CN113487583A - Underground roadway surface deformation detection system based on 3D point cloud slice - Google Patents
Underground roadway surface deformation detection system based on 3D point cloud slice Download PDFInfo
- Publication number
- CN113487583A CN113487583A CN202110812819.8A CN202110812819A CN113487583A CN 113487583 A CN113487583 A CN 113487583A CN 202110812819 A CN202110812819 A CN 202110812819A CN 113487583 A CN113487583 A CN 113487583A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- explosion
- proof
- deformation
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Abstract
The invention relates to the field of detection of roadway surfaces, and discloses an underground roadway surface deformation detection system based on 3D point cloud slices. The explosion-proof binocular depth camera collects images of the surface of the underground roadway in real time, and the images are wirelessly transmitted to a computer through a WiFi module to be analyzed and processed. The software system generates a dense 3D point cloud picture based on a vision simultaneous positioning and picture building technology; by utilizing a 3D point cloud slicing technology, the space coordinates of each point of each layer of point cloud on the surface of the roadway are obtained, and the deformation position, the deformation size and the deformation geometric shape can be obtained. According to the invention, the surface of the underground roadway does not need to be manually detected, and the 3D point cloud dense mapping, the point cloud slicing and the deformation detection of the surface of the underground roadway can be completed only by carrying out autonomous movement of the whole roadway for one to two times by the explosion-proof mobile robot with the explosion-proof binocular depth camera. The system has high automation degree, high detection speed and high measurement precision.
Description
Technical Field
The invention relates to the field of detection of roadway surfaces, in particular to an underground roadway surface deformation detection system based on 3D point cloud slices.
Background
The underground roadway plays a role in lifting in coal mine safety production, supports the whole coal bed and provides necessary conditions for mining lifting, transportation, ventilation, drainage and power supply, and the deformation of the surface of the underground roadway refers to the change of the shape and the size of a roadway rock stratum under the action of external force factors. The deformation and damage of the surface of the underground tunnel can block underground traffic, increase the ventilation resistance of a mine, damage production equipment, cause casualties and seriously threaten the safety production of a coal mine, so the tunnel surface monitoring is one of the important monitoring targets of the coal mine.
At present, instruments for measuring the surface deformation of the underground roadway at home and abroad can be divided into a mechanical measuring instrument and an electrical measuring instrument, and the instruments mainly adopt an acoustic ranging method, a laser ranging method, an optical surveying instrument, a close-range photogrammetry method and the like. These methods for monitoring roadway deformation often need to manually carry equipment to move back and forth in an underground roadway for detection, which not only consumes long time and has low automation degree, but also has unstable measurement precision. With the development of underground unmanned intelligence, a new method is urgently needed to overcome the defects of the traditional roadway surface deformation measurement method.
Disclosure of Invention
In order to solve the above mentioned shortcomings in the background art, the present invention provides a system for detecting surface deformation of an underground roadway based on a 3D point cloud slice.
The purpose of the invention can be realized by the following technical scheme:
the utility model provides a underworkings surface deformation detecting system based on 3D point cloud section, includes explosion-proof mobile robot, its characterized in that, install explosion-proof binocular depth camera on the explosion-proof mobile robot, explosion-proof binocular depth camera is connected with the high performance computer through the wiFi module, includes the software system among the high performance computer.
Furthermore, the explosion-proof binocular depth camera is installed on a vertical rod support at the front end of the body of the explosion-proof mobile robot, and the angle is adjustable.
Furthermore, the anti-explosion mobile robot is composed of an anti-explosion vehicle body, a power supply, a wheel driving control system and a communication system, wherein the power supply is connected with the wheel driving control system and the communication system to realize power supply, and the anti-explosion mobile robot can walk autonomously or through remote control when in use.
Further, explosion-proof two mesh degree of depth cameras comprise explosion-proof toughened glass, RGB camera, infrared dot matrix transmitter and two mesh infrared cameras, and two mesh infrared cameras comprise left infrared camera and right infrared camera, and RGB camera and infrared dot matrix transmitter set up between left infrared camera and right infrared camera.
Further, explosion-proof mobile robot places in the underworkings, and the RGB image in the underworkings is gathered to the RGB camera, and binocular infrared camera gathers the degree of depth information that corresponds with RGB in corresponding the scene.
Furthermore, the explosion-proof binocular depth camera performs one to two times of image acquisition on the whole underground tunnel, video image information is transmitted to a high-performance computer in real time through a WiFi module, and a software system in the high-performance computer automatically processes the acquired images based on a VSLAM algorithm to generate dense 3D point cloud images.
Further, the software system is based on a VSLAM algorithm, and the algorithm process comprises sensor information reading, front-end visual odometry, rear-end optimization, loop detection, image building, point cloud slicing and comparison.
Further, the software system carries out through filtering on the generated dense 3D point cloud picture according to three dimensionality directions of x, y and z to filter noise points, carries out voxel filtering on the result to reduce the number of point clouds, extracts a clear 3D point cloud picture of the underground tunnel, automatically carries out point cloud slicing according to one dimensionality of x, y and z, compares the point cloud slicing with a standard point cloud slice of the underground tunnel, and outputs position coordinates, deformation size and deformation geometric shape of tunnel deformation after the deformation is found, the deformation information can be stored, and historical information can be consulted.
The invention has the beneficial effects that:
when the software system is used, a dense 3D point cloud picture is generated based on a visual simultaneous positioning and mapping technology, the space coordinates of each point of each layer of point cloud on the surface of a roadway are obtained by utilizing a 3D point cloud slicing technology, and the deformation position, the deformation size, the deformation geometric shape and the like can be accurately obtained.
According to the invention, the surface of the underground tunnel is not required to be manually detected, and the 3D point cloud dense mapping, the point cloud slicing and the deformation detection of the surface of the underground tunnel can be completed only by carrying out autonomous movement of the whole tunnel for one to two times by the explosion-proof mobile robot with the explosion-proof binocular depth camera. Compared with manual detection, the system has the advantages of high automation degree, high detection speed and high measurement precision.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without creative efforts;
FIG. 1 is a schematic diagram of a downhole roadway surface deformation detection system of the present invention;
FIG. 2 is a schematic view of the overall structure of the explosion-proof mobile robot of the present invention;
FIG. 3 is a schematic structural view of an explosion-proof binocular depth camera of the present invention;
FIG. 4 is a schematic diagram of a software system workflow in a high performance computer;
in the figure: explosion-proof toughened glass 1, left infrared camera 2, RGB camera 3, infrared dot matrix transmitter 4, right infrared camera 5.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The underground roadway surface deformation detection system based on the 3D point cloud slice comprises an explosion-proof mobile robot, wherein an explosion-proof binocular depth camera is mounted on the explosion-proof mobile robot, the explosion-proof binocular depth camera is mounted on a vertical rod support at the front end of an automobile body of the explosion-proof mobile robot, the angle is adjustable, the explosion-proof binocular depth camera is connected with a high-performance computer through a WiFi module, and the high-performance computer comprises a software system.
The anti-explosion mobile robot consists of an anti-explosion vehicle body, a power supply, a wheel driving control system and a communication system, wherein the power supply is connected with the wheel driving control system and the communication system to realize power supply, and the anti-explosion mobile robot can independently walk or walk through remote control when in use.
Explosion-proof two mesh degree of depth cameras comprise explosion-proof toughened glass 1, RGB camera 3, infrared dot matrix transmitter 4 and two mesh infrared cameras, and two mesh infrared cameras comprise left infrared camera 2 and right infrared camera 5, and RGB camera 3 and infrared dot matrix transmitter 4 set up between left infrared camera 2 and right infrared camera 5.
After the system is started, the anti-explosion mobile robot is placed in an underground roadway, the RGB camera 3 collects RGB images in the underground roadway, and the binocular infrared camera collects depth information corresponding to RGB in a corresponding scene. The explosion-proof binocular depth camera performs one-to-two image acquisition on the whole underground tunnel, transmits video image information to a high-performance computer in real time through a WiFi module, and a software system in the high-performance computer automatically processes the acquired images based on a VSLAM algorithm to generate dense 3D point cloud images.
As shown in fig. 4, the software system of the system is based on the VSLAM algorithm, and the algorithm process includes sensor information reading, front-end visual odometer, back-end optimization, loop detection, image building, point cloud slicing and comparison.
The sensor information reading is to acquire RGB images and depth images on the surface of the underground roadway by an explosion-proof binocular depth camera;
the front-end visual odometer estimates the motion state of the camera according to the information of the front frame and the back frame of the input image data, the motion track and the local map of the camera in a short time can be obtained through the front-end visual odometer, and the back-end optimization further optimizes the established map by adopting a filter method and nonlinear optimization to obtain a more accurate 3D image;
SLAM systems are prone to track drift during camera motion, which increases over time, and loop detection is used to detect when the mobile robot has returned to the mapped area for correcting errors accumulated since the last visit to the area.
The software system builds a map according to the result, carries out through filtering on the generated dense 3D point cloud map according to three dimensionality directions of x, y and z to filter noise points, carries out voxel filtering on the result to reduce the number of point clouds, extracts a clear 3D point cloud map of the underground tunnel, automatically carries out point cloud slicing according to one dimensionality of x, y and z, compares the point cloud slice with a standard point cloud slice of the underground tunnel, and outputs results such as position coordinates of tunnel deformation, deformation size, deformation geometric shape and the like after the deformation is found, the deformation information can be stored, and historical information can be consulted.
According to the invention, the surface of the underground tunnel is not required to be manually detected, and the 3D point cloud dense mapping, the point cloud slicing and the deformation detection of the surface of the underground tunnel can be completed only by carrying out autonomous movement of the whole tunnel for one to two times by the explosion-proof mobile robot with the explosion-proof binocular depth camera. Compared with manual detection, the system has the advantages of high automation degree, high detection speed and high measurement precision.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.
Claims (8)
1. The utility model provides a underworkings surface deformation detecting system based on 3D point cloud section, includes explosion-proof mobile robot, its characterized in that, install explosion-proof binocular depth camera on the explosion-proof mobile robot, explosion-proof binocular depth camera is connected with the high performance computer through the wiFi module, includes the software system among the high performance computer.
2. The underground roadway surface deformation detection system based on the 3D point cloud slice of claim 1, wherein the explosion-proof binocular depth camera is mounted on a vertical rod support at the front end of an explosion-proof mobile robot body, and the angle is adjustable.
3. The system for detecting the surface deformation of the underground roadway based on the 3D point cloud slice according to claim 1, wherein the explosion-proof mobile robot is composed of an explosion-proof vehicle body, a power supply, a wheel driving control system and a communication system, the power supply is connected with the wheel driving control system and the communication system to realize power supply, and the explosion-proof mobile robot can walk autonomously or remotely when in use.
4. The underground roadway surface deformation detection system based on 3D point cloud slice of claim 1, characterized in that, explosion-proof binocular depth camera comprises explosion-proof toughened glass (1), RGB camera (3), infrared dot matrix transmitter (4) and binocular infrared camera, and binocular infrared camera comprises left infrared camera (2) and right infrared camera (5), and RGB camera (3) and infrared dot matrix transmitter (4) set up between left infrared camera (2) and right infrared camera (5).
5. The system for detecting the surface deformation of the underground roadway based on the 3D point cloud slice according to claim 4, wherein the anti-explosion mobile robot is placed in the underground roadway, the RGB camera (3) collects RGB images in the underground roadway, and the binocular infrared camera collects depth information corresponding to RGB in a corresponding scene.
6. The system for detecting the surface deformation of the underground tunnel based on the 3D point cloud slice according to claim 5, wherein the explosion-proof binocular depth camera performs one to two times of image acquisition on the whole underground tunnel, transmits video image information to a high-performance computer through a WiFi module in real time, and a software system in the high-performance computer automatically processes the acquired images based on a VSLAM algorithm to generate a dense 3D point cloud image.
7. The system of claim 1, wherein the software system is based on a VSLAM algorithm, and the algorithm process comprises sensor information reading, front-end visual odometry, back-end optimization, loop detection, mapping, point cloud slicing and comparison.
8. The system according to claim 7, wherein the software system performs straight-through filtering on the generated dense 3D point cloud image in the directions of three dimensions x, y and z to filter noise points, performs voxel filtering on the result to reduce the number of point clouds, extracts a clear 3D point cloud image of the underground tunnel, automatically performs point cloud slicing in one of the dimensions x, y and z, compares the point cloud image with a standard point cloud slice of the underground tunnel, and outputs a position coordinate, a deformation size and a deformation geometry of tunnel deformation after the deformation is found, wherein the deformation information can be stored, and the history information can be consulted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110812819.8A CN113487583A (en) | 2021-07-19 | 2021-07-19 | Underground roadway surface deformation detection system based on 3D point cloud slice |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110812819.8A CN113487583A (en) | 2021-07-19 | 2021-07-19 | Underground roadway surface deformation detection system based on 3D point cloud slice |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113487583A true CN113487583A (en) | 2021-10-08 |
Family
ID=77941204
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110812819.8A Pending CN113487583A (en) | 2021-07-19 | 2021-07-19 | Underground roadway surface deformation detection system based on 3D point cloud slice |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113487583A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115200540A (en) * | 2022-07-08 | 2022-10-18 | 安徽省皖北煤电集团有限责任公司 | Mine roadway deformation monitoring and early warning method and system |
CN116295074A (en) * | 2023-02-13 | 2023-06-23 | 中国矿业大学 | Coal mine roadway surrounding rock deformation damage monitoring device and method based on depth image |
CN117646828A (en) * | 2024-01-29 | 2024-03-05 | 中国市政工程西南设计研究总院有限公司 | Device and method for detecting relative displacement and water leakage of pipe jacking interface |
-
2021
- 2021-07-19 CN CN202110812819.8A patent/CN113487583A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115200540A (en) * | 2022-07-08 | 2022-10-18 | 安徽省皖北煤电集团有限责任公司 | Mine roadway deformation monitoring and early warning method and system |
CN116295074A (en) * | 2023-02-13 | 2023-06-23 | 中国矿业大学 | Coal mine roadway surrounding rock deformation damage monitoring device and method based on depth image |
CN117646828A (en) * | 2024-01-29 | 2024-03-05 | 中国市政工程西南设计研究总院有限公司 | Device and method for detecting relative displacement and water leakage of pipe jacking interface |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110262546B (en) | Tunnel intelligent unmanned aerial vehicle inspection method | |
CN113487583A (en) | Underground roadway surface deformation detection system based on 3D point cloud slice | |
CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
JP7073315B2 (en) | Vehicles, vehicle positioning systems, and vehicle positioning methods | |
CN109911188B (en) | Bridge detection unmanned aerial vehicle system in non-satellite navigation and positioning environment | |
CN107463173B (en) | Storage AGV navigation method and device, computer equipment and storage medium | |
CN103926933A (en) | Indoor simultaneous locating and environment modeling method for unmanned aerial vehicle | |
CN110108255B (en) | Universal mobile data acquisition and processing tunnel detection system for multiple scanners | |
CN106289285A (en) | Map and construction method are scouted by a kind of robot associating scene | |
CN114199240B (en) | Two-dimensional code, laser radar and IMU fusion positioning system and method without GPS signal | |
CN210773935U (en) | Mining three-dimensional laser digital measuring instrument | |
CN112476433B (en) | Mobile robot positioning method based on identification array boundary | |
CN113485325A (en) | SLAM mapping and autonomous navigation method for underground coal mine water pump house inspection robot | |
CN110766785A (en) | Real-time positioning and three-dimensional reconstruction device and method for underground pipeline | |
CN113075686B (en) | Cable trench intelligent inspection robot graph building method based on multi-sensor fusion | |
CN104369742A (en) | Image-processing-based fast intelligent detection vehicle for tunnel surface cracks | |
CN113465728A (en) | Terrain perception method, terrain perception system, storage medium and computer equipment | |
Krotkov et al. | Mapping and positioning for a prototype lunar rover | |
CN105373130A (en) | Special device accident on-site information detection system based on stereo modeling | |
CN112330745A (en) | Tunnel portal side and elevation slope stability monitoring and early warning system and method based on binocular vision | |
CN116560357A (en) | Tunnel inspection robot system based on SLAM and inspection control method | |
CN112033400B (en) | Intelligent positioning method and system for coal mine mobile robot based on strapdown inertial navigation and vision combination | |
CN107647828A (en) | The sweeping robot of fish-eye camera is installed | |
CN116352722A (en) | Multi-sensor fused mine inspection rescue robot and control method thereof | |
CN204196909U (en) | A kind of quick, intelligent inspection vehicle in tunnel surface crack based on image procossing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |