CN117523239A - Point cloud processing method and system for power equipment - Google Patents
Point cloud processing method and system for power equipment Download PDFInfo
- Publication number
- CN117523239A CN117523239A CN202311472833.3A CN202311472833A CN117523239A CN 117523239 A CN117523239 A CN 117523239A CN 202311472833 A CN202311472833 A CN 202311472833A CN 117523239 A CN117523239 A CN 117523239A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- power equipment
- source
- anchor
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims description 18
- 238000007635 classification algorithm Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 6
- 230000007547 defect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a point cloud processing method and a point cloud processing system for power equipment, which relate to the technical field of point cloud data processing of the power equipment and comprise the steps of acquiring first point cloud data of the power equipment; processing the first point cloud data to generate second point cloud data; searching an anchor point matching point pair in the second point cloud data through classification operation; and acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set. The video obtained through daily inspection shooting is used as the original data to establish the three-dimensional model, the original data acquisition mode is simpler and more convenient, daily updating and reconstruction of the three-dimensional model are facilitated, so that the fault defect of the power equipment is found, and meanwhile, the point cloud is combined with the power equipment with the real scale, so that the accurate registration of the power equipment image in the three-dimensional space is facilitated.
Description
Technical Field
The invention relates to the technical field of point cloud data processing of power equipment, in particular to a method and a system for processing point cloud of power equipment.
Background
In order to respond to the implementation of the digital transformation strategy of the power grid, various digital twin technologies are developed gradually in China, and a technical means is provided for high-precision informatization and vectorization of various power equipment in a power transmission corridor.
At present, the Chinese patent application number 201810695359.3 discloses a point cloud of power equipment, a three-dimensional space model is divided into a plurality of cuboid spaces, point cloud data in the cuboid spaces can be used for monitoring characteristics such as shapes, environments and the like of single power equipment, associated attribute information can be used for identifying the running states of the power equipment, such as appearance, stress deformation and the like, so that technical support is provided for operation and inspection of the power equipment, three-dimensional reconstruction can be performed, but a point cloud identification method of traditional machine learning or deep learning is not combined with the power equipment with real dimensions, and therefore registration of power equipment images is difficult to accurately achieve in the three-dimensional space.
Disclosure of Invention
The invention solves the technical problems that: because the traditional machine learning or deep learning point cloud identification method is not combined with the real-scale power equipment, accurate registration of the power equipment images in the three-dimensional space is difficult to realize.
In order to solve the technical problems, the invention provides the following technical scheme: the power equipment point cloud processing method comprises the steps of obtaining first point cloud data of power equipment; processing the first point cloud data to generate second point cloud data; searching for anchor point matching point pairs in the second point cloud data through classification operation; and acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set.
As a preferable scheme of the power equipment point cloud processing method of the present invention, the method comprises: the obtained point cloud data of the power equipment comprises the following steps: shooting the power equipment by using transformer substation shooting equipment; decomposing the video shot by the camera into independent pictures frame by frame, and sequencing according to a time sequence to form a visible light image sequence; and carrying out gray scale processing on the visible light image sequence to form a gray scale image sequence, and taking pixel values and pixel position information of each pixel on a gray scale image as first point cloud data.
As a preferable scheme of the power equipment point cloud processing method of the present invention, the method comprises:
processing the first point cloud data to generate second point cloud data includes:
the first point cloud data comprises a target point cloud and a source point cloud;
extracting edge information of images on each gray scale image through a guide filter;
defining the time sequence of the adjacent gray images as target point clouds earlier, and defining the time sequence of the adjacent gray images as source point clouds later;
selecting an endpoint on the edge information as an anchor point, and taking a pixel value and pixel position information at the anchor point as second point cloud data;
the second point cloud data includes a target point cloud anchor point and a source point Yun Maodian;
and defining an anchor point in the target point cloud as a target point cloud anchor point, and defining an anchor point in the source point cloud as a source point cloud anchor point.
As a preferable scheme of the power equipment point cloud processing method of the present invention, the method comprises:
searching for anchor point matching point pairs in the second point cloud data by performing classification operation comprises:
respectively calculating Euclidean distances of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points;
randomly selecting Euclidean distances of two adjacent target point cloud anchor points in the target point cloud anchor points as target Euclidean distances;
and performing first classification operation on the Euclidean distances of the source points of the adjacent source point cloud anchors in the source point cloud anchors by using a classification algorithm, and screening the source point Euclidean distances which are the same as the target Euclidean distances.
As a preferable scheme of the power equipment point cloud processing method of the present invention, the method comprises:
performing a second classification operation on the screened Euclidean distance of the source point by using a classification algorithm, and screening the source point Euclidean distance which is the same as the target Euclidean distance;
and repeating the classification operation until all target point cloud anchor point operations are finished, wherein the classification algorithm is a K nearest neighbor algorithm.
As a preferable scheme of the power equipment point cloud processing method of the present invention, the method comprises:
the acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set comprises the following steps:
acquiring a set of Euclidean distances of a source point matched with a source point cloud anchor point;
dividing the region according to the position of the edge information;
and selecting the area with the largest Euclidean distance number of the source points matched with the source point cloud anchor points as an edge information superposition part in the target point cloud and the source point cloud.
As a preferable scheme of the power equipment point cloud processing system of the invention, the power equipment point cloud processing system comprises:
the acquisition module is used for shooting the power equipment and acquiring first point cloud data;
the extraction module is used for extracting second point cloud data;
the registration module is used for matching the target point cloud anchor point and the source point cloud anchor point in the second point cloud data with a point pair, constructing a point cloud registration model for matching the point pair on the power equipment picture.
As a preferable scheme of the power equipment point cloud processing system of the invention, the power equipment point cloud processing system comprises:
the acquisition module comprises an acquisition subunit and a decomposition subunit;
the acquisition subunit acquires shooting videos by shooting the power equipment;
the decomposition subunit performs gray scale processing on the video to form a gray scale image sequence, and takes pixel values and pixel position information of each pixel on a gray scale image as first point cloud data.
As a preferable scheme of the power equipment point cloud processing system of the invention, the power equipment point cloud processing system comprises:
the extraction module comprises a guide filter and a calibration subunit;
the guiding filter is used for extracting edge information of the images on each gray level image;
the marking unit is used for marking the anchor points on the edge information.
As a preferable scheme of the power equipment point cloud processing system of the invention, the power equipment point cloud processing system comprises:
the registration module comprises a calculation subunit, a classification subunit and a selection subunit;
the Euclidean distance of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points is calculated;
the classifying subunit is used for classifying the Euclidean distance of the source points of the adjacent anchor points in the source point cloud anchor points;
the selecting subunit is configured to select an edge information overlapping portion in the target point cloud and the source point cloud as a registration result.
The invention has the beneficial effects that: the video obtained through daily inspection shooting is used as the original data to establish the three-dimensional model, the original data acquisition mode is simpler and more convenient, daily updating and reconstruction of the three-dimensional model are facilitated, so that the fault defect of the power equipment is found, and meanwhile, the point cloud is combined with the power equipment with the real scale, so that the accurate registration of the power equipment image in the three-dimensional space is facilitated.
Drawings
Fig. 1 is a basic flow diagram of a point cloud processing method for an electrical device according to an embodiment of the present invention;
fig. 2 is a physical diagram of adjacent source point cloud anchor points of a power equipment point cloud processing method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an adjacent target point cloud anchor point of a power device point cloud processing method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of adjacent source point cloud anchor points of a power device point cloud processing method according to an embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings.
Example 1
1-4, for one embodiment of the present invention, a method for processing a point cloud of an electrical device is provided, including:
s100: the obtained point cloud data of the power equipment comprises the following steps:
shooting the power equipment by using transformer substation shooting equipment;
decomposing the video shot by the camera into independent pictures frame by frame, and sequencing according to a time sequence to form a visible light image sequence;
and carrying out gray scale processing on the visible light image sequence to form a gray scale image sequence, and taking pixel values and pixel position information of each pixel on a gray scale image as first point cloud data. And recording pixel points, pixel values and pixel positions on the gray level images as pixel information, wherein all the pixel points on all the gray level images are first point cloud data, and the first point cloud data are grouped according to the gray level images and are ordered according to a time sequence.
The laser point cloud model containing absolute scale information can be obtained by utilizing the laser acquisition equipment, but the laser three-dimensional model is a high-precision reference three-dimensional model of the power equipment, and has the advantages of high modeling cost, low scanning frequency and the like, and is obtained by
According to the method, the video obtained through daily inspection shooting is used as the original data to establish the three-dimensional model, the original data acquisition mode is simpler and more convenient, daily updating and reconstruction of the three-dimensional model are facilitated, and therefore fault defects of the power equipment are found.
S200: processing the first point cloud data to generate second point cloud data includes:
the first point cloud data comprises a target point cloud and a source point cloud;
extracting edge information of images on each gray scale image through a guide filter;
defining the time sequence of the adjacent gray images as target point clouds earlier, and defining the time sequence of the adjacent gray images as source point clouds later;
selecting an endpoint on the edge information as an anchor point, and taking a pixel value and pixel position information at the anchor point as second point cloud data;
the second point cloud data includes a target point cloud anchor point and a source point Yun Maodian;
and defining an anchor point in the target point cloud as a target point cloud anchor point, and defining an anchor point in the source point cloud as a source point cloud anchor point.
The edge information on the gray scale image is the edge of each power device in the picture.
In this embodiment, preferably, referring to fig. 3 and fig. 4, in the first target point cloud chart, the edges where A1, B1, C1, D1, E1 and F1 are located are taken as edge information, the edge information includes a pixel point on the edge, and the pixel value and the position information of the pixel point, and A1, B1, C1, D1, E1 and F1 are taken as target point cloud anchor points, so that there may be more actual images. In the cloud image of the second target point, the edges where A2, B2, C2, D2, E2 and F2 are located are used as edge information, and the edges A2, B2, C2, D2, E2 and F2 are used as source point cloud anchor points.
S300: searching for anchor point matching point pairs in the second point cloud data by performing classification operation comprises:
respectively calculating Euclidean distances of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points;
randomly selecting Euclidean distances of two adjacent target point cloud anchor points in the target point cloud anchor points as target Euclidean distances;
performing first classification operation on the Euclidean distances of the source points of adjacent source point cloud anchor points in the source point cloud anchor points by using a classification algorithm, and screening out the Euclidean distances of the source points which are the same as the Euclidean distances of the targets;
performing a second classification operation on the screened Euclidean distance of the source point by using a classification algorithm, and screening the source point Euclidean distance which is the same as the target Euclidean distance;
and repeating the classification operation until all target point cloud anchor point operations are finished, wherein the classification algorithm is a K nearest neighbor algorithm.
And calculating the distance between two adjacent anchor points in the second point cloud data, namely respectively calculating the distances between two adjacent anchor points in the target point cloud anchor point and the source point cloud anchor point through the Euclidean formula.
In this embodiment, preferably, two target point cloud anchors A1 and B1 are selected randomly as target point cloud anchors, target euclidean distances of A1 and B1 are calculated, two arbitrary adjacent source point cloud anchors of the source point cloud anchors are selected randomly at the same time, the source point euclidean distances are calculated, the two adjacent source point cloud anchors include source point euclidean distances of all permutation and combination of A2 and B2, A2 and C2, A2 and D2, A2 and E2 and A2 and F2, B2 and C2, B2 and D2, B2 and E2 and B2 and F2, and the like.
And classifying the source point cloud anchor points with the same Euclidean distance as the target Euclidean distance of A1 and B1 for all the arrangement and combination of any two adjacent source point cloud anchor points for the first time by using a K nearest neighbor algorithm, and screening out the same source point cloud anchor points with the same Euclidean distance as the target Euclidean distance of A1 and B1.
And (3) calculating the target Euclidean distance between one of two adjacent punctuation cloud anchors in the target point cloud anchors and the next adjacent punctuation cloud anchor, namely calculating the target Euclidean distance of B1 and C1, classifying the screened source Euclidean distance for the second time by using a K nearest neighbor algorithm, and screening out the same source point cloud anchor with the same target Euclidean distance of B1 and C1. And (5) ending the cloud anchor point operation of all the target points.
S300: the acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set comprises the following steps:
acquiring a set of Euclidean distances of a source point matched with a source point cloud anchor point;
dividing the region according to the position of the edge information;
and selecting the area with the largest Euclidean distance number of the source points matched with the source point cloud anchor points as an edge information superposition part in the target point cloud and the source point cloud.
Each of the blocks with the edge information closed represents an object in the gray scale image, and the same type of power device shape is the same. Selecting the region with the largest Euclidean distance number of the source points matched with the source point cloud anchor points, namely the same power equipment, namely the points in the blocks with closed edge information can be registered, completing the point cloud registration,
the video obtained through daily inspection shooting is used as the original data to establish the three-dimensional model, the original data acquisition mode is simpler and more convenient, daily updating and reconstruction of the three-dimensional model are facilitated, so that the fault defect of the power equipment is found, and meanwhile, the point cloud is combined with the power equipment with the real scale, so that the accurate registration of the power equipment image in the three-dimensional space is facilitated.
Example 2
For another embodiment of the present invention, which is different from the first embodiment, a power equipment point cloud processing system is provided.
The acquisition module is used for shooting the power equipment and acquiring first point cloud data;
the extraction module is used for extracting second point cloud data;
the registration module is used for matching the target point cloud anchor point and the source point cloud anchor point in the second point cloud data with a point pair, constructing a point cloud registration model for matching the point pair on the power equipment picture.
The acquisition module comprises an acquisition subunit and a decomposition subunit;
the acquisition subunit acquires shooting videos by shooting the power equipment;
the decomposition subunit performs gray scale processing on the video to form a gray scale image sequence, and takes pixel values and pixel position information of each pixel on a gray scale image as first point cloud data.
The extraction module comprises a guide filter and a calibration subunit;
the guiding filter is used for extracting edge information of the images on each gray level image;
the marking unit is used for marking the anchor points on the edge information.
The registration module comprises a calculation subunit, a classification subunit and a selection subunit;
the Euclidean distance of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points is calculated;
the classifying subunit is used for classifying the Euclidean distance of the source points of the adjacent anchor points in the source point cloud anchor points;
the selecting subunit is configured to select an edge information overlapping portion in the target point cloud and the source point cloud as a registration result
The video obtained through daily inspection shooting is used as the original data to establish the three-dimensional model, the original data acquisition mode is simpler and more convenient, daily updating and reconstruction of the three-dimensional model are facilitated, so that the fault defect of the power equipment is found, and meanwhile, the point cloud is combined with the power equipment with the real scale, so that the accurate registration of the power equipment image in the three-dimensional space is facilitated.
It should be appreciated that embodiments of the invention may be implemented or realized by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, in accordance with the methods and drawings described in the specific embodiments. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. The power equipment point cloud processing method is characterized by comprising the following steps of:
the method comprises the steps of obtaining first point cloud data of the power equipment;
processing the first point cloud data to generate second point cloud data;
searching for anchor point matching point pairs in the second point cloud data through classification operation;
and acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set.
2. The power equipment point cloud processing method as claimed in claim 1, wherein:
the obtained point cloud data of the power equipment comprises the following steps:
shooting the power equipment by using transformer substation shooting equipment;
decomposing the video shot by the camera into independent pictures frame by frame, and sequencing according to a time sequence to form a visible light image sequence;
and carrying out gray scale processing on the visible light image sequence to form a gray scale image sequence, and taking pixel values and pixel position information of each pixel on a gray scale image as first point cloud data.
3. The power equipment point cloud processing method as claimed in claim 2, wherein:
processing the first point cloud data to generate second point cloud data includes:
the first point cloud data comprises a target point cloud and a source point cloud;
extracting edge information of images on each gray scale image through a guide filter;
defining the time sequence of the adjacent gray images as target point clouds earlier, and defining the time sequence of the adjacent gray images as source point clouds later;
selecting an endpoint on the edge information as an anchor point, and taking a pixel value and pixel position information at the anchor point as second point cloud data;
the second point cloud data includes a target point cloud anchor point and a source point Yun Maodian;
and defining an anchor point in the target point cloud as a target point cloud anchor point, and defining an anchor point in the source point cloud as a source point cloud anchor point.
4. The power equipment point cloud processing method as claimed in claim 3, wherein:
searching for anchor point matching point pairs in the second point cloud data by performing classification operation comprises:
respectively calculating Euclidean distances of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points;
randomly selecting Euclidean distances of two adjacent target point cloud anchor points in the target point cloud anchor points as target Euclidean distances;
and performing first classification operation on the Euclidean distances of the source points of the adjacent source point cloud anchors in the source point cloud anchors by using a classification algorithm, and screening the source point Euclidean distances which are the same as the target Euclidean distances.
5. The power equipment point cloud processing method as claimed in claim 4, wherein:
performing a second classification operation on the screened Euclidean distance of the source point by using a classification algorithm, and screening the source point Euclidean distance which is the same as the target Euclidean distance;
and repeating the classification operation until all target point cloud anchor point operations are finished, wherein the classification algorithm is a K nearest neighbor algorithm.
6. The method and system for processing the point cloud of the power equipment according to claim 1, wherein the method is characterized in that:
the acquiring the target point cloud and the edge information superposition part in the source point cloud based on the source point Euclidean distance set comprises the following steps:
acquiring a set of Euclidean distances of a source point matched with a source point cloud anchor point;
dividing the region according to the position of the edge information;
and selecting the area with the largest Euclidean distance number of the source points matched with the source point cloud anchor points as an edge information superposition part in the target point cloud and the source point cloud.
7. A power equipment point cloud processing system, comprising:
the acquisition module is used for shooting the power equipment and acquiring first point cloud data;
the extraction module is used for extracting second point cloud data;
the registration module is used for matching the target point cloud anchor point and the source point cloud anchor point in the second point cloud data with a point pair, constructing a point cloud registration model for matching the point pair on the power equipment picture.
8. The power device point cloud processing system of claim 7, wherein: the acquisition module comprises an acquisition subunit and a decomposition subunit;
the acquisition subunit acquires shooting videos by shooting the power equipment;
the decomposition subunit performs gray scale processing on the video to form a gray scale image sequence, and takes pixel values and pixel position information of each pixel on a gray scale image as first point cloud data.
9. The power device point cloud processing system of claim 8, wherein: the extraction module comprises a guide filter and a calibration subunit;
the guiding filter is used for extracting edge information of the images on each gray level image;
the marking unit is used for marking the anchor points on the edge information.
10. The method and system for processing the point cloud of the power equipment according to claim 9, wherein the method is characterized in that:
the registration module comprises a calculation subunit, a classification subunit and a selection subunit;
the Euclidean distance of adjacent anchor points in the target point cloud anchor points and the source point cloud anchor points is calculated;
the classifying subunit is used for classifying the Euclidean distance of the source points of the adjacent anchor points in the source point cloud anchor points;
the selecting subunit is configured to select an edge information overlapping portion in the target point cloud and the source point cloud as a registration result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311472833.3A CN117523239A (en) | 2023-11-07 | 2023-11-07 | Point cloud processing method and system for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311472833.3A CN117523239A (en) | 2023-11-07 | 2023-11-07 | Point cloud processing method and system for power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117523239A true CN117523239A (en) | 2024-02-06 |
Family
ID=89759952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311472833.3A Pending CN117523239A (en) | 2023-11-07 | 2023-11-07 | Point cloud processing method and system for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117523239A (en) |
-
2023
- 2023-11-07 CN CN202311472833.3A patent/CN117523239A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113256778B (en) | Method, device, medium and server for generating vehicle appearance part identification sample | |
| Furrer et al. | Incremental object database: Building 3d models from multiple partial observations | |
| CN110516707B (en) | Image labeling method and device and storage medium thereof | |
| CN112801047B (en) | Defect detection method and device, electronic equipment and readable storage medium | |
| CN109934873B (en) | Method, device and equipment for acquiring marked image | |
| CN109726746A (en) | A kind of method and device of template matching | |
| CN112348737B (en) | Method for generating simulation image, electronic device and storage medium | |
| CN114758337A (en) | Semantic instance reconstruction method, device, equipment and medium | |
| CN110567441A (en) | Particle filter-based positioning method, positioning device, mapping and positioning method | |
| CN110544202A (en) | parallax image splicing method and system based on template matching and feature clustering | |
| CN115937461B (en) | Multi-source fusion model construction and texture generation method, device, medium and equipment | |
| CN112801988A (en) | Object grabbing pose detection method based on RGBD and deep neural network | |
| CN114332183A (en) | Image registration method and device, computer equipment and storage medium | |
| CN112115879A (en) | Shielding-sensitive self-supervision pedestrian re-identification method and system | |
| Akhyar et al. | A beneficial dual transformation approach for deep learning networks used in steel surface defect detection | |
| CN112766348A (en) | Method and device for generating sample data based on antagonistic neural network | |
| CN117523239A (en) | Point cloud processing method and system for power equipment | |
| CN113139540B (en) | Backboard detection method and equipment | |
| CN115937492A (en) | Transformer equipment infrared image identification method based on feature identification | |
| CN117011481A (en) | Method and device for constructing three-dimensional map, electronic equipment and storage medium | |
| US20200013189A1 (en) | Image indexing and retrieval using local image patches for object three-dimensional pose estimation | |
| CN113869122A (en) | Distribution network engineering reinforced control method | |
| CN111928852A (en) | Indoor robot positioning method and system based on LED position coding | |
| CN115311296B (en) | Data generation method, image recognition method, computer storage medium and terminal device | |
| CN116433848B (en) | Screen model generation method, device, electronic equipment and storage medium |
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 |