CN118115688A - Mine cavity three-dimensional map construction method and system for unmanned mine car - Google Patents
Mine cavity three-dimensional map construction method and system for unmanned mine car Download PDFInfo
- Publication number
- CN118115688A CN118115688A CN202410465777.9A CN202410465777A CN118115688A CN 118115688 A CN118115688 A CN 118115688A CN 202410465777 A CN202410465777 A CN 202410465777A CN 118115688 A CN118115688 A CN 118115688A
- Authority
- CN
- China
- Prior art keywords
- hole
- point cloud
- dimensional map
- visual image
- mine
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 21
- 230000000007 visual effect Effects 0.000 claims description 111
- 230000000875 corresponding effect Effects 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 27
- 239000000523 sample Substances 0.000 claims description 24
- 238000000547 structure data Methods 0.000 claims description 21
- 238000005259 measurement Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a mine cavity three-dimensional map construction method and system for an unmanned mine car, and relates to the technical field of unmanned mine cars.
Description
Technical Field
The invention relates to the technical field of unmanned mine cars, in particular to a mine cavity three-dimensional map construction method and system for an unmanned mine car.
Background
Three-dimensional maps of mine openings of unmanned mining vehicles play a key role in mining applications. Firstly, it provides an accurate and real-time representation of the mine tunnel internal structure, providing a basis for mine car navigation and path planning. Through the three-dimensional map, the unmanned mine car can avoid the obstacle and plan the optimal path, thereby improving the transportation efficiency and the safety.
Most of the existing mine hole three-dimensional map generation modes are composed of point cloud data, the mine hole three-dimensional map composed of the point cloud data is high in resolution, but the conditions in the mine hole change more, the later updating of the mine hole three-dimensional map needs to be updated by means of the point cloud data, and the cost is high, so that a mine hole three-dimensional map construction method and system with low updating cost are needed.
Disclosure of Invention
The invention aims to provide a mine cavity three-dimensional map construction method and system for an unmanned mine car with low updating cost.
The invention discloses a mine cavity three-dimensional map construction method for an unmanned mine car, which comprises the following steps:
acquiring in-hole point cloud structure data, and analyzing the in-hole point cloud structure data by using a surface reconstruction algorithm to generate an in-hole point cloud structure model;
analyzing the point cloud structure model in the hole, determining the protruding features to be focused, and independently geometrically forming the protruding features to be focused to generate an initial mine hole three-dimensional map;
Performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of reference hole visual images, and associating the reference hole visual images with the initial mine hole three-dimensional map based on position nodes corresponding to the reference hole visual images of each frame;
Scanning and analyzing the visual image in the reference hole, determining the structural characteristics in the hole expressed by the image, correlating the structural characteristics in the hole with the raised characteristics to be focused in the visual image in the reference hole, and marking the raised characteristics on the visual image in the reference hole;
And acquiring a real-time in-tunnel visual image of the unmanned mine car, matching the corresponding reference in-tunnel visual image based on the position node corresponding to the real-time in-tunnel visual image, comparing the two images, and updating the initial three-dimensional map if the images are different and meet the three-dimensional map reconstruction requirement.
In some embodiments of the present disclosure, a method for generating a point cloud structure model in a hole includes:
coordinate positioning is carried out on the point cloud structure data, and preprocessing is carried out on the point cloud structure data, wherein the preprocessing comprises outlier removal and ground segmentation;
generating an in-hole point cloud structure model by using a surface reconstruction algorithm, and optimizing the in-hole point cloud structure model, wherein the in-hole point cloud structure model comprises artifact removal, isolated point removal or abnormal structure removal;
And smoothing the protruding features which do not meet the attention requirement in the in-hole point cloud structure model, and neglecting the protruding features which meet the attention requirement for excessive processing.
In some embodiments of the present disclosure, a method of independently geometrically linking protruding features of a structure includes:
determining the protruding structural features of the point cloud structural model in the hole, and if the protruding features meet the attention requirements, marking the protruding features as protruding features to be noted;
And performing polygonal structure simplification on the mutually connected protruding features to be focused to obtain independent geometric bodies, and configuring the independent geometric bodies at corresponding positions of the point cloud structure model in the hole.
In some embodiments of the present disclosure, a method of determining whether a protruding feature meets a requirement of interest includes:
establishing a central reference line for a central area of a hole body of the in-hole point cloud structure model, wherein the central reference line is parallel to the trend of the hole body, setting a plurality of metering probe points on the in-hole point cloud structure model at uniform intervals, and calculating the relative distance between each metering probe point and the central reference line;
Setting a virtual block with a specific size to carry out mobile scanning on the point cloud structure model in the hole, determining a measurement probe point mapped during each mobile scanning, determining a convex expression value of the convex feature based on the overall performance characteristic of the relative distance of the measurement probe point, and if the convex expression value is greater than or equal to a preset value, determining that the convex feature meets the attention requirement;
And if the convex features corresponding to the mutually connected virtual blocks meet the attention requirements, connecting the convex features.
In some embodiments of the present disclosure, the expression for calculating the convex expression value of the convex feature is:
；
wherein T is the convex expression value of the convex feature, Weights are considered for convex area,/>For the projection height, weight is considered,/>To measure the standard relative distance of the probe point to the central reference line,/>For the relative distance of the ith metrology probe point to the central reference line,/>As the first measurement probe height judging function, when/>When the value is smaller than or equal to a first preset value, then/>Output 1, otherwise output 0,/>As the second measurement probe point height judging functionWhen the value is less than or equal to a second preset value, then/>Output 1, otherwise output 0,/>The constant is adjusted for the protrusion height.
In some embodiments of the present disclosure, a method for scanning and analyzing a visual image in a reference hole to determine a structural feature in the hole expressed by the image includes:
Graying the visual image in the reference hole, determining an edge line of the visual image in the reference hole by utilizing an edge detection technology, positioning image coordinates of the edge line of the projection feature to be focused, and marking the image coordinates as a marked edge line;
the marked edge lines are correlated and a first simple geometric line is constructed from the shape of the marked edge lines and correlated with the marked edge lines.
In some embodiments of the present disclosure, a method of comparing a real-time intra-hole visual image with a reference intra-hole visual image includes:
graying the visual image in the real-time hole, determining edge lines of the visual image in the real-time hole by utilizing an edge detection technology, and positioning image coordinates of the edge lines in the image;
based on the positioning coordinates of the edge lines in the real-time hole visual image, finding out the edge lines with the identical positioning coordinates in the reference hole visual image, comparing and correlating the edge lines, and constructing a second simple geometric line according to the shape of the edge lines in the real-time hole visual image;
And comparing the matched lengths of the first simple geometric line and the second simple geometric line, and if the matched lengths are smaller than or equal to a preset value, determining that the image difference characteristics of the visual image in the real-time hole and the visual image in the reference hole accord with the three-dimensional map reconstruction requirement.
In some embodiments of the present disclosure, a mine cavity three-dimensional map construction system for an unmanned mine car is also disclosed, comprising:
the first module is used for acquiring point cloud structure data in the hole, analyzing the point cloud structure data in the hole by utilizing a surface reconstruction algorithm and generating an in-hole point cloud structure model;
The second module is used for analyzing the point cloud structure model in the hole, determining the protruding features to be focused, and independently geometrically generating the protruding features to be focused to generate an initial mine hole three-dimensional map;
The third module is used for performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of visual images in the reference hole, and associating the visual images in the reference hole with the initial mine hole three-dimensional map based on the position nodes corresponding to the visual images in each frame of the reference hole;
A fourth module, configured to scan and analyze the visual image in the reference hole, determine the structural feature in the hole expressed by the image, correlate the structural feature in the hole with the salient feature to be focused in the visual image in the reference hole, and mark the salient feature on the visual image in the reference hole;
And a fifth module, configured to obtain a real-time in-tunnel visual image of the unmanned mine car, match a corresponding reference in-tunnel visual image based on a position node corresponding to the real-time in-tunnel visual image, and compare image difference features of the two, and update the initial three-dimensional map if the image difference features meet a three-dimensional map reconstruction requirement.
The invention discloses a mine cavity three-dimensional map construction method and system for an unmanned mine car, and relates to the technical field of unmanned mine cars.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a diagram of method steps of a mine cavity three-dimensional construction method for an unmanned mine car according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments, it being understood that the preferred embodiments described herein are for illustrating and explaining the present invention only and are not to be construed as limiting the scope of the present invention, and that some insubstantial modifications and adaptations can be made by those skilled in the art in light of the following disclosure. In the present invention, unless explicitly specified and defined otherwise, technical terms used in the present invention should be construed in a general sense as understood by those skilled in the art to which the present invention pertains.
The invention aims to provide a mine cavity three-dimensional map construction method and system for an unmanned mine car with low updating cost.
The invention discloses a mine cavity three-dimensional map construction method for an unmanned mine car, referring to FIG. 1, comprising the following steps:
and S100, acquiring in-hole point cloud structure data, and analyzing the in-hole point cloud structure data by using a surface reconstruction algorithm to generate an in-hole point cloud structure model.
In the step, firstly, acquiring point cloud structure data in a mine cavity through sensors such as a laser radar and the like; the data comprise three-dimensional coordinate information of the inner surface of the mine cavity; then, analyzing the point cloud structure data in the hole by using a surface reconstruction algorithm; the surface reconstruction algorithm can restore discrete point cloud data into a smooth surface through interpolation, fitting and other technologies, so that an in-hole point cloud structure model is generated; this model will accurately reflect the topography and structural features within the mine cavity.
In some embodiments of the present disclosure, a method for generating a point cloud structure model in a hole includes:
step S101, coordinate positioning is conducted on point cloud structure data, and preprocessing is conducted on the point cloud structure data, wherein the preprocessing comprises outlier removal and ground segmentation.
Step S102, generating an in-hole point cloud structure model by using a surface reconstruction algorithm, and optimizing the in-hole point cloud structure model, wherein the in-hole point cloud structure model comprises artifact removal, isolated point removal or abnormal structure removal.
And step S103, smoothing the protruding features which do not meet the attention requirement in the in-hole point cloud structure model, and neglecting the protruding features which meet the attention requirement for excessive processing.
In some embodiments of the present disclosure, a method of determining whether a protruding feature meets a requirement of interest includes:
Step S1031, a central reference line is established for the central area of the cavity body of the in-cavity point cloud structure model, the central reference line is parallel to the trend of the cavity body, a plurality of metering probe points are set on the in-cavity point cloud structure model at uniform intervals, and the relative distance between each metering probe point and the central reference line is calculated.
Step S1032, setting a virtual block with a specific size to carry out mobile scanning on the point cloud structure model in the hole, determining a measurement probe point mapped during each mobile scanning, determining a convex expression value of the convex feature based on the overall performance characteristic of the relative distance of the measurement probe point, and if the convex expression value is greater than or equal to a preset value, determining that the convex feature meets the attention requirement.
Step S1033, if the protruding features corresponding to the virtual blocks connected with each other meet the attention requirement, connecting the protruding features.
And step S200, analyzing the point cloud structure model in the hole, determining the salient features to be focused, and independently geometrically generating the salient features to be focused to generate an initial mine hole three-dimensional map.
In the step, the in-hole point cloud structure model is analyzed in detail to determine the protruding features needing to be focused; these raised features may represent critical structures or targets within the mine cavity; performing independent geometric treatment on the salient features to be focused to generate an initial mine cavity three-dimensional map; the purpose of this step is to extract key features in the map, providing a basis for subsequent visual testing and updating.
In some embodiments of the present disclosure, a method of independently geometrically linking protruding features of a structure includes:
step S201, determining the protruding structural features of the point cloud structural model in the hole, and if the protruding features meet the attention requirements, marking the protruding features as protruding features needing attention.
Step S202, performing polygonal structure simplification on the connected protruding features to be focused to obtain independent geometric bodies, and configuring the independent geometric bodies at corresponding positions of the point cloud structure model in the hole.
And step S300, performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of visual images in the reference hole, and associating the visual images in the reference hole with the initial mine hole three-dimensional map based on the position nodes corresponding to the visual images in the reference hole of each frame.
In this step, a preliminary visual test is performed on the initial mine cavity three-dimensional map; the method comprises the steps that through obtaining a plurality of frames of visual images in a reference hole, the visual images in the reference hole are associated with an initial mine hole three-dimensional map based on position nodes corresponding to the visual images in each frame of reference hole; the association process aims at verifying the accuracy and consistency of the map and simultaneously establishing the corresponding relation between the visual image in the hole and the three-dimensional map.
Step S400, scanning and analyzing the visual image in the reference hole, determining the structural characteristics in the hole expressed by the image, correlating the structural characteristics in the hole with the salient characteristics to be focused in the visual image in the reference hole, and marking the salient characteristics on the visual image in the reference hole.
In this step, a detailed scan analysis is performed on the visual image within the reference hole; by determining the in-hole structural features expressed by the image, correlating the features with the previously determined raised features to be noted and marking the raised features on the visual image in the reference hole; this step aims at associating intra-cavity structural features in the three-dimensional map of the mine cavity with salient features of interest.
In some embodiments of the present disclosure, a method for scanning and analyzing a visual image in a reference hole to determine a structural feature in the hole expressed by the image includes:
Step S401, graying the visual image in the reference hole, determining edge lines of the visual image in the reference hole by utilizing an edge detection technology, positioning image coordinates of the edge lines which are mapped with the raised features to be focused, and marking the image coordinates as marked edge lines.
Step S402, the marked edge lines are associated, and a first simple geometric line is constructed according to the shape of the marked edge lines and is associated with the marked edge lines.
And S500, acquiring a real-time in-tunnel visual image of the unmanned mine car, matching the corresponding reference in-tunnel visual image based on the position node corresponding to the real-time in-tunnel visual image, and comparing the image difference characteristics of the two images, and updating the initial three-dimensional map if the image difference characteristics meet the three-dimensional map reconstruction requirement.
In some embodiments of the present disclosure, a method of comparing a real-time intra-hole visual image with a reference intra-hole visual image includes:
step S501, graying is carried out on the visual image in the real-time hole, an edge line of the visual image in the real-time hole is determined by utilizing an edge detection technology, and image coordinate positioning is carried out on the edge line in the image.
Step S502, based on the positioning coordinates of the edge lines in the real-time hole visual image, finding out the edge lines with the identical positioning coordinates in the reference hole visual image, comparing and correlating the edge lines, and constructing a second simple geometric line according to the shape of the compared and correlated edge lines in the real-time hole visual image.
Step S503, comparing the matched lengths of the first simple geometric line and the second simple geometric line, and if the matched length is smaller than or equal to a preset value, determining that the image difference characteristics of the visual image in the real-time hole and the visual image in the reference hole meet the three-dimensional map reconstruction requirement.
In the step, a real-time in-tunnel visual image of the unmanned mine car is acquired; matching corresponding reference intra-hole visual images by the position nodes corresponding to the real-time intra-hole visual images, and comparing the image difference characteristics of the two images; if the image difference characteristics meet the requirements of three-dimensional map reconstruction, namely reflect the actual structural change in the mine cavity, updating the initial three-dimensional map; the step realizes the real-time dynamic update of the map, and ensures that the map can reflect the latest state in the mine tunnel.
The steps S100-S500 realize accurate three-dimensional modeling and map updating of the internal structure of the mine tunnel; acquiring point cloud structure data in a hole by adopting sensors such as a laser radar and the like, generating a point cloud structure model by utilizing a surface reconstruction algorithm, and firstly establishing an initial model of the mine hole topography by the system; then, on the basis of analyzing the model, generating an initial mine cavity three-dimensional map by independently geometrically processing the salient features to be focused; this map reflects not only the overall structure of the mine tunnel, but also focuses on key geological features. Then, the system acquires visual images in a plurality of frames of reference holes through preliminary visual testing on the initial mine hole three-dimensional map, and establishes association with the map; determining the intra-hole structural features expressed by the images by scanning and analyzing the reference intra-hole visual images, and associating the features to the salient features to be focused in the initial map; this process enhances understanding of the map structure and makes the map richer and finer. Finally, matching and comparing the real-time image with a previous reference image by acquiring a real-time in-tunnel visual image of the unmanned mine car; if the image difference characteristics meet the three-dimensional map reconstruction requirement, the system updates the initial three-dimensional map in real time; the step realizes the real-time dynamic update of the map, and ensures that the map can reflect the change in the mine hole in time; in combination, the whole process provides a continuously optimized mechanism to adapt to the real-time change of the internal structure of the mine tunnel, and provides accurate and real-time navigation and environment perception support for the unmanned mine car.
In some embodiments of the present disclosure, the expression for calculating the convex expression value of the convex feature is:
。
wherein T is the convex expression value of the convex feature, Weights are considered for convex area,/>For the projection height, weight is considered,/>To measure the standard relative distance of the probe point to the central reference line,/>For the relative distance of the ith metrology probe point to the central reference line,/>As the first measurement probe height judging function, when/>When the value is smaller than or equal to a first preset value, then/>Output 1, otherwise output 0,/>As the second measurement probe point height judging functionWhen the value is less than or equal to a second preset value, then/>Output 1, otherwise output 0,/>The constant is adjusted for the protrusion height.
In some embodiments of the present disclosure, a mine cavity three-dimensional map construction system for an unmanned mine car is also disclosed, comprising:
the first module is used for acquiring point cloud structure data in the hole, analyzing the point cloud structure data in the hole by utilizing a surface reconstruction algorithm and generating an in-hole point cloud structure model;
The second module is used for analyzing the point cloud structure model in the hole, determining the protruding features to be focused, and independently geometrically generating the protruding features to be focused to generate an initial mine hole three-dimensional map;
The third module is used for performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of visual images in the reference hole, and associating the visual images in the reference hole with the initial mine hole three-dimensional map based on the position nodes corresponding to the visual images in each frame of the reference hole;
A fourth module, configured to scan and analyze the visual image in the reference hole, determine the structural feature in the hole expressed by the image, correlate the structural feature in the hole with the salient feature to be focused in the visual image in the reference hole, and mark the salient feature on the visual image in the reference hole;
And a fifth module, configured to obtain a real-time in-tunnel visual image of the unmanned mine car, match a corresponding reference in-tunnel visual image based on a position node corresponding to the real-time in-tunnel visual image, and compare image difference features of the two, and update the initial three-dimensional map if the image difference features meet a three-dimensional map reconstruction requirement.
The invention discloses a mine cavity three-dimensional map construction method and system for an unmanned mine car, and relates to the technical field of unmanned mine cars.
From the above description of the embodiments, it will be clear to those skilled in the art that the present invention may be implemented in hardware, or may be implemented by means of software plus necessary general hardware platforms. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (8)
1. A mine cavity three-dimensional map construction method for an unmanned mine car, comprising the steps of:
acquiring in-hole point cloud structure data, and analyzing the in-hole point cloud structure data by using a surface reconstruction algorithm to generate an in-hole point cloud structure model;
analyzing the point cloud structure model in the hole, determining the protruding features to be focused, and independently geometrically forming the protruding features to be focused to generate an initial mine hole three-dimensional map;
Performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of reference hole visual images, and associating the reference hole visual images with the initial mine hole three-dimensional map based on position nodes corresponding to the reference hole visual images of each frame;
Scanning and analyzing the visual image in the reference hole, determining the structural characteristics in the hole expressed by the image, correlating the structural characteristics in the hole with the raised characteristics to be focused in the visual image in the reference hole, and marking the raised characteristics on the visual image in the reference hole;
And acquiring a real-time in-tunnel visual image of the unmanned mine car, matching the corresponding reference in-tunnel visual image based on the position node corresponding to the real-time in-tunnel visual image, comparing the two images, and updating the initial three-dimensional map if the images are different and meet the three-dimensional map reconstruction requirement.
2. A method of three-dimensional map construction of a mine tunnel for an unmanned mine car according to claim 1, wherein the method of generating an in-tunnel point cloud structure model comprises:
coordinate positioning is carried out on the point cloud structure data, and preprocessing is carried out on the point cloud structure data, wherein the preprocessing comprises outlier removal and ground segmentation;
generating an in-hole point cloud structure model by using a surface reconstruction algorithm, and optimizing the in-hole point cloud structure model, wherein the in-hole point cloud structure model comprises artifact removal, isolated point removal or abnormal structure removal;
And smoothing the protruding features which do not meet the attention requirement in the in-hole point cloud structure model, and neglecting the protruding features which meet the attention requirement for excessive processing.
3. A method of three-dimensional map construction of a mine cavity for an unmanned mine car according to claim 1, wherein the method of independent geometrically-based protruding features of the structure comprises:
determining the protruding structural features of the point cloud structural model in the hole, and if the protruding features meet the attention requirements, marking the protruding features as protruding features to be noted;
And performing polygonal structure simplification on the mutually connected protruding features to be focused to obtain independent geometric bodies, and configuring the independent geometric bodies at corresponding positions of the point cloud structure model in the hole.
4. A method of three-dimensional mapping a mine cavity for an unmanned mine car according to claim 2 or claim 3, wherein the method of determining whether the protruding feature meets the requirements of interest comprises:
establishing a central reference line for a central area of a hole body of the in-hole point cloud structure model, wherein the central reference line is parallel to the trend of the hole body, setting a plurality of metering probe points on the in-hole point cloud structure model at uniform intervals, and calculating the relative distance between each metering probe point and the central reference line;
Setting a virtual block with a specific size to carry out mobile scanning on the point cloud structure model in the hole, determining a measurement probe point mapped during each mobile scanning, determining a convex expression value of the convex feature based on the overall performance characteristic of the relative distance of the measurement probe point, and if the convex expression value is greater than or equal to a preset value, determining that the convex feature meets the attention requirement;
And if the convex features corresponding to the mutually connected virtual blocks meet the attention requirements, connecting the convex features.
5. The method for three-dimensional map construction of mine tunnel for unmanned mine car as claimed in claim 4, wherein the expression for calculating the protruding expression value of the protruding feature is:
；
wherein T is the convex expression value of the convex feature, Weights are considered for convex area,/>In order to take the weight of the protrusion height into consideration,To measure the standard relative distance of the probe point to the central reference line,/>For the relative distance of the ith metrology probe point to the central reference line,/>As the first measurement probe height judging function, when/>When the value is smaller than or equal to a first preset value, then/>Output 1, otherwise output 0,/>As the second measurement probe point height judging functionWhen the value is less than or equal to a second preset value, then/>Output 1, otherwise output 0,/>The constant is adjusted for the protrusion height.
6. A method of three-dimensional map construction of a mine cavity for an unmanned mine car according to claim 1, wherein the method of scanning the visual image of the reference cavity to determine the structural characteristics of the cavity expressed by the image comprises:
Graying the visual image in the reference hole, determining an edge line of the visual image in the reference hole by utilizing an edge detection technology, positioning image coordinates of the edge line of the projection feature to be focused, and marking the image coordinates as a marked edge line;
the marked edge lines are correlated and a first simple geometric line is constructed from the shape of the marked edge lines and correlated with the marked edge lines.
7. A method of three-dimensional map construction of a mine cavity for an unmanned mine car as defined in claim 6, wherein the method of comparing the real-time in-cavity visual image with the reference in-cavity visual image comprises:
graying the visual image in the real-time hole, determining edge lines of the visual image in the real-time hole by utilizing an edge detection technology, and positioning image coordinates of the edge lines in the image;
based on the positioning coordinates of the edge lines in the real-time hole visual image, finding out the edge lines with the identical positioning coordinates in the reference hole visual image, comparing and correlating the edge lines, and constructing a second simple geometric line according to the shape of the edge lines in the real-time hole visual image;
And comparing the matched lengths of the first simple geometric line and the second simple geometric line, and if the matched lengths are smaller than or equal to a preset value, determining that the image difference characteristics of the visual image in the real-time hole and the visual image in the reference hole accord with the three-dimensional map reconstruction requirement.
8. A mine cavity three-dimensional map construction system for an unmanned mine car, comprising:
the first module is used for acquiring point cloud structure data in the hole, analyzing the point cloud structure data in the hole by utilizing a surface reconstruction algorithm and generating an in-hole point cloud structure model;
The second module is used for analyzing the point cloud structure model in the hole, determining the protruding features to be focused, and independently geometrically generating the protruding features to be focused to generate an initial mine hole three-dimensional map;
The third module is used for performing preliminary visual testing on the initial mine hole three-dimensional map to obtain a plurality of frames of visual images in the reference hole, and associating the visual images in the reference hole with the initial mine hole three-dimensional map based on the position nodes corresponding to the visual images in each frame of the reference hole;
A fourth module, configured to scan and analyze the visual image in the reference hole, determine the structural feature in the hole expressed by the image, correlate the structural feature in the hole with the salient feature to be focused in the visual image in the reference hole, and mark the salient feature on the visual image in the reference hole;
And a fifth module, configured to obtain a real-time in-tunnel visual image of the unmanned mine car, match a corresponding reference in-tunnel visual image based on a position node corresponding to the real-time in-tunnel visual image, and compare image difference features of the two, and update the initial three-dimensional map if the image difference features meet a three-dimensional map reconstruction requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410465777.9A CN118115688A (en) | 2024-04-18 | 2024-04-18 | Mine cavity three-dimensional map construction method and system for unmanned mine car |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410465777.9A CN118115688A (en) | 2024-04-18 | 2024-04-18 | Mine cavity three-dimensional map construction method and system for unmanned mine car |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118115688A true CN118115688A (en) | 2024-05-31 |
Family
ID=91219286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410465777.9A Pending CN118115688A (en) | 2024-04-18 | 2024-04-18 | Mine cavity three-dimensional map construction method and system for unmanned mine car |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118115688A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0981778A (en) * | 1995-09-13 | 1997-03-28 | Toshiba Corp | Device and method for modeling |
| CN109991621A (en) * | 2019-04-15 | 2019-07-09 | 贵州省山地资源研究所 | A kind of cave three-dimensional laser scanning measurement method |
| CN113256588A (en) * | 2021-05-31 | 2021-08-13 | 西安建筑科技大学 | Real-time updating method for refuse dump and refuse disposal edge line in unmanned strip mine |
| KR20220151572A (en) * | 2021-05-06 | 2022-11-15 | 한국도로공사 | Method and System for change detection and automatic updating of road marking in HD map through IPM image and HD map fitting |
| CN115858702A (en) * | 2022-11-23 | 2023-03-28 | 北京天玛智控科技股份有限公司 | Maintenance method and device for point cloud map under mine, aircraft and electronic equipment |
| CN115908727A (en) * | 2022-11-03 | 2023-04-04 | 中煤科工集团沈阳设计研究院有限公司 | Method for establishing design and construction integration of intelligent strip mine |
| CN117350085A (en) * | 2023-12-05 | 2024-01-05 | 西安热工研究院有限公司 | Three-dimensional original view reproduction method and device for cabin and cabin materials |
-
2024
- 2024-04-18 CN CN202410465777.9A patent/CN118115688A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0981778A (en) * | 1995-09-13 | 1997-03-28 | Toshiba Corp | Device and method for modeling |
| CN109991621A (en) * | 2019-04-15 | 2019-07-09 | 贵州省山地资源研究所 | A kind of cave three-dimensional laser scanning measurement method |
| KR20220151572A (en) * | 2021-05-06 | 2022-11-15 | 한국도로공사 | Method and System for change detection and automatic updating of road marking in HD map through IPM image and HD map fitting |
| CN113256588A (en) * | 2021-05-31 | 2021-08-13 | 西安建筑科技大学 | Real-time updating method for refuse dump and refuse disposal edge line in unmanned strip mine |
| CN115908727A (en) * | 2022-11-03 | 2023-04-04 | 中煤科工集团沈阳设计研究院有限公司 | Method for establishing design and construction integration of intelligent strip mine |
| CN115858702A (en) * | 2022-11-23 | 2023-03-28 | 北京天玛智控科技股份有限公司 | Maintenance method and device for point cloud map under mine, aircraft and electronic equipment |
| CN117350085A (en) * | 2023-12-05 | 2024-01-05 | 西安热工研究院有限公司 | Three-dimensional original view reproduction method and device for cabin and cabin materials |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105136054B (en) | The fine deformation monitoring method of structures and system based on Three Dimensional Ground laser scanning | |
| CN111913169B (en) | Laser radar internal reference and point cloud data correction method, device and storage medium | |
| CN107122522B (en) | Digital elevation model precision evaluation method based on fill-cut analysis | |
| EP3792591B1 (en) | Surveying data processing device, surveying data processing method, and surveying data processing program | |
| JP6099728B1 (en) | Laser measurement system and laser measurement method | |
| CN111709131A (en) | Tunnel axis determining method and device | |
| CN113538668A (en) | Geological model construction method, geological model construction system, storage medium and electronic equipment | |
| CN114595238A (en) | Vector-based map processing method and device | |
| CN108759668B (en) | Tracking type three-dimensional scanning method and system in vibration environment | |
| JP2020135764A (en) | Three-dimensional object modeling method, three-dimensional object modeling device, server, three-dimensional model creation system, and program | |
| Lucks et al. | Improving trajectory estimation using 3D city models and kinematic point clouds | |
| CN118115688A (en) | Mine cavity three-dimensional map construction method and system for unmanned mine car | |
| Ma et al. | Hybrid model for realistic and efficient estimation of highway sight distance using airborne LiDAR data | |
| CN114820965B (en) | Live-action three-dimensional modeling method for holographic map construction | |
| CN111982152B (en) | Point cloud map quantification method and device, computer equipment and storage medium | |
| CN115270240A (en) | Power transmission area visualization implementation method and device, computer equipment and storage medium | |
| CN107246863A (en) | A kind of irregular bore tunnel inwall image projecting method of deploying | |
| CN113515513B (en) | Track correction method and device, and point cloud map generation method and device | |
| CN116528360B (en) | Bluetooth AOA positioning resolving method | |
| CN115900644B (en) | Laser scanning imaging method and device for hydraulic support robot working face bottom plate | |
| CN117668574B (en) | Data model optimization method, device and equipment for light shadow show and storage medium | |
| CN113029166B (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| US20230243926A1 (en) | Ranging error calculation device, ranging error calculation method and storage medium | |
| CN111366172B (en) | Quality detection method and device of digital elevation model and storage medium | |
| CN109489553B (en) | Method, device, equipment and storage medium for generating space marker point library |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |