Underground confined space adjoint type target tracking and positioning test method

Abstract

The invention discloses an underground confined space adjoint type target tracking and positioning test method, which adopts a ground unmanned vehicle platform to carry a 3D laser radar, an RGB-D visual camera, an IMU inertial navigation positioning module and other multi-source sensors to form a tracking and positioning test system. The method comprises the following steps: acquiring a marker attached to an obstacle or a wall with known arrangement position information in an underground confined space, fusing data information acquired by various sensors, and resolving to obtain position information of a tracking and positioning test system; markers with certain recognition features are attached to the tail and the side face of the tested unmanned system, and the tracking and positioning test system recognizes marker information attached to the tested unmanned system through a carried multi-source sensor and compares and matches the marker information with a marker recognition model established in a model library, so that accompanying tracking of the mobile tested intelligent unmanned system is achieved. The system has good maneuvering deployment capability, and can better meet the requirements of demonstration verification and capability assessment of the intelligent unmanned equipment in an underground limited environment.

Description

Technical Field

[0001] The invention belongs to the technical field of unmanned system testing, and in particular relates to an underground confined space accompanying target tracking and positioning testing method. Background Art

[0002] As the status of underground space in urban warfare increases, it is called the new battlefield of human warfare after land, sea, air, space, network and electricity. The closedness and diversity of urban underground structures make it a strategic combat field, which determines that soldiers need to fight in complex environments such as underground passages and tunnel systems. Intelligent unmanned systems have many advantages in providing real-time intelligence and executing precision strikes, making them an indispensable weapon for underground space warfare. Its advanced perception, intelligent navigation and remote control capabilities will provide real-time support for combat and improve the combat effectiveness of soldiers in urban underground environments. The test of underground confined space intelligent unmanned system is an important bridge from the development stage to actual combat application. It mainly assesses the autonomy, perception, action, decision-making and control capabilities in complex mission environments. Among them, accurate position information and posture information are important bases for its ability evaluation. How to meet the accompanying precise positioning of underground confined space intelligent unmanned systems in motion has become one of the problems that need to be solved urgently. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the present invention provides a method for tracking and positioning a target in an underground confined space. The method comprises a tracking and positioning test system composed of a multi-source sensor such as a 3D laser radar, an RGB-D visual camera, and an IMU inertial navigation positioning module mounted on a ground unmanned vehicle platform. By acquiring obstacles with known position information or markers attached to the wall in the underground confined space, the multi-source sensor information data fusion processing is used to fuse the data information collected by various sensors, and the position information of the tracking and positioning test system is obtained after solving the problem. Markers with certain identification features are attached to the tail and sides of the unmanned system under test. The tracking and positioning test system recognizes the marker information attached to the unmanned system under test through the multi-source sensors carried, and compares and matches the marker identification model established in the model library to realize the accompanying tracking of the mobile intelligent unmanned system under test. The present invention has good mobile deployment capabilities and can better meet the needs of demonstration, verification and capability assessment of intelligent unmanned equipment in underground confined environments.

[0004] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0005] Step 1: Build an underground confined space accompanying target tracking and positioning test system, including a ground unmanned vehicle platform, a 3D laser radar, an RGB-D visual camera, and an IMU inertial navigation positioning module;

[0006] The 3D laser radar, RGB-D visual camera and IMU inertial navigation positioning module are mounted on the ground unmanned vehicle platform;

[0007] The ground unmanned vehicle platform wheeled unmanned vehicle is used as a mobile platform to achieve accompanying tracking of the moving target;

[0008] The 3D laser radar and RGB-D visual camera are used to obtain information about known landmarks in the surrounding area of ​​the underground confined space environment, and obtain their own position information after fusing and processing multi-source sensor data;

[0009] The IMU inertial navigation positioning module is used for the positioning of the measurement system itself in an underground space without navigation signals, and is used for correction after the fusion processing of information collected by multi-source sensors;

[0010] Step 2: Arrangement of markers in underground confined spaces;

[0011] Before the test begins, obstacles are placed in the underground confined space, and markers with depth image information are attached to the walls of the underground confined space at certain intervals. The tracking and positioning measurement system enters the underground confined space in advance to collect the position information of obstacles and markers.

[0012] Step 3: Acquire the position of the tracking and positioning measurement system;

[0013] At the beginning of the test, the unmanned system under test enters the underground confined space environment, and the tracking and positioning measurement system follows the unmanned system under test into the underground confined space. The model library established based on the information of obstacles or landmarks in the confined space obtained in advance is matched with the information collected at the test site. The multi-source sensor navigation positioning is selectively corrected through multi-source sensor data fusion processing to achieve accurate positioning of the tracking and positioning measurement system.

[0014] Step 4: Obtain the location of the unmanned system under test;

[0015] A marker with identification features is attached to the tail or side of the unmanned system under test. The left side of the marker is a circle composed of red hexagonal concave-convex microstructures, and the right side is a circle composed of green quadrilateral concave-convex microstructures. The tracking and positioning measurement system identifies the marker of the unmanned system under test through 3D laser radar and RGB-D visual camera, and measures the distance and angle information between the marker of the unmanned system under test and itself. After dynamic coordinate system conversion and distance correction, the position information of the center of the unmanned system under test in the same coordinate system is obtained.

[0016] Step 5: companion tracking control;

[0017] By comparing the radar wave signals transmitted and received by the onboard 3D laser radar, the distance, direction, attitude and speed change information between the unmanned system under test and itself are obtained. The turning direction of the unmanned system under test is determined and stable tracking is achieved based on the distortion of the image of the marker when the unmanned system under test is driving straight or turning. The speed and turning direction of the tracking and positioning measurement system are adjusted in real time according to the changes in the speed and turning direction of the unmanned system under test.

[0018] Step 6: Upload positioning information;

[0019] During the test, the tracking and positioning measurement system transmits the acquired positioning and image information to the command and control center via wired / wireless means for situation display.

[0020] Preferably, the measurement radius of the 3D laser radar is 0.15m to 12m, and the sampling frequency is 8000Hz.

[0021] Preferably, there are two 3D laser radars, one of which collects obstacles with known positions and markers with depth information in the underground confined space, and the other obtains the position information of the unmanned system under test;

[0022] Preferably, the RGB-D visual camera has a resolution of 1080p, an optical zoom of 30 times, and has infrared and night vision capabilities.

[0023] A computer program enables a computer to execute the target tracking and positioning test method.

[0024] An electronic device comprises: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the above-mentioned target tracking and positioning test method.

[0025] A computer-readable storage medium stores a computer program, which implements the target tracking and positioning test method when executed by a processor.

[0026] A chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned target tracking and positioning test method.

[0027] A computer program product, the computer program product includes a computer storage medium, the computer storage medium stores a computer program, the computer program includes instructions that can be executed by at least one processor, and when the instructions are executed by the at least one processor, the above-mentioned target tracking and positioning test method is implemented.

[0028] The beneficial effects of the present invention are as follows:

[0029] The present invention can realize the accompanying measurement of mobile targets in underground confined spaces and the real-time acquisition of position information. It can be flexibly deployed according to the test tasks, has good mobile deployment capabilities, and can better meet the demonstration, verification and capability assessment needs of intelligent unmanned equipment in underground confined environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a diagram of the target tracking and positioning test method of the present invention.

[0031] Figure 2 It is a layout diagram of markers with location information in an underground confined test space according to an embodiment of the present invention.

[0032] Figure 3 It is a design drawing of the unmanned system identification object of the embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0034] In order to realize the accompanying tracking and positioning of the intelligent unmanned system in the underground confined space, a tracking and positioning test system is composed of a ground unmanned vehicle platform equipped with multi-source sensors such as 3D laser radar, RGB-D visual camera and IMU inertial navigation positioning module. By obtaining the obstacles with known position information or markers attached to the wall (with image / depth information) in the underground confined space, the multi-source sensor information data fusion processing is used to fuse the data information collected by various sensors, and the position information of the tracking and positioning test system is obtained after solution; markers with certain identification features are attached to the tail and side of the unmanned system under test, and the tracking and positioning test system recognizes the marker information attached to the unmanned system under test through the multi-source sensors (laser radar, visual camera, etc.) carried by the tracking and positioning test system, and compares and matches the marker recognition model established in the model library to realize the mobile intelligent unmanned vehicle under test. The system's accompanying tracking extracts features from the 3D point cloud generated by the onboard laser radar after reflection from the target surface, determines the position of the marker in the sensor coordinate system, obtains the real-time pose information of the target center through position correction, and uses the moving target coordinate system conversion to convert the tracking and positioning test system and the position of the unmanned system under test based on the marker to the same coordinate system for solution; combines the image detection in adjacent time intervals collected by the onboard visual camera to predict the speed and direction changes of the intelligent unmanned system under test, and automatically controls the speed and direction of the tracking and positioning test system while ensuring a safe distance, thereby realizing accompanying tracking of moving targets in underground confined spaces and real-time acquisition of position information, and transmitting the measured position information and image data to the command and control center, providing an evaluation reference for the performance assessment and performance verification of intelligent unmanned systems in underground confined spaces.

[0035] Underground confined spaces are characterized by darkness, weak light, obstructed line of sight, no navigation signals, and obstructed communications. The tracking and positioning test system needs to collect the characteristics and position information of surrounding markers in the complex underground confined space to obtain its own position; on the other hand, it needs to collect the characteristics of the markers attached to the unmanned system under test to obtain their information. Therefore, the use of a multi-wheeled unmanned vehicle platform can greatly meet the traffic capacity of complex underground environments. Various sensors are controlled by a pan-tilt platform to achieve 360° all-round observation, ensuring that as much surrounding information as possible is obtained.

[0036] It is equipped with two 3D laser radars with a measurement radius of 0.15m to 12m and a sampling frequency of 8000Hz. One of them collects known obstacles and markers with depth information in underground confined spaces, and the other obtains the location information of the unmanned system under test; it is equipped with two 1080p, 30x optical zoom high-definition cameras with infrared and night vision functions, which can observe and obtain the characteristic information of markers in dark and weak light environments underground. The functions of the two high-definition cameras are the same as those of radar observation targets. It is equipped with an IMU inertial navigation positioning module, which is mainly used for tracking and positioning the test system itself in an environment without navigation signals in underground spaces, and is corrected after fusion processing of information collected by multi-source sensors.

[0037] The control module is mainly used for the tracking and positioning test system to accurately control its own speed and direction according to the speed, direction and other information of the unmanned system under test. Using the visual feature extraction model, the visual information of the markers obtained by the visual camera before and after the tracking and positioning test system is compared to predict the speed and direction changes of the unmanned system under test, and the predicted information is transmitted to its own control mechanism to track the target to the maximum extent while ensuring a sufficient safety distance.

[0038] This system uses both wired and wireless methods to transmit the image and location information of the unmanned system under test to the command and control center. The wired method mainly uses a flexible optical fiber to be dragged at the tail of the tracking and positioning test system, and the collected image and location information is transmitted to the data switch using a wired optical fiber network, and then transmitted to the command and control center through the backbone network. This method can also be used to control the tracking and positioning test system through human intervention in an emergency; the wireless transmission method mainly uses a small number of relay base stations to be temporarily deployed in the underground confined space, and the collected information is transmitted to the communication base station, and then transmitted to the command and control center through the backbone network for situation display.

[0039] Example:

[0040] The present invention is used for accompanying tracking and positioning of an intelligent unmanned system in a confined space. The following takes an example of accompanying tracking and positioning of an intelligent unmanned system (length×width: X (cm)×Y (cm)) in an underground confined space as an example to specifically introduce the implementation method.

[0041] Attached Figure 1 As shown in the figure, the tracking and positioning test system mainly includes a wheeled unmanned vehicle platform, a 3D laser radar module, an RGB-D visual camera, an IMU inertial navigation positioning module, etc. The wheeled unmanned vehicle is mainly used as a mobile platform to realize the accompanying tracking of the mobile target under test; the 3D laser radar and the RGB-D visual camera mainly obtain the information of the known markers in the surrounding position of the underground confined space environment, and obtain their own position information after fusing and processing the multi-source sensor data; the multi-source sensor is used to identify the marker information attached to the tail of the unmanned system under test to obtain its distance, speed and other information from the tracking and positioning test system, and the test system and the test system are converted to the same world coordinate system through dynamic coordinate system conversion and relative position solution to obtain the specific position information of the unmanned system under test.

[0042] The tracking and positioning process is as follows:

[0043] Step 1: Placement of markers in underground confined spaces

[0044] Attached Figure 2 As shown, before the test begins, a considerable number of obstacles (with known positions) are arranged in the underground confined space, and markers (with known positions) with depth image information are attached at certain intervals on the walls of the underground confined space, and an accompanying tracking and positioning measurement system enters the underground confined space in advance to collect the position information of obstacles and markers.

[0045] Step 2: Acquire the location of the companion test system

[0046] At the beginning of the test, the unmanned system under test enters the underground confined space environment, and the accompanying positioning and tracking test system follows the unmanned system under test into the underground confined space. The model library established based on the information of obstacles or landmarks in the confined space obtained in advance is matched with the information collected at the test site. Through multi-source sensor data fusion processing, the multi-source sensor navigation and positioning are selectively corrected to achieve precise positioning of the accompanying test system.

[0047] Step 3: Obtaining the location of the unmanned system under test

[0048] Attached Figure 3 As shown in the figure, a marker with certain identification features is attached to the tail or side of the unmanned system under test. The left side of the marker is a circle composed of red hexagonal concave-convex microstructures, and the right side is a circle composed of green quadrilateral concave-convex microstructures. The accompanying tracking and positioning measurement system identifies the marker through sensors such as 3D laser radar and RGB-D visual camera, and measures the distance and angle information between the marker of the unmanned system under test and itself. After dynamic coordinate system conversion and distance correction (related to the length and width of the unmanned system under test), the position information of the center of the unmanned system under test in the same coordinate system is obtained.

[0049] Step 4: Accompanying tracking control

[0050] By comparing the radar wave signals transmitted and received by the onboard 3D laser radar, the distance, direction, attitude and speed change between itself and the unmanned system under test can be obtained. The turning direction of the unmanned system can be judged and stable tracking can be achieved based on the distortion of the (concave / convex / color) image of the marker when the unmanned system is driving in a straight line or turning. The speed and turning direction of the tracking and positioning test system can be adjusted in real time according to the changes in the speed and turning direction of the unmanned system under test. While ensuring a safe distance, accompanying tracking is performed as close as possible, which can effectively reduce the time and probability of losing the target during turning.

[0051] Step 5: Upload location information

[0052] During the test, the tracking and positioning test system transmits the acquired positioning and image information to the command and control center via wired / wireless means for situation display.

Claims

1. A method for tracking and positioning a target in an underground confined space, characterized in that: The steps include: Step 1: Build an underground confined space accompanying target tracking and positioning test system, including a ground unmanned vehicle platform, a 3D laser radar, an RGB-D visual camera, and an IMU inertial navigation positioning module; The 3D laser radar, RGB-D visual camera and IMU inertial navigation positioning module are mounted on the ground unmanned vehicle platform; The ground unmanned vehicle platform wheeled unmanned vehicle is used as a mobile platform to achieve accompanying tracking of the moving target; The 3D laser radar and RGB-D visual camera are used to obtain information about known landmarks in the surrounding area of ​​the underground confined space environment, and obtain their own position information after fusing and processing multi-source sensor data; The IMU inertial navigation positioning module is used for the positioning of the measurement system itself in an underground space without navigation signals, and is used for correction after the fusion processing of information collected by multi-source sensors; Step 2: Arrangement of markers in underground confined spaces; Before the test begins, obstacles are placed in the underground confined space, and markers with depth image information are attached to the walls of the underground confined space at certain intervals. The tracking and positioning measurement system enters the underground confined space in advance to collect the position information of obstacles and markers. Step 3: Acquire the position of the tracking and positioning measurement system; At the beginning of the test, the unmanned system under test enters the underground confined space environment, and the tracking and positioning measurement system follows the unmanned system under test into the underground confined space. The model library established based on the information of obstacles or landmarks in the confined space obtained in advance is matched with the information collected at the test site. The multi-source sensor navigation positioning is selectively corrected through multi-source sensor data fusion processing to achieve accurate positioning of the tracking and positioning measurement system. Step 4: Obtain the location of the unmanned system under test; A marker with identification features is attached to the tail or side of the unmanned system under test. The left side of the marker is a circle composed of red hexagonal concave-convex microstructures, and the right side is a circle composed of green quadrilateral concave-convex microstructures. The tracking and positioning measurement system identifies the marker of the unmanned system under test through 3D laser radar and RGB-D visual camera, and measures the distance and angle information between the marker of the unmanned system under test and itself. After dynamic coordinate system conversion and distance correction, the position information of the center of the unmanned system under test in the same coordinate system is obtained. Step 5: companion tracking control; By comparing the radar wave signals transmitted and received by the onboard 3D laser radar, the distance, direction, attitude and speed change information between the unmanned system under test and itself are obtained. The turning direction of the unmanned system under test is determined and stable tracking is achieved based on the distortion of the image of the marker when the unmanned system under test is driving straight or turning. The speed and turning direction of the tracking and positioning measurement system are adjusted in real time according to the changes in the speed and turning direction of the unmanned system under test. Step 6: Upload positioning information; During the test, the tracking and positioning measurement system transmits the acquired positioning and image information to the command and control center via wired / wireless means for situation display.

2. The underground confined space accompanying target tracking and positioning test method according to claim 1 is characterized in that: The measurement radius of the 3D laser radar is 0.15m to 12m, and the sampling frequency is 8000Hz.

3. The underground confined space accompanying target tracking and positioning test method according to claim 1 is characterized in that: There are two 3D laser radars, one of which collects obstacles with known positions and markers with depth information in the underground confined space, and the other obtains the position information of the unmanned system under test.

4. The underground confined space accompanying target tracking and positioning test method according to claim 1 is characterized in that: The RGB-D vision camera has a resolution of 1080p, an optical zoom of 30x, and infrared and night vision capabilities.

5. A computer program, characterized in that The computer program enables a computer to execute the method according to any one of claims 1 to 4.

6. An electronic device, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method as claimed in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

8. A chip, characterized in that: include: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 4.

9. A computer program product, characterized in that The computer program product comprises a computer storage medium storing a computer program, wherein the computer program comprises instructions executable by at least one processor, and when the instructions are executed by the at least one processor, the method according to any one of claims 1 to 4 is implemented.

Images