CN112034481B - Automatic cable identification method based on reflective sticker and laser radar - Google Patents
Automatic cable identification method based on reflective sticker and laser radar Download PDFInfo
- Publication number
- CN112034481B CN112034481B CN202010911764.1A CN202010911764A CN112034481B CN 112034481 B CN112034481 B CN 112034481B CN 202010911764 A CN202010911764 A CN 202010911764A CN 112034481 B CN112034481 B CN 112034481B
- Authority
- CN
- China
- Prior art keywords
- point
- reflective
- point cloud
- cable
- laser radar
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000007621 cluster analysis Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000002310 reflectometry Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000009434 installation Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 229910052573 porcelain Inorganic materials 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/021—Optical sensing devices
- B25J19/022—Optical sensing devices using lasers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses an automatic cable identification method based on a reflective sticker and a laser radar, which comprises the following steps: (1) At least one reflective patch is arranged on the target cable, and the laser radar scans the target cable and splices the target cable to obtain point cloud; (2) Performing range filtering and highlight threshold extraction on the spliced point cloud to obtain a point cloud cluster at the position of the reflective sticker; (3) Carrying out statistical filtering and cluster analysis on the point cloud cluster to extract a centroid; (4) Calculating to obtain the mutual distance between the reflective patches according to the step (3); and the distance relation and the branch line communication relation are obtained by combining different cables, and each reflective patch is matched with the corresponding cable, so that the automatic identification of the cable is realized. According to the invention, the reflective patch is used on the target cable in advance, then the identification is carried out through the laser radar, the reflective patch position is used as priori information, automatic calculation and point selection can be rapidly and effectively completed, dependence on manual point selection is eliminated, and the consistency of multiple times of calculation is ensured.
Description
Technical Field
The invention relates to the field of live working robots, in particular to an automatic cable identification method based on a reflective sticker and a laser radar.
Background
The live working robot is a robot capable of carrying out live working on a high-altitude distribution network line, and replaces manual work to finish live working through a remote control strategy. Compared with the traditional manual live working mode, the method has the advantages that personal safety risk is avoided, the working efficiency is doubled, physical isolation between people and electricity is achieved in the whole process, and live working quality and efficiency are effectively improved.
In the aerial operation process of the live working robot, effective perception needs to be achieved on objects such as specific surrounding wires, porcelain bottles and electric poles, a point cloud model of surrounding environment is rapidly and accurately obtained, and support can be provided for a subsequent series of operations. However, when the existing live working robot calculates a main line wire stripping point, two endpoints of the main line and the branch line are manually selected on a point cloud model, and then the main line wire stripping point and the branch line wire grabbing point are calculated according to the selected endpoints serving as priori conditions through an algorithm. The requirement on the accuracy and consistency of manual operation is high, meanwhile, the manual point selection is long in time consumption, and the operation is complex.
Disclosure of Invention
The invention aims to: aiming at the defects, the invention provides an automatic cable identification method based on a reflective sticker and a laser radar, which can lead a live working robot to get rid of dependence on manual operation and complicated flow requirements and quickly and effectively realize automatic calculation and point selection.
The technical scheme is as follows:
a cable automatic identification method based on a reflective sticker and a laser radar comprises the following steps:
(1) At least one reflective sticker is arranged on the target cable, and a laser radar on the live working robot scans the target cable and splices the target cable to obtain corresponding point clouds;
(2) Performing range filtering and highlight threshold extraction on the spliced point cloud obtained by the laser radar in the step (1) to obtain a point cloud cluster at the position of the reflective sticker;
(3) Carrying out statistical filtering and cluster analysis on the point cloud clusters extracted in the step (2) to extract mass centers so as to obtain corresponding effective reflection paste mass centers;
(4) Calculating the mutual distance between the reflective patches according to the effective reflective patch centroid obtained in the step (3); and the distance relation and the branch line communication relation are obtained by combining different cables, and each reflective patch is matched with the corresponding cable, so that the automatic identification of the cable is realized.
The step (2) specifically comprises the following steps:
In the point cloud after the splicing is finished, each point consists of space coordinates and reflectivity, and is specifically expressed as p (x, y, z, intensity) (p epsilon MatchedPoints robot), and then the point cloud data meeting the following formula is extracted to obtain point cloud clusters at the positions of the reflective stickers;
p.x∈(xmin,xmax)
p.y∈(ymin,ymax)
p.z∈(zmin,zmax)
p.intensity>intensitythreshold
Wherein, intensity is reflectivity information, matchedPoints robot represents a spliced point cloud set under a robot coordinate system; (x min,xmax)、(ymin,ymax)、(zmin,zmax) respectively represents the value ranges of the three-axis coordinate values of the point cloud p (x, y, z) under the laser radar coordinate system; intensity threshold represents the highlighting threshold for determining the reflective patch.
The step of cluster analysis in the step (3) is as follows:
1) Finding a certain point p in the space, finding n nearest points kdTree, judging the distance between the n points and the p, and placing the point with the distance smaller than a threshold value r in a class Q;
2) Finding a point in the class Q, and repeating the step 1) until no new point is added in the class Q;
3) Judging whether the point cloud number in class Q is between the set exposure point number thresholds, if so, completing searching; if not, returning to the step 2).
Further comprising the step (5): and (3) the live working robot generates the matching result in the step (4) to the interface for visual display, a user checks the matching result through a visual interface, and if the automatic calculation result is judged to be wrong, the manual intervention can update and recalculate the wrong point until the data is judged to be correct.
The number and the installation position of the reflective patches on each branch line are determined according to actual requirements.
Two reflective stickers are arranged on each branch line and are respectively arranged at the root of each branch line and the line grabbing point, wherein the line grabbing point of each branch line is at the highest radian of each branch line.
The width of the reflective patch is larger than 5cm.
The beneficial effects are that: according to the invention, the reflective paste is used on the target cable in advance, then the identification is carried out through the laser radar, the reflective paste position is used as priori information, automatic calculation of the selected point can be rapidly and effectively completed, time consumption and deviation of multiple interactions are saved, dependence on manual selected points is eliminated, and the consistency of multiple calculations is ensured.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The invention is further elucidated below in connection with the drawings and the specific embodiments.
The laser returns different reflection intensities to objects with different reflectivities, the reflectivity of the black wire is low, and the reflectivity of the reflective patch is high. Therefore, according to the actual working requirements, two reflective stickers can be stuck at the root part and the line grabbing point of each branch line, wherein the root part of each branch line is positioned at the porcelain bottle, and the line grabbing point of each branch line is positioned at the highest radian of each branch line; according to the laser radar system and the method, point cloud data of a target cable are collected by the laser radar on the live working robot, the position of the reflective patch can be automatically extracted according to the difference of reflectivity information, the position of a manual point selection is replaced by the automatically extracted position of the reflective patch, a calculation result is pushed to an interface for visual display, a worker is required to judge whether automatic calculation is correct or not according to the visual result, when the automatic calculation is biased, the worker can select to intervene in a connecting pipe continuing process, manual intervention can delete the automatic point selection data, manual marking of the point selection is performed, and the calculation is performed again. If successful, clicking to confirm is needed, and manual confirmation is added in the step, so that stability is improved.
The width of the reflective patch is larger than 5cm.
The reflective patch used by a single branch line is not limited to two, the specific position is not limited, and the reflective patch can be automatically adjusted according to the requirements and is in the scope of patent protection.
The automatic cable identification method based on the reflective sticker and the laser radar is shown in fig. 1, and comprises the following steps:
(1) Providing at least one reflective patch on the target cable, such as at the root of the branch line and at the line grabbing point; in the invention, the target cable can be single, two or three branch lines;
(2) Scanning a target cable by a laser radar on the live working robot and splicing to obtain a corresponding point cloud;
(3) Performing range filtering and highlight threshold extraction on the point cloud after the laser radar scanning splicing in the step (2) is finished to obtain a point cloud cluster of the position where the reflective patch is positioned;
The method comprises the following steps: in the point cloud after the splicing is finished, each point consists of space coordinates and reflectivity, and is specifically expressed as p (x, y, z, intensity) (p epsilon MatchedPoints robot), and then the point cloud data meeting the following formula is extracted to obtain point cloud clusters at the positions of the reflective stickers;
p.x∈(xmin,xmax)
p.y∈(ymin,ymax)
p.z∈(zmin,zmax)
p.intensity>intensitythreshold
Wherein, intensity is reflectivity information, matchedPoints robot represents a spliced point cloud set under a robot coordinate system; the extracted point p needs to meet a certain range in each dimension of x, y, z and intensity; p.x, p.y and p.z respectively represent three-axis coordinate values of the point cloud p (x, y, z) under the laser radar coordinate system, and (x min,xmax)、(ymin,ymax)、(zmin,zmax) respectively represent the value ranges of the three-axis coordinate values of the point cloud p (x, y, z) under the laser radar coordinate system; intensity threshold represents a highlighting threshold that determines a reflective patch;
(4) Carrying out statistical filtering and cluster analysis on the highlight cloud cluster extracted in the step (3) to extract mass centers so as to obtain a plurality of effective reflective paste mass centers;
Wherein:
The statistical filtering is to perform a statistical analysis on the neighborhood of each point, calculate the average distance of the adjacent points, consider the obtained result to be gaussian distribution, then the shape is determined by the mean value and the standard deviation, and then the point with the average distance outside the standard range is considered as the outlier to be deleted.
The clustering analysis steps were as follows:
1) A point p10 in space is found, and kdTree points closest to the point p are found, and the distances from the n points to the point p are judged. Placing points p12, p13, p14 … with a distance less than the threshold r in class Q;
2) Finding a point p12 in Q (p 10), repeating 1;
3) Finding a point at Q (p 10, p 12), repeating 1, finding p22, p23, p24 …, and putting all into Q;
4) When Q can not be added with new points any more, the search is completed. Meanwhile, the number of the point cloud in Q is required to be between the set maximum and minimum numbers.
(5) Calculating a coordinate of each reflection patch centroid under a laser radar coordinate system and a mutual distance between each reflection patch according to the plurality of effective reflection patch centroids obtained in the step (4);
(6) And (3) combining the coordinates of the mass centers of the reflective patches obtained in the step (5) under a laser radar coordinate system, the mutual distance between the reflective patches, the distance relation between different cables and the branch line communication relation, matching the reflective patches with the corresponding cables, and entering a calculation flow for calculating branch line grabbing points and main line stripping points.
(7) And (3) the live working robot generates the matching result in the step (6) to the interface for visual display, a user checks the matching result through a visual interface, and if the automatic calculation result is judged to be wrong, the manual intervention can update and recalculate the wrong point until the data is judged to be correct. The calculation result provides data support for the subsequent branch line grabbing and stripping actions.
The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific details of the above embodiments, and various equivalent changes (such as number, shape, position, etc.) may be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and these equivalent changes all fall within the scope of the present invention.
Claims (5)
1. A cable automatic identification method based on a reflective sticker and a laser radar is characterized by comprising the following steps: the method comprises the following steps:
(1) At least one reflective sticker is arranged on the target cable, and a laser radar on the live working robot scans the target cable and splices the target cable to obtain corresponding point clouds;
(2) Performing range filtering and highlight threshold extraction on the spliced point cloud obtained by the laser radar in the step (1) to obtain a point cloud cluster at the position of the reflective sticker;
In the spliced point cloud, each point consists of space coordinates and reflectivity, and is specifically expressed as p (x, y, z, intensity), p is MatchedPoints robot, and then point cloud data meeting the following requirements are extracted to obtain point cloud clouds at the position of the reflective sticker;
p.x∈(xmin,xmax)
p.y∈(ymin,ymax)
p.z∈(zmin,zmax)
p.intensity>intensitythreshold
Wherein, intensity is reflectivity information, matchedPoints robot represents a spliced point cloud set under a robot coordinate system; (x min,xmax)、(ymin,ymax)、(zmin,zmax) respectively represents the value ranges of the three-axis coordinate values of the point cloud p (x, y, z) under the laser radar coordinate system; intensity threshold represents a highlighting threshold that determines a reflective patch;
(3) Carrying out statistical filtering and cluster analysis on the point cloud clusters extracted in the step (2) to extract mass centers so as to obtain corresponding effective reflection paste mass centers;
The statistical filtering is to perform a statistical analysis on the neighborhood of each point, calculate to obtain the average distance of the adjacent points, the distribution of the distance is Gaussian distribution, and delete the points with the average distance outside the standard range as outliers;
The cluster analysis steps are as follows:
1) Finding a certain point p in the space, finding n nearest points kdTree, judging the distance between the n points and the p, and placing the point with the distance smaller than a threshold value r in a class Q;
2) Finding a point in the class Q, and repeating the step 1) until no new point is added in the class Q;
3) Judging whether the point cloud number in class Q is between the set exposure point number thresholds, if so, completing searching; if not, returning to the step 2);
(4) Calculating the mutual distance between the reflective patches according to the effective reflective patch centroid obtained in the step (3); and the distance relation and the branch line communication relation are obtained by combining different cables, and each reflective patch is matched with the corresponding cable, so that the automatic identification of the cable is realized.
2. The automatic cable identification method of claim 1, wherein: further comprising the step (5): and (3) the live working robot generates the matching result in the step (4) to the interface for visual display, a user checks the matching result through the visual interface, and if the automatic calculation result is judged to be wrong, the manual intervention is performed again to update and recalculate the wrong point until the data is judged to be correct.
3. The automatic cable identification method of claim 1, wherein: the number and the installation position of the reflective patches on each branch line are determined according to actual requirements.
4. The automatic cable identification method of claim 1, wherein: two reflective stickers are arranged on each branch line and are respectively arranged at the root of each branch line and the line grabbing point, wherein the line grabbing point of each branch line is at the highest radian of each branch line.
5. The automatic cable identification method of claim 1, wherein: the width of the reflective patch is larger than 5cm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010911764.1A CN112034481B (en) | 2020-09-02 | 2020-09-02 | Automatic cable identification method based on reflective sticker and laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010911764.1A CN112034481B (en) | 2020-09-02 | 2020-09-02 | Automatic cable identification method based on reflective sticker and laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112034481A CN112034481A (en) | 2020-12-04 |
| CN112034481B true CN112034481B (en) | 2024-08-02 |
Family
ID=73591281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010911764.1A Active CN112034481B (en) | 2020-09-02 | 2020-09-02 | Automatic cable identification method based on reflective sticker and laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112034481B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117751301A (en) * | 2021-08-27 | 2024-03-22 | 深圳市速腾聚创科技有限公司 | Method, device, equipment and storage medium for processing laser radar point cloud |
| CN114494020B (en) * | 2022-02-15 | 2024-07-16 | 国网江苏省电力工程咨询有限公司 | Data splicing method for cable channel point cloud data |
| CN116787466B (en) * | 2023-08-21 | 2023-11-07 | 福建大观电子科技有限公司 | Insulation sleeve-based drainage wire identification method, storage medium and robot |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157361A (en) * | 2016-05-31 | 2016-11-23 | 中国科学院遥感与数字地球研究所 | A kind of multiple fission conductor full-automatic three-dimensional method for reconstructing based on LiDAR point cloud |
| CN110793512A (en) * | 2019-09-11 | 2020-02-14 | 上海宾通智能科技有限公司 | Pose recognition method and device, electronic equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201084488Y (en) * | 2007-07-09 | 2008-07-09 | 江苏泛亚电缆有限公司 | Lighting cable |
| KR101404655B1 (en) * | 2014-04-18 | 2014-06-09 | 국방과학연구소 | Power line extraction using eigenvalues ratio of 3d raw data of laser radar |
| CN104732588B (en) * | 2015-03-30 | 2016-06-01 | 中国测绘科学研究院 | A kind of power line three-dimensional rebuilding method based on airborne laser radar point cloud |
| JP6751732B2 (en) * | 2018-03-12 | 2020-09-09 | 日本電信電話株式会社 | Equipment condition diagnosis device, equipment condition diagnosis method and its program, equipment condition display method |
| TWI690439B (en) * | 2018-11-01 | 2020-04-11 | 財團法人車輛研究測試中心 | Lane stripe detecting method based on three-dimensional lidar and system thereof |
| CN111369779B (en) * | 2018-12-26 | 2021-09-03 | 北京图森智途科技有限公司 | Accurate parking method, equipment and system for truck in shore crane area |
-
2020
- 2020-09-02 CN CN202010911764.1A patent/CN112034481B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157361A (en) * | 2016-05-31 | 2016-11-23 | 中国科学院遥感与数字地球研究所 | A kind of multiple fission conductor full-automatic three-dimensional method for reconstructing based on LiDAR point cloud |
| CN110793512A (en) * | 2019-09-11 | 2020-02-14 | 上海宾通智能科技有限公司 | Pose recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112034481A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112034481B (en) | Automatic cable identification method based on reflective sticker and laser radar | |
| CN111340317B (en) | Automatic early warning method for tree obstacle hidden danger of overhead transmission line and electronic equipment | |
| CN112034470B (en) | Cable identification and positioning method based on solid-state area array laser radar | |
| CN112700497B (en) | Loop detection method, device, equipment and computer readable storage medium | |
| CN112733839A (en) | Method and device for determining position of lamp holder, storage medium, program, and road side device | |
| KR20230043754A (en) | Positioning method and apparatus, device, system, medium and self-driving vehicle | |
| CN114842187A (en) | Tea tender shoot picking point positioning method based on fusion of thermal image and RGB image | |
| CN114140592A (en) | High-precision map generation method, device, equipment, medium and automatic driving vehicle | |
| CN113052761B (en) | Laser point cloud map fusion method, device and computer readable storage medium | |
| CN114386674A (en) | Power transmission line tree lodging dynamic risk early warning method and system | |
| CN115609587A (en) | Target following method, device, equipment and storage medium | |
| CN114547227A (en) | Ant colony and A-Star algorithm parallel grid map path planning method | |
| CN111179428A (en) | Ground object manufacturing method and device based on locking plane | |
| CN114782357A (en) | Self-adaptive segmentation system and method for transformer substation scene | |
| CN117516513A (en) | Intelligent mower path planning method, device, equipment and storage medium | |
| CN112558091A (en) | Real-time detection method and device for spatial distance of power transmission line to tree and terminal equipment | |
| CN113997292B (en) | Operation method of mechanical arm based on machine vision, medium and electronic equipment | |
| CN112008730B (en) | Sun position identification and avoidance method based on solid-state area array laser radar | |
| CN115239178A (en) | Rural low-voltage distribution type photovoltaic site selection and volume fixing method, system and medium | |
| CN115356706A (en) | Power transmission line progress confirmation method based on BIM information and laser point cloud data | |
| CN112085036A (en) | Region identification method, device, equipment and medium | |
| CN112053365B (en) | Method for extracting laser point cloud data of power transmission line conductor based on linear characteristics | |
| CN113223155A (en) | Distance prediction method, device, equipment and medium | |
| CN112669387A (en) | Method and device for determining position of lamp holder, storage medium, program, and road side device | |
| CN114431018B (en) | Tree obstacle clearing method, device and system |
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 |