CN112884026B - Image identification-assisted power transmission line laser LiDAR point cloud classification method - Google Patents
Image identification-assisted power transmission line laser LiDAR point cloud classification method Download PDFInfo
- Publication number
- CN112884026B CN112884026B CN202110142298.XA CN202110142298A CN112884026B CN 112884026 B CN112884026 B CN 112884026B CN 202110142298 A CN202110142298 A CN 202110142298A CN 112884026 B CN112884026 B CN 112884026B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- point
- transmission line
- building
- classification
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image identification-assisted power transmission line laser LiDAR point cloud classification method, which comprises the following steps of: step S1: performing color point cloud dimension reduction processing to generate a channel orthophoto; step S2: establishing a ground object sample library of the power transmission line, and constructing an image recognition model; step S3: coarse extraction is carried out on roads and buildings based on image recognition; step S4: the roads and the buildings based on the morphological characteristics are finely classified. According to the invention, an image recognition technology is introduced based on the traditional classification technology, the texture information contained in the color point cloud is utilized to assist in point cloud classification, and the point cloud classification is predefined before the traditional classification is carried out, so that the classification effect on buildings and roads is improved.
Description
Technical Field
The invention relates to the technical field of power transmission line airborne laser LiDAR, in particular to an image identification-assisted power transmission line laser LiDAR point cloud classification method.
Background
Along with the continuous expansion of the application scale of the airborne laser LiDAR technology in the power industry, the requirement on the automation degree of laser LiDAR data processing is continuously increased. The point cloud classification is a premise and a foundation for processing electric power application data of a laser LiDAR technology, and the existing laser LIDAR classification algorithm mostly only adopts a morphological filtering algorithm, so that the classification effect on vegetation, power lines, towers and other categories with obvious spatial characteristics is good, but the classification effect on ground features (buildings and roads) with the same morphological characteristics is poor. Meanwhile, buildings and roads are ground object categories which are very concerned in the power industry, and in actual power application, visual judgment and manual adjustment are needed, so that great workload is brought to data processing personnel.
Disclosure of Invention
Therefore, one of the purposes of the present invention is to provide an image recognition-assisted power transmission line laser LiDAR point cloud classification method. The method has the advantages that the point cloud classification is assisted by utilizing the image recognition technology, the buildings and roads are pre-recognized in the aspect of images, the building and road boundaries are extracted in a refined mode through morphological characteristics, the classification effect of the point cloud classification on the buildings, the roads and the towers is improved, and the automatic process of the point cloud data processing is further promoted.
One of the purposes of the invention is realized by the following technical scheme:
the image identification-assisted power transmission line laser LiDAR point cloud classification method comprises the following steps of:
step S1: performing color point cloud dimension reduction processing to generate a channel orthophoto;
step S2: establishing a ground object sample library of the power transmission line, and constructing an image recognition model;
step S3: coarse extraction is carried out on roads and buildings based on image recognition;
step S4: the roads and the buildings based on the morphological characteristics are finely classified.
In particular, the step S1 specifically includes:
in the upper left corner (X) of the point cloud plane coordinate min ,Y max ) Dividing a planar two-dimensional grid along the X axis and the Y axis by using the set grid size dL as a starting point, and setting the plane coordinate value of any point P in the point cloud as (X) P ,Y P ) Then it is in the gridThe position is (u) P ,v P )。
And dividing each point in the color point cloud into corresponding grids according to the formula. Constructing an RGB channel image with a pixel size [ (X) max -X min )/dL+1]×[(Y max -Y min )/dL+1]And the pixel RGB is the RGB mean value of the three-dimensional points in the corresponding grid, and a channel orthophoto map is generated.
In particular, the step S2 is to collect image data of the transmission line channel, make building and road labels, establish a transmission line ground feature training sample library, extract image multidimensional depth features from the sample library through a u-net network, improve feature expression capability of various ground feature images, and build a high-precision image recognition model for the transmission line channel images based on a high-power GPU as a hardware basis and combining with a tensor operation calculation mode.
In particular, in the step S3, the image recognition model is used to automatically recognize the building, the road and the tower in the channel orthographic image generated in the step one, so as to obtain the frame standard range of each category. And assigning the three-dimensional point category attribute in the grid corresponding to the pixel in the category frame standard range as the type code identified by the image through the one-to-one correspondence between the pixel and the point cloud grid.
Specifically, the step S4 is based on the rough extraction result of the step S3, different classification results set different morphological feature thresholds, and the morphological features of the point set after rough classification are discriminated and denoised to obtain a fine classification result.
In particular, in the step S4, the definition of each feature is as follows:
building characteristics: the building is divided into inclined roof or flat-topped plane, and the boundary point and the ground have elevation mutation of more than 2 m. Utilizing the pre-classified building point cloud extracted in the step S3, and utilizing a greedy triangular algorithm to construct a triangular network and a topological relation; and further calculating the normal vector of each three-dimensional point in the point cloud, extracting a normal vector change point by utilizing the characteristic of fixed normal vector of the inclined roof or flat roof of the building, comparing the normal vector change point with the adjacent point within 0.5m, and taking the point as a building boundary point when the maximum value of the height difference is more than 2 m. And constructing a convex hull for the extracted boundary points to extract an outer boundary, obtaining the whole outer frame of the building, filtering the points outside the frame, and keeping the points in the frame as building point clouds.
Road characteristics: the road is characterized by a smooth curved surface, and the normal vector is continuous and less than 45 degrees. Utilizing the pre-classified road point cloud extracted in the step S3, and utilizing a greedy triangular algorithm to construct a triangular network and a topological relation; and calculating the normal vector of each three-dimensional point in the point cloud, filtering noise points with the normal vector and the XOY plane included angle being larger than 45 degrees, extracting neighborhood points within 1m of each three-dimensional point, comparing the normal vector, and determining the three-dimensional points with the normal vector included angle being larger than 15 degrees as road boundaries.
It is a further object of the invention to provide a computer device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, which processor implements the method as described above when executing the computer program.
It is a further object of the invention to provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described above.
The beneficial effects of the invention are as follows: the invention introduces an image recognition technology based on the traditional classification technology, utilizes texture information contained in color point clouds to assist in point cloud classification, and predefines the point cloud classification before traditional classification. The method improves the classification effect on buildings, roads and towers.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.
As shown in the figure, the image recognition-assisted power transmission line laser LiDAR point cloud classification method of the embodiment comprises the following steps:
step S1: performing color point cloud dimension reduction processing to generate a channel orthophoto;
in this embodiment, the method specifically includes:
in the upper left corner (X) of the point cloud plane coordinate min ,Y max ) Dividing a planar two-dimensional grid along the X axis and the Y axis by using the set grid size dL as a starting point, and setting the plane coordinate value of any point P in the point cloud as (X) P ,Y P ) Then the grid position where it is located is (u) P ,v P )。
And dividing each point in the color point cloud into corresponding grids according to the formula. Constructing an RGB channel image with a pixel size [ (X) max -X min )/dL+1]×[(Y max -Y min )/dL+1]And generating a channel orthophoto map by using the pixel RGB values as RGB average values of three-dimensional points in the corresponding grids.
Step S2: image data of a transmission line channel is collected, building and road labels are manufactured, a transmission line ground feature training sample library is established, image multidimensional depth features are extracted from the sample library through a u-net network, feature expression capacity of various ground feature images is improved, a high-precision image recognition model aiming at the transmission line channel images is built on the basis of high-computation GPU as a hardware basis and in combination with a tensor operation calculation mode.
Step S3: coarse extraction is carried out on roads and buildings based on image recognition; in this embodiment, the image recognition model is used to automatically recognize the buildings, roads and towers in the channel orthographic image generated in the step one, and the frame standard range of each category is obtained. And assigning the three-dimensional point category attribute in the grid corresponding to the pixel in the category frame standard range as the type code identified by the image through the one-to-one correspondence between the pixel and the point cloud grid.
Step S4: the roads and the buildings based on the morphological characteristics are finely classified. In this embodiment, based on the rough extraction result in step S3, different classification results set different morphological feature thresholds, and the morphological features of the point set after rough classification are determined and denoised to obtain a fine classification result.
In this embodiment, the definition of each feature is as follows:
building characteristics: the building is divided into inclined roof or flat-topped plane, and the boundary point and the ground have elevation mutation of more than 2 m. Utilizing the pre-classified building point cloud extracted in the step S3, and utilizing a greedy triangular algorithm to construct a triangular network and a topological relation; and further calculating the normal vector of each three-dimensional point in the point cloud, extracting a normal vector change point by utilizing the characteristic of fixed normal vector of the inclined roof or flat roof of the building, comparing the normal vector change point with the adjacent point within 0.5m, and taking the point as a building boundary point when the maximum value of the height difference is more than 2 m. And constructing a convex hull for the extracted boundary points to extract an outer boundary, obtaining the whole outer frame of the building, filtering the points outside the frame, and keeping the points in the frame as building point clouds.
Road characteristics: the road is characterized by a smooth curved surface, and the normal vector is continuous and less than 45 degrees. Utilizing the pre-classified road point cloud extracted in the step S3, and utilizing a greedy triangular algorithm to construct a triangular network and a topological relation; and calculating the normal vector of each three-dimensional point in the point cloud, filtering noise points with the normal vector and the XOY plane included angle being larger than 45 degrees, extracting neighborhood points within 1m of each three-dimensional point, comparing the normal vector, and determining the three-dimensional points with the normal vector included angle being larger than 15 degrees as road boundaries.
It should be noted that any process or method descriptions in flow charts of the present invention or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and that preferred embodiments of the present invention include additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
Finally, it is 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 modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (5)
1. An image identification-assisted power transmission line laser LiDAR point cloud classification method is characterized by comprising the following steps of: the method comprises the following steps:
step S1: performing color point cloud dimension reduction processing to generate a channel orthophoto; the step S1 specifically includes:
in the upper left corner (X) of the point cloud plane coordinate min ,Y max ) Dividing a planar two-dimensional grid along the X axis and the Y axis by using the set grid size dL as a starting point, and setting the plane coordinate value of any point P in the point cloud as (X) P ,Y P ) Then the grid position where it is located is (u) P ,v P )；
Dividing each point in the color point cloud into corresponding grids according to the formula to construct an RGB channel image, wherein the pixel size of the RGB channel image is [ (X) max -X min )/dL+1]×[(Y max -Y min )/dL+1]The pixel RGB is the RGB mean value of the three-dimensional points in the corresponding grid, and a channel orthophoto map is generated;
step S2: establishing a ground object sample library of the power transmission line, and constructing an image recognition model; step S2 is to collect image data of a transmission line channel, make building and road labels, establish a transmission line ground feature training sample library, extract image multidimensional depth features from the sample library through a u-net network, improve feature expression capability of various ground feature images, and build a high-precision image recognition model aiming at the transmission line channel images based on a high-computation GPU as a hardware basis and combining a tensor operation calculation mode;
step S3: coarse extraction is carried out on roads and buildings based on image recognition; step S3 is to automatically identify buildings, roads and towers in the channel orthographic images generated in the step I by using an image identification model, and obtain frame standard ranges of all categories; assigning three-dimensional point category attributes in grids corresponding to pixels in a category frame standard range as type codes identified by the images through one-to-one correspondence between the pixels and the point cloud grids;
step S4: finely classifying roads and buildings based on morphological characteristics; and step S4, setting different morphological feature thresholds according to different classification results based on the rough extraction result of step S3, and judging and denoising morphological features of the point set after rough classification to obtain a fine classification result.
2. The image recognition-assisted power transmission line laser LiDAR point cloud classification method as claimed in claim 1, wherein the method comprises the following steps of: in the step S4, the building characteristics are defined as follows:
building characteristics: the building is divided into inclined roof or flat-top planes, elevation mutation of boundary points and the ground with the height of more than 2m exists, a triangular network is constructed by utilizing the pre-classified building point cloud extracted in the step S3 and a greedy triangular algorithm, and a topological relation is constructed; and further calculating the normal vector of each three-dimensional point in the point cloud, extracting a normal vector change point by utilizing the characteristic of fixed normal vector of the inclined roof or flat roof of the building, comparing the normal vector change point with a neighborhood point within 0.5m, when the maximum value of the height difference is greater than 2m, taking the point as a building boundary point, constructing a convex hull for the extracted boundary point, extracting an outer boundary to obtain an integral outer frame of the building, filtering the points outside the frame, and retaining the points in the frame as the building point cloud.
3. The image recognition-assisted power transmission line laser LiDAR point cloud classification method as claimed in claim 1, wherein the method comprises the following steps of: in the step S4, the definition of the road characteristics is as follows:
road characteristics: the morphological characteristics of the road are a smooth curved surface, normal vectors are continuous and smaller than 45 degrees, a triangular network is constructed by utilizing the pre-classified road point cloud extracted in the step S3 and a greedy triangular algorithm, and a topological relation is constructed; and calculating the normal vector of each three-dimensional point in the point cloud, filtering noise points with the normal vector and the XOY plane included angle being larger than 45 degrees, extracting neighborhood points within 1m of each three-dimensional point, comparing the normal vector, and determining the three-dimensional points with the normal vector included angle being larger than 15 degrees as road boundaries.
4. A computer apparatus comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor, characterized by: the processor, when executing the computer program, implements the method of any one of claims 1 to 3.
5. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program, when executed by a processor, implements a method as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110142298.XA CN112884026B (en) | 2021-02-02 | 2021-02-02 | Image identification-assisted power transmission line laser LiDAR point cloud classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110142298.XA CN112884026B (en) | 2021-02-02 | 2021-02-02 | Image identification-assisted power transmission line laser LiDAR point cloud classification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112884026A CN112884026A (en) | 2021-06-01 |
| CN112884026B true CN112884026B (en) | 2023-05-12 |
Family
ID=76052589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110142298.XA Active CN112884026B (en) | 2021-02-02 | 2021-02-02 | Image identification-assisted power transmission line laser LiDAR point cloud classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112884026B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569914B (en) * | 2021-06-29 | 2024-02-09 | 山东信通电子股份有限公司 | Point cloud data fusion type power transmission line inspection method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9672734B1 (en) * | 2016-04-08 | 2017-06-06 | Sivalogeswaran Ratnasingam | Traffic aware lane determination for human driver and autonomous vehicle driving system |
| CN112013830A (en) * | 2020-08-20 | 2020-12-01 | 中国电建集团贵州电力设计研究院有限公司 | Accurate positioning method for unmanned aerial vehicle inspection image detection defects of power transmission line |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160309065A1 (en) * | 2015-04-15 | 2016-10-20 | Lytro, Inc. | Light guided image plane tiled arrays with dense fiber optic bundles for light-field and high resolution image acquisition |
| CN109977921B (en) * | 2019-04-11 | 2022-02-11 | 广东电网有限责任公司 | Method for detecting hidden danger of power transmission line |
| CN111915662B (en) * | 2019-05-07 | 2024-01-12 | 北京京东乾石科技有限公司 | Three-dimensional laser point cloud data preprocessing method and device |
| CN111507423B (en) * | 2020-04-24 | 2023-06-09 | 国网湖南省电力有限公司 | Engineering quantity measuring method for cleaning transmission line channel |
-
2021
- 2021-02-02 CN CN202110142298.XA patent/CN112884026B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9672734B1 (en) * | 2016-04-08 | 2017-06-06 | Sivalogeswaran Ratnasingam | Traffic aware lane determination for human driver and autonomous vehicle driving system |
| CN112013830A (en) * | 2020-08-20 | 2020-12-01 | 中国电建集团贵州电力设计研究院有限公司 | Accurate positioning method for unmanned aerial vehicle inspection image detection defects of power transmission line |
Non-Patent Citations (1)
| Title |
|---|
| K. Sikorska-Łukasiewicz.Methods of automatic vegetation encroachment detection for high voltage power lines.《Radioelectronic Systems Conference 2019》.2020,1-6. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112884026A (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801022B (en) | Method for rapidly detecting and updating road boundary of unmanned mining card operation area | |
| CN112070769B (en) | Layered point cloud segmentation method based on DBSCAN | |
| CN107767382A (en) | The extraction method and system of static three-dimensional map contour of building line | |
| CN111444821A (en) | Automatic identification method for urban road signs | |
| CN111598916A (en) | Preparation method of indoor occupancy grid map based on RGB-D information | |
| CN108399424B (en) | Point cloud classification method, intelligent terminal and storage medium | |
| CN113920134B (en) | Slope ground point cloud segmentation method and system based on multi-line laser radar | |
| CN111580131A (en) | Method for identifying vehicles on expressway by three-dimensional laser radar intelligent vehicle | |
| CN111783722B (en) | Lane line extraction method of laser point cloud and electronic equipment | |
| CN115797813B (en) | Water environment pollution detection method based on aerial image | |
| CN111915583A (en) | Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene | |
| CN114492619A (en) | Point cloud data set construction method and device based on statistics and concave-convex property | |
| CN111783721A (en) | Lane line extraction method of laser point cloud and electronic equipment | |
| CN116279592A (en) | Method for dividing travelable area of unmanned logistics vehicle | |
| CN112884026B (en) | Image identification-assisted power transmission line laser LiDAR point cloud classification method | |
| EP2677462A1 (en) | Method and apparatus for segmenting object area | |
| CN115272306A (en) | Solar cell panel grid line enhancement method utilizing gradient operation | |
| CN111860084B (en) | Image feature matching and positioning method and device and positioning system | |
| CN116452604A (en) | Complex substation scene segmentation method, device and storage medium | |
| CN116681932A (en) | Object identification method and device, electronic equipment and storage medium | |
| CN114511862B (en) | Form identification method and device and electronic equipment | |
| CN112348950B (en) | Topological map node generation method based on laser point cloud distribution characteristics | |
| CN113095309B (en) | Method for extracting road scene ground marker based on point cloud | |
| Wang et al. | Obstacle recognition method for ship based on 3D lidar | |
| CN117372988B (en) | Road boundary detection 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |