Underground three-dimensional scanning inspection method and device, electronic equipment and storage medium

Abstract

The invention provides an underground three-dimensional scanning inspection method and device, electronic equipment and a storage medium, the method is applied to an inspection system, the inspection system at least comprises a plurality of radar sensors arranged on the same mobile platform, and the method comprises the following steps: acquiring three-dimensional data in a mine environment collected by the plurality of radar sensors; based on an extended Kalman filter algorithm, performing distributed processing on the three-dimensional data acquired by each radar sensor to obtain target point cloud data corresponding to the three-dimensional data, the target point cloud data being point cloud data capable of performing data fusion in the same coordinate system; and based on the target point cloud data, constructing a three-dimensional environment map in the mine environment. The three-dimensional perception capability in a complex mine environment can be improved, and the robustness and accuracy of an inspection result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of underground inspection, and in particular to an underground three-dimensional scanning inspection method, device, electronic equipment and storage medium. Background Art

[0002] Relevant technologies show that the environment in mines is complex and changeable, and traditional manual inspections have problems such as high safety risks and low efficiency. With the development of automation technology, some automated inspection robots have emerged, but the existing technologies mostly use a single sensor with limited perception of complex environments, resulting in low robustness and accuracy of inspections.

[0003] Therefore, finding an underground three-dimensional scanning inspection method that can improve the robustness and accuracy of inspection results has become a current research hotspot. Summary of the invention

[0004] The present invention provides an underground three-dimensional scanning inspection method, device, electronic equipment and storage medium, which can improve the three-dimensional perception capability in a complex underground mine environment and improve the robustness and accuracy of the inspection results.

[0005] The present invention provides an underground three-dimensional scanning inspection method, which is applied to an inspection system, wherein the inspection system at least includes a plurality of radar sensors arranged on the same mobile platform, and the method includes: acquiring three-dimensional data in a mine environment collected by the plurality of radar sensors; based on an extended Kalman filter algorithm, performing distributed processing on the three-dimensional data collected by each of the radar sensors to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; based on the target point cloud data, constructing a three-dimensional environmental map in a mine environment.

[0006] According to an underground three-dimensional scanning inspection method provided by the present invention, before the three-dimensional data collected by each radar sensor is distributedly processed based on the extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, the method also includes: based on the three-dimensional data collected by each radar sensor, obtaining point cloud data corresponding to each three-dimensional data; the three-dimensional data collected by each radar sensor is distributedly processed based on the extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, specifically including: based on the extended Kalman filter algorithm, distributedly maintaining an enhanced state vector corresponding to each radar sensor, wherein the enhanced state vector is determined by the posture, motion parameters and external parameters of the geometric center of the radar sensor; based on the enhanced state vector, calibrating the point cloud data to obtain target point cloud data corresponding to the three-dimensional data; based on the target point cloud data, constructing a three-dimensional environment map under a mine environment, specifically including: fusing the target point cloud data to construct a three-dimensional environment map under a mine environment.

[0007] According to a three-dimensional underground scanning and inspection method provided by the present invention, the point cloud data corresponding to each three-dimensional data is obtained based on the three-dimensional data collected by each radar sensor, which specifically includes: denoising and filtering the three-dimensional data collected by each radar sensor to obtain point cloud data corresponding to each three-dimensional data.

[0008] According to a downhole three-dimensional scanning and inspection method provided by the present invention, the enhanced state vector is maintained in the following manner: real-time determination of the posture of the geometric center in the current frame, the motion parameters in the current frame and the extrinsic parameters in the current frame corresponding to the current sensor; obtaining enhanced state vectors corresponding to other sensors, wherein the other sensors are sensors other than the current sensor; based on the posture of the geometric center in the current frame, the motion parameters in the current frame, the extrinsic parameters in the current frame, and the enhanced state vectors corresponding to the other sensors, updating the enhanced state vector corresponding to the current sensor to obtain an updated enhanced state vector, so as to maintain the enhanced state vector of the current sensor.

[0009] According to a three-dimensional underground scanning and inspection method provided by the present invention, after obtaining the point cloud data corresponding to each of the three-dimensional data, the method further includes: based on the radar sensor odometer and mapping algorithm, predicting the posture of the radar sensor to obtain the predicted posture; based on the predicted posture, performing alignment optimization processing on the point cloud data to obtain optimized point cloud data; based on the enhanced state vector, calibrating the point cloud data to obtain target point cloud data corresponding to the three-dimensional data, specifically including: based on the enhanced state vector, calibrating the optimized point cloud data to obtain target point cloud data corresponding to the three-dimensional data.

[0010] According to an underground three-dimensional scanning inspection method provided by the present invention, constructing a three-dimensional environment map in a mine environment based on the target point cloud data specifically includes: Based on the target point cloud data, point cloud distance optimization processing is performed to minimize the point cloud distance, and a three-dimensional environmental map in a mine environment is constructed.

[0011] The present invention also provides an underground three-dimensional scanning inspection device, which is applied to an inspection system, wherein the inspection system includes at least a plurality of radar sensors arranged on the same mobile platform, and the device includes: an acquisition module, used to acquire three-dimensional data in a mine environment collected by the plurality of radar sensors; a processing module, used to perform distributed processing on the three-dimensional data collected by each of the radar sensors based on an extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; a construction module, used to construct a three-dimensional environmental map in a mine environment based on the target point cloud data.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any of the above-described three-dimensional underground scanning and inspection methods.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the three-dimensional underground scanning inspection method as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned three-dimensional underground scanning inspection methods.

[0015] The present invention provides an underground three-dimensional scanning inspection method, device, electronic device and storage medium. The method is applied to an inspection system, wherein the inspection system at least includes multiple radar sensors arranged on the same mobile platform, and obtains three-dimensional data in a mine environment collected by multiple radar sensors; based on an extended Kalman filter algorithm, the three-dimensional data collected by each radar sensor is distributedly processed to obtain target point cloud data corresponding to the three-dimensional data; and then based on the target point cloud data, a three-dimensional environmental map in the mine environment is constructed. The three-dimensional environmental map is obtained by fusing multiple target point cloud data corresponding to the three-dimensional data collected by the sensors, thereby improving the accuracy and completeness of the three-dimensional environmental map, thereby achieving the ability to improve the three-dimensional perception capability in a complex underground mine environment and improving the robustness and accuracy of the inspection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the underground three-dimensional scanning inspection method provided by the present invention.

[0018] Figure 2 It is a schematic diagram of a process for constructing a three-dimensional environment map in a mine environment based on target point cloud data provided by the present invention.

[0019] Figure 3 It is a schematic diagram of the process of maintaining the enhanced state vector provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the underground three-dimensional scanning inspection device provided by the present invention.

[0021] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The underground three-dimensional scanning inspection method provided by the present invention adopts the data fusion of multiple radar sensors to perform accurate three-dimensional modeling and positioning of underground equipment and environment, and adopts a distributed framework for using multiple radar sensors to calibrate, locate and map simultaneously, thereby improving the accuracy and completeness of the three-dimensional environmental map, realizing the ability to improve the three-dimensional perception in complex underground mine environments, and improving the robustness and accuracy of inspection results.

[0024] Figure 1 It is a flow chart of the underground three-dimensional scanning inspection method provided by the present invention.

[0025] The following will be combined Figure 1 The process of the underground three-dimensional scanning inspection method provided by the present invention is described.

[0026] In an exemplary embodiment of the present invention, the underground three-dimensional scanning inspection method can be applied to the inspection system, wherein the inspection system can include at least a plurality of radar sensors arranged on the same mobile platform. Among them, the plurality of radar sensors can be distributed and deployed on the same mobile platform to reduce blind spots and improve the coverage of the data. In another embodiment, the inspection system can also include a communication module and a central processing unit. Among them, the communication module can communicate and transmit with the ground control center so that the ground control center can understand the situation in the mine in real time, and the central processing unit can be used to execute the underground three-dimensional scanning inspection method provided by the present invention.

[0027] Combination Figure 1 It can be seen that the underground three-dimensional scanning inspection method may include steps 110 to 130, and each step will be introduced below.

[0028] In step 110, three-dimensional data in a mine environment collected by a plurality of radar sensors is obtained.

[0029] In one embodiment, three-dimensional data in a mine environment collected by multiple radar sensors may be obtained, wherein the three-dimensional data may be three-dimensional data related to equipment, surrounding environment, operation scene, etc. in the mine environment. In another example, the number and installation positions of radar sensors may be adjusted according to actual needs.

[0030] In step 120, based on the extended Kalman filter algorithm, the three-dimensional data collected by each radar sensor is processed in a decentralized manner to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system.

[0031] In step 130, a three-dimensional environment map of the mine environment is constructed based on the target point cloud data.

[0032] In another embodiment, the three-dimensional data collected by each radar sensor can be processed in a decentralized manner based on the extended Kalman filter algorithm, so as to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system. Furthermore, fusion processing is performed based on the target point cloud data, so as to construct a three-dimensional environmental map in a mine environment. In this embodiment, a decentralized framework is used to use multiple radar sensors, such as LiDAR sensors, to calibrate, locate and map at the same time, so as to improve the accuracy and completeness of the three-dimensional environmental map, realize the ability to improve the three-dimensional perception in a complex mine environment, and improve the robustness and accuracy of the inspection results.

[0033] Figure 2 It is a schematic diagram of a process for constructing a three-dimensional environment map in a mine environment based on target point cloud data provided by the present invention.

[0034] The following will be combined Figure 2 The process of constructing a three-dimensional environmental map in a mine environment based on target point cloud data is explained.

[0035] In an exemplary embodiment of the present invention, Figure 2 It can be seen that constructing a three-dimensional environment map in a mine environment based on the target point cloud data may include steps 210 to 240, and each step will be introduced below.

[0036] In step 210 , based on the three-dimensional data collected by each radar sensor, point cloud data corresponding to each three-dimensional data is obtained.

[0037] In another exemplary embodiment of the present invention, based on the three-dimensional data collected by each radar sensor, point cloud data corresponding to each three-dimensional data is obtained, which can be implemented in the following manner: The three-dimensional data collected by each radar sensor is subjected to denoising and filtering to obtain point cloud data corresponding to each three-dimensional data.

[0038] In one embodiment, the three-dimensional data collected by each radar sensor can be denoised and filtered to obtain point cloud data corresponding to each three-dimensional data without irrelevant interference, thereby laying the foundation for generating an accurate three-dimensional environmental map in a mine environment.

[0039] In step 220, based on the extended Kalman filter algorithm, an enhanced state vector corresponding to each radar sensor is maintained in a decentralized manner, wherein the enhanced state vector is determined by the posture, motion parameters, and extrinsic parameters of the geometric center of the radar sensor.

[0040] In step 230, the point cloud data is calibrated based on the enhanced state vector to obtain target point cloud data corresponding to the three-dimensional data.

[0041] In step 240, the target point cloud data is fused and processed to construct a three-dimensional environment map of the mine environment.

[0042] In one embodiment, an enhanced state vector corresponding to each radar sensor may be maintained in a distributed manner based on an extended Kalman filter algorithm, wherein the enhanced state vector is determined by the attitude, motion parameters, and extrinsic parameters of the geometric center of the radar sensor. It is understood that the extended Kalman filter algorithm may be run simultaneously on all radar sensors.

[0043] Furthermore, based on the enhanced state vector, the point cloud data is calibrated to obtain target point cloud data corresponding to the three-dimensional data, and the target point cloud data is fused to construct a three-dimensional environment map in the mine environment. Since the target point cloud data is point cloud data calibrated by the enhanced state vector, that is, point cloud data that can be fused in the same coordinate system, it is possible to fuse multiple target point cloud data corresponding to the three-dimensional data collected by the sensor to obtain a three-dimensional environment map, thereby improving the accuracy and completeness of the three-dimensional environment map, and realizing the ability to improve the three-dimensional perception in the complex mine environment, and improving the robustness and accuracy of the inspection results.

[0044] Figure 3 It is a schematic diagram of the process of maintaining the enhanced state vector provided by the present invention.

[0045] The following will be combined Figure 3 The process of maintaining the enhanced state vector is described.

[0046] In an exemplary embodiment of the present invention, Figure 3 It can be seen that maintaining the enhanced state vector may include steps 310 to 330, and each step will be introduced below.

[0047] In step 310, the posture of the geometric center in the current frame, the motion parameters in the current frame, and the extrinsic parameters in the current frame corresponding to the current sensor are determined in real time.

[0048] In step 320, an enhanced state vector corresponding to other sensors is obtained, wherein the other sensors are sensors other than the current sensor.

[0049] In step 330, based on the posture of the geometric center in the current frame, the motion parameters in the current frame, the extrinsic parameters in the current frame, and the enhanced state vectors corresponding to other sensors, the enhanced state vector corresponding to the current sensor is updated to obtain an updated enhanced state vector, so as to maintain the enhanced state vector of the current sensor.

[0050] In one embodiment, an extended Kalman filter algorithm, also known as a decentralized EKF algorithm, can be used, which runs simultaneously on all radar sensors LiDAR. Each EKF instance performs the following same process: maintaining an enhanced state vector, wherein the enhanced state vector may include the attitude of the geometric center, motion parameters such as acceleration, velocity, etc., and external parameters of all LiDARs.

[0051] During the application process, the latest state (corresponding to the enhanced state vector corresponding to other sensors) received from other EKF instances in the network can be updated for prediction. Use the new frame of its local LiDAR (the posture of the geometric center in the current frame, the motion parameters in the current frame, and the external parameter parameters in the current frame) to update the state vector. The updated state vector is published to the network for use by other EKF instances. That is, based on the posture of the geometric center in the current frame, the motion parameters in the current frame, the external parameter parameters in the current frame, and the enhanced state vectors corresponding to other sensors, the enhanced state vector corresponding to the current sensor can be updated to obtain an updated enhanced state vector to maintain the enhanced state vector of the current sensor. In this embodiment, the enhanced state vector corresponding to each laser radar has the mutual influence of the enhanced state vectors of other laser radars, so as to better ensure that the target point cloud data corresponding to the three-dimensional data obtained by calibrating the point cloud data based on the enhanced state vector can be better fused.

[0052] In another embodiment, the state prediction step of the EKF can be used to predict the state at the current moment based on the state and control input at the previous moment: k+1∣k =f(x k ,u k ,w k ) where f is the system dynamic model, x k is the state at time k, u k is the control input, w k is the process noise.

[0053] In yet another embodiment, the measurement update step of the EKF is used to correct the predicted state by incorporating the latest sensor data: k+1 =x k+1∣k +K k+1 (z k+1 -Hx k+1∣k ) where Kk+1 is the Kalman gain, z k+1 is the measurement value and H is the measurement matrix.

[0054] In another embodiment of the present invention, the above-mentioned embodiment is continued as an example for explanation. After obtaining the point cloud data corresponding to each three-dimensional data, the underground three-dimensional scanning inspection method may further include the following steps: Based on the radar sensor odometer and mapping algorithm, the attitude of the radar sensor is predicted to obtain the predicted attitude; Based on the predicted posture, the point cloud data is registered and optimized to obtain the optimized point cloud data; Furthermore, based on the enhanced state vector, the point cloud data is calibrated to obtain the target point cloud data corresponding to the three-dimensional data, which can be achieved in the following ways: Based on the enhanced state vector, the optimized point cloud data is calibrated to obtain the target point cloud data corresponding to the three-dimensional data.

[0055] In one embodiment, the attitude of the radar sensor can be predicted based on the radar sensor odometer and mapping algorithm to obtain the predicted attitude; then based on the predicted attitude, the point cloud data is registered and optimized to obtain the optimized point cloud data. In the application process, the LiDAR odometer and mapping (LOAM) algorithm can be used to process the data of each LiDAR to solve the i-th LiDAR attitude. The predicted attitude is used as an initial estimate and corrected through the optimization process.

[0056] Furthermore, after obtaining the optimized point cloud data, the optimized point cloud data can be calibrated based on the enhanced state vector to obtain target point cloud data corresponding to the three-dimensional data, thereby improving the accuracy and rationality of the target point cloud data, thereby improving the accuracy and completeness of the three-dimensional environmental map and laying the foundation for improving the robustness and accuracy of the inspection results.

[0057] In another exemplary embodiment of the present invention, a three-dimensional environment map in a mine environment is constructed based on the target point cloud data, which can be implemented in the following manner: Based on the target point cloud data, the point cloud distance optimization processing is minimized to construct a three-dimensional environmental map in the mine environment.

[0058] In one embodiment, the data from all LiDAR sensors can be fused into a unified coordinate system to optimize the continuity of the map by minimizing the point cloud distance: min∑i||p i frame1 -p i frame2 || 2 .

[0059] The underground three-dimensional scanning inspection method provided by the present invention can provide an inspection system that applies the underground three-dimensional scanning inspection method, such as improving the perception accuracy and robustness of the robot in a complex environment; realizing real-time data processing, improving the response speed and decision-making ability of the robot; and enhancing the accuracy and completeness of the environmental map through multi-sensor fusion, and enabling the robot to plan the inspection path more intelligently based on the adaptive navigation system, thereby improving the inspection efficiency.

[0060] According to the foregoing description, the underground three-dimensional scanning inspection method provided by the present invention is applied to an inspection system, wherein the inspection system at least includes multiple radar sensors arranged on the same mobile platform, and obtains three-dimensional data in a mine environment collected by multiple radar sensors; based on the extended Kalman filter algorithm, the three-dimensional data collected by each radar sensor is distributedly processed to obtain target point cloud data corresponding to the three-dimensional data; and then based on the target point cloud data, a three-dimensional environmental map in the mine environment is constructed, and the three-dimensional environmental map obtained by fusing multiple target point cloud data corresponding to the three-dimensional data collected by the sensor improves the accuracy and completeness of the three-dimensional environmental map, thereby achieving the ability to improve the three-dimensional perception capability in a complex underground mine environment and improve the robustness and accuracy of the inspection results.

[0061] The downhole three-dimensional scanning and inspection device provided by the present invention is described below. The downhole three-dimensional scanning and inspection device described below and the downhole three-dimensional scanning and inspection method described above can be referenced to each other.

[0062] Figure 4 It is a structural schematic diagram of the underground three-dimensional scanning inspection device provided by the present invention.

[0063] The following will be combined Figure 4 The structure of the underground three-dimensional scanning inspection device provided by the present invention is described.

[0064] In an exemplary embodiment of the present invention, the underground three-dimensional scanning inspection device can be applied to an inspection system, wherein the inspection system can at least include a plurality of radar sensors arranged on the same mobile platform. Figure 4 It can be seen that the underground three-dimensional scanning inspection device can include the following modules: The acquisition module 410 may be configured to acquire three-dimensional data in a mine environment collected by a plurality of radar sensors; The processing module 420 may be configured to perform distributed processing on the three-dimensional data collected by each of the radar sensors based on an extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; The construction module 430 may be configured to construct a three-dimensional environment map in a mine environment based on the target point cloud data.

[0065] In an exemplary embodiment of the present invention, the processing module 420 may also be configured to: Based on the three-dimensional data collected by each radar sensor, obtaining point cloud data corresponding to each three-dimensional data; The processing module 420 may implement distributed processing of the three-dimensional data collected by each radar sensor based on an extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data in the following manner: Based on an extended Kalman filter algorithm, an enhanced state vector corresponding to each of the radar sensors is maintained in a decentralized manner, wherein the enhanced state vector is determined by a posture, motion parameters, and extrinsic parameters of a geometric center of the radar sensor; Based on the enhanced state vector, calibrate the point cloud data to obtain target point cloud data corresponding to the three-dimensional data; The construction module 430 can construct a three-dimensional environment map in a mine environment based on the target point cloud data in the following manner: The target point cloud data are fused and processed to construct a three-dimensional environmental map in a mine environment.

[0066] In an exemplary embodiment of the present invention, the processing module 420 may obtain point cloud data corresponding to each of the three-dimensional data based on the three-dimensional data collected by each of the radar sensors in the following manner: The three-dimensional data collected by each radar sensor is subjected to denoising and filtering to obtain point cloud data corresponding to each three-dimensional data.

[0067] In an exemplary embodiment of the present invention, the processing module 420 may implement the maintenance of the enhanced state vector in the following manner: Determine in real time the posture of the geometric center in the current frame, the motion parameters in the current frame, and the external parameter parameters in the current frame corresponding to the current sensor; Acquire an enhanced state vector corresponding to other sensors, wherein the other sensors are other sensors except the current sensor; Based on the posture of the geometric center in the current frame, the motion parameters in the current frame, the extrinsic parameters in the current frame, and the enhanced state vectors corresponding to other sensors, the enhanced state vector corresponding to the current sensor is updated to obtain an updated enhanced state vector, so as to maintain the enhanced state vector of the current sensor.

[0068] In an exemplary embodiment of the present invention, the processing module 420 may also be configured to: Based on the radar sensor odometer and the mapping algorithm, the posture of the radar sensor is predicted to obtain a predicted posture; Based on the predicted posture, performing registration optimization processing on the point cloud data to obtain optimized point cloud data; The processing module 420 may implement calibration processing on the point cloud data based on the enhanced state vector to obtain target point cloud data corresponding to the three-dimensional data in the following manner: Based on the enhanced state vector, the optimized point cloud data is calibrated to obtain target point cloud data corresponding to the three-dimensional data.

[0069] In an exemplary embodiment of the present invention, the construction module 430 can construct a three-dimensional environment map in a mine environment based on the target point cloud data in the following manner: Based on the target point cloud data, point cloud distance optimization processing is performed to minimize the point cloud distance, and a three-dimensional environmental map in a mine environment is constructed.

[0070] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the underground three-dimensional scanning inspection method, the method is applied to the inspection system, wherein the inspection system at least includes a plurality of radar sensors arranged on the same mobile platform, the method includes: obtaining three-dimensional data in a mine environment collected by the plurality of radar sensors; based on the extended Kalman filter algorithm, performing distributed processing on the three-dimensional data collected by each of the radar sensors to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; based on the target point cloud data, constructing a three-dimensional environment map in a mine environment.

[0071] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0072] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the underground three-dimensional scanning inspection method provided by the above-mentioned methods. The method is applied to an inspection system, wherein the inspection system at least includes multiple radar sensors arranged on the same mobile platform. The method includes: obtaining three-dimensional data in a mine environment collected by multiple radar sensors; based on an extended Kalman filter algorithm, performing distributed processing on the three-dimensional data collected by each of the radar sensors to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; based on the target point cloud data, constructing a three-dimensional environmental map in a mine environment.

[0073] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the underground three-dimensional scanning inspection method provided by the above-mentioned methods, wherein the method is applied to an inspection system, wherein the inspection system includes at least a plurality of radar sensors arranged on the same mobile platform, and the method includes: obtaining three-dimensional data in a mine environment collected by the plurality of radar sensors; based on an extended Kalman filter algorithm, performing distributed processing on the three-dimensional data collected by each of the radar sensors to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; based on the target point cloud data, constructing a three-dimensional environmental map in a mine environment.

[0074] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A three-dimensional scanning inspection method for underground mines, characterized in that: The method is applied to a patrol inspection system, wherein the patrol inspection system at least includes a plurality of radar sensors arranged on the same mobile platform, and the method includes: Acquire three-dimensional data in a mine environment collected by a plurality of radar sensors; Based on the extended Kalman filter algorithm, the three-dimensional data collected by each radar sensor is processed in a decentralized manner to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; Based on the target point cloud data, a three-dimensional environmental map of the mine environment is constructed.

2. The underground three-dimensional scanning inspection method according to claim 1, characterized in that: Before performing distributed processing on the three-dimensional data collected by each radar sensor based on the extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, the method further includes: Based on the three-dimensional data collected by each radar sensor, obtaining point cloud data corresponding to each three-dimensional data; The distributed processing of the three-dimensional data collected by each radar sensor based on the extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data specifically includes: Based on an extended Kalman filter algorithm, an enhanced state vector corresponding to each of the radar sensors is maintained in a decentralized manner, wherein the enhanced state vector is determined by a posture, motion parameters, and extrinsic parameters of a geometric center of the radar sensor; Based on the enhanced state vector, calibrate the point cloud data to obtain target point cloud data corresponding to the three-dimensional data; The constructing of a three-dimensional environment map in a mine environment based on the target point cloud data specifically includes: The target point cloud data are fused and processed to construct a three-dimensional environmental map in a mine environment.

3. The underground three-dimensional scanning inspection method according to claim 2, characterized in that: The obtaining of point cloud data corresponding to each of the three-dimensional data based on the three-dimensional data collected by each of the radar sensors specifically includes: The three-dimensional data collected by each radar sensor is subjected to denoising and filtering to obtain point cloud data corresponding to each three-dimensional data.

4. The underground three-dimensional scanning inspection method according to claim 2, characterized in that: The enhanced state vector is maintained in the following manner: Determine in real time the posture of the geometric center in the current frame, the motion parameters in the current frame, and the external parameter parameters in the current frame corresponding to the current sensor; Acquire an enhanced state vector corresponding to other sensors, wherein the other sensors are other sensors except the current sensor; Based on the posture of the geometric center in the current frame, the motion parameters in the current frame, the extrinsic parameters in the current frame, and the enhanced state vectors corresponding to other sensors, the enhanced state vector corresponding to the current sensor is updated to obtain an updated enhanced state vector, so as to maintain the enhanced state vector of the current sensor.

5. The underground three-dimensional scanning inspection method according to any one of claims 2 to 4, characterized in that: After obtaining the point cloud data corresponding to each of the three-dimensional data, the method further includes: Based on the radar sensor odometer and the mapping algorithm, the posture of the radar sensor is predicted to obtain a predicted posture; Based on the predicted posture, performing registration optimization processing on the point cloud data to obtain optimized point cloud data; The step of calibrating the point cloud data based on the enhanced state vector to obtain target point cloud data corresponding to the three-dimensional data specifically includes: Based on the enhanced state vector, the optimized point cloud data is calibrated to obtain target point cloud data corresponding to the three-dimensional data.

6. The underground three-dimensional scanning inspection method according to claim 1, characterized in that: The constructing of a three-dimensional environment map in a mine environment based on the target point cloud data specifically includes: Based on the target point cloud data, point cloud distance optimization processing is performed to minimize the point cloud distance, and a three-dimensional environmental map in a mine environment is constructed.

7. An underground three-dimensional scanning inspection device, characterized in that: The device is applied to a patrol inspection system, wherein the patrol inspection system at least includes a plurality of radar sensors arranged on the same mobile platform, and the device includes: An acquisition module, used to acquire three-dimensional data in a mine environment collected by a plurality of radar sensors; A processing module, configured to perform distributed processing on the three-dimensional data collected by each of the radar sensors based on an extended Kalman filter algorithm to obtain target point cloud data corresponding to the three-dimensional data, wherein the target point cloud data is point cloud data that can be fused in the same coordinate system; The construction module is used to construct a three-dimensional environment map in a mine environment based on the target point cloud data.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the underground three-dimensional scanning inspection method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the underground three-dimensional scanning inspection method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the underground three-dimensional scanning inspection method as described in any one of claims 1 to 6 is implemented.

Images