape image data presented in the three-dimensional coordinate system are aggregated to form complete three-dimensional image data of the vehicle.
The imaging method according to claim 1, further comprising: judging the quality of the point cloud of the scanned outline image data and optimizing the quality defects;

Wherein, the optimization process includes: judging the continuity of the vehicle shape image data, and performing fuzzy filling processing on the blank image area; and/or, according to the symmetry characteristics of the vehicle, in response The obtained image data is bad, and the qualified image data scanned on the other side is mirrored, and finally the complete three-dimensional image data of the vehicle is synthesized.
The imaging method according to claim 2, further comprising: in response to the fact that the scanned profile image data of the vehicle is still determined to be bad after the optimization process, performing the following processing operations: A model database of the complete shape of the vehicle, according to the model of the detected current vehicle, query the vehicle model data of the same model from the model database for replacement; or, query whether the current vehicle has historical scan data, and respond to the presence of historical scan data, Select the corresponding vehicle model data from the historical scan data for replacement.
The imaging method according to claim 2, wherein said optimization processing also includes: dynamically scanning the outline image of the vehicle in real time, acquiring a large amount of scanning data, establishing an artificial intelligence model, and learning and understanding the presence of imaging equipment during the imaging process. defects and improve the working parameters of the imaging device.
The imaging method according to claim 1, wherein said establishing a unified three-dimensional coordinate system according to the working environment comprises:

According to the structural layout of the working environment where the vehicle is located, determine a certain point within the structural layout as the coordinate origin, and determine the type and direction of the coordinate system at the same time; and

Measure and calibrate the positions of the structures in the environmental structure and the vehicles in the parking area, and determine their coordinate points relative to the origin of the coordinates.
The imaging method according to claim 5, wherein the motion scanning comprises: correcting the actually scanned image data and the measured and calibrated position data;

The correction includes: taking the position coordinate points of the structure and the vehicle relative to the origin that have been measured and calibrated as the reference, and comparing with the coordinate points of the image data obtained by the actual scanning of the imaging device relative to the origin, to calibrate the imaging accuracy error, and if there is an error, the A margin of error is preset and corrected in the imaging data.
The imaging method according to claim 1, wherein the motion scan includes motion scan, rotation scan or a combination of the two, and the motion scan includes horizontal, vertical or oblique motion scan .
The imaging method according to claim 7, wherein the motion scanning further comprises: when scanning different positions of the vehicle, controlling and adjusting the position and posture of the imaging device so that the incident source is close to the normal direction of the vehicle surface ; Wherein, the scanning of different positions of the vehicle includes global scanning and local scanning.
The imaging method according to claim 1 or 8, wherein the imaging device includes one or more of laser radar, vision sensor, image sensor, distance sensor, millimeter wave sensor, ultrasonic sensor, thermal imaging sensor .
The imaging method according to claim 9, further comprising: performing fusion processing on image data collected by different types of imaging devices.
A vehicle three-dimensional scanning imaging system, characterized in that it comprises:

The coordinate system establishment module is used to construct a unified three-dimensional coordinate system according to the structural layout in the working environment;

The image acquisition module is used to acquire the outline image data of the vehicle; wherein, the outline image data is obtained by scanning the outer side of the vehicle parked in the parking area by various imaging devices; and

The image generating module is used for uniformly presenting the external image data of the vehicle acquired at different times in the three-dimensional coordinate system and performing data aggregation to form complete three-dimensional image data of the vehicle.
The system according to claim 10, further comprising: a data optimization module, configured to judge the quality of the scanned profile image data and optimize the data with quality defects;

Wherein, the data optimization module includes:

The image filling unit performs fuzzy filling processing on the blank image area appearing in the scanned vehicle shape image data;

The mirror image processing unit, according to the symmetry characteristics of the vehicle, responds to the detection of bad image data obtained by scanning on one side, and performs mirror processing on the qualified image data obtained by scanning on the other side to replace it;

The vehicle model replacement unit includes a model database storing the complete shape features of different vehicle models and storing historical scanning data of the vehicle, which is used to respond to the scanning imaging data of the preceding vehicle being processed by the image filling unit or the image processing unit and still determined as Defective, replace it with the model data of the same model vehicle in the model database, or select the corresponding qualified model data from the historical scan data of the vehicle for replacement; and

The intelligent model building unit accumulates the vehicle shape image data obtained by dynamic real-time scanning, and establishes an artificial intelligence model including vehicle shape features.
A computer device, characterized by comprising a memory and one or more processors, wherein computer readable instructions are stored in the memory, and when the computer readable instructions are executed by the one or more processors, the The one or more processors execute the steps of the method according to any one of claims 1-10.
One or more non-transitory computer-readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors Performing the steps of the method according to any one of claims 1-10.