CN110579170A - valve hall infrared inspection robot positioning system - Google Patents
valve hall infrared inspection robot positioning system Download PDFInfo
- Publication number
- CN110579170A CN110579170A CN201910730462.1A CN201910730462A CN110579170A CN 110579170 A CN110579170 A CN 110579170A CN 201910730462 A CN201910730462 A CN 201910730462A CN 110579170 A CN110579170 A CN 110579170A
- Authority
- CN
- China
- Prior art keywords
- module
- robot
- image feature
- inspection robot
- data processing
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a valve hall infrared inspection robot positioning system, which comprises: the vision sensor is arranged on the robot and is electrically connected with the robot control machine; the method is characterized in that: the robot manual control machine is provided with an image feature extraction module, an image feature matching module, a data processing module and an output module; the image feature matching module is electrically connected with the image feature extraction module and the data processing module respectively; the data processing module is electrically connected with the output module. The invention ensures that the inspection robot is not limited by a fixed route, and the inspection robot can complete the positioning of the inspection robot no matter at any position.
Description
Technical Field
The invention relates to the field of positioning systems, in particular to a positioning system of an infrared inspection robot for a valve hall.
Background
The converter station is a station established in a high-voltage direct-current transmission system for completing the conversion between alternating current and direct current and meeting the requirements of a power system on safety, stability and power quality, a valve hall is a closed building of a discharge and replacement valve in the converter station and is a core part of the converter station, and the operation state of the converter station is directly related to the stable operation of the whole power system.
Along with the development in the field of power inspection, conventional manual inspection is gradually replaced by an inspection robot, the inspection robot needs to know the specific position of the inspection robot when the inspection is performed, and the robot can conveniently reach the specified point position to inspect and accurately position the fault point when the inspection is performed.
At present, the conventional inspection mode has methods such as RFID label and track positioning, but has the problems of expensive equipment, positioning precision and the like.
Disclosure of Invention
the invention mainly solves the problems in the prior art and provides a robot positioning system which is low in cost, accurate in positioning and not limited by a fixed route.
the invention is realized by the following technologies:
The utility model provides an infrared robot positioning system that patrols and examines in valve room, includes: the vision sensor is arranged on the robot and is electrically connected with the robot control machine; the robot manual control machine is provided with an image feature extraction module, an image feature matching module, a data processing module and an output module; the image feature matching module is electrically connected with the image feature extraction module and the data processing module respectively; the data processing module is electrically connected with the output module.
Further, the vision sensor employs a depth camera.
Further, the feature points extracted by the image feature extraction module are SIFT, SURF or ORB feature points.
The working process of the invention is as follows: the method comprises the following steps that a visual sensor collects an environment image, the environment image is transmitted to an image feature extraction module, and ORB feature points are extracted from the image; then, an image feature matching module performs image matching on two adjacent frames of images to obtain two groups of well matched point sets; and through the data processing module, the position and posture change of the camera between two frames of images is obtained through iterative calculation of the two groups of point sets, and then the positions and postures of the camera relative to the original point at present are obtained through accumulating the calculated positions and postures between the continuous images and outputting the accumulated positions and postures.
The invention has the beneficial effects that:
1. The inspection robot is not limited by a fixed route, and can complete the positioning of the inspection robot no matter at any position;
2. The visual sensor adopts a depth camera, and compared with a monocular camera, an image acquired by the depth camera comprises a color image and a depth image, and the depth image comprises information of depth information of corresponding pixel points in the color image.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
reference signs mean: 1. a vision sensor; 2. a robot manual controller; 201. an image feature extraction module; 202. an image feature matching module; 203. a data processing module; 204. and an output module.
Detailed Description
The technical solution of the present invention is further explained below with reference to the drawings and the embodiments.
As shown in fig. 1, a valve hall infrared inspection robot positioning system includes: the vision sensor 1 is arranged on the robot, and the vision sensor 1 is electrically connected with the robot control machine 2; the robot control machine 2 is provided with an image feature extraction module 201, an image feature matching module 202, a data processing module 203 and an output module 204; the image feature matching module 202 is electrically connected with the image feature extraction module 201 and the data processing module 203 respectively; the data processing module 203 is electrically connected to the output module 204.
The vision sensor 1 employs a Kinect depth camera.
the robot manual control machine 2 adopts an MIO-5272U-U6A1E industrial control machine.
the feature points extracted by the image feature extraction module 201 are ORB feature points.
the working process of the invention is as follows:
When the inspection robot moves, the vision sensor 1 collects an environment image having depth information, and transmits the environment image to the image feature extraction module 201.
The ORB characteristic points of the environment image are extracted in the following acquisition mode: selecting a pixel point P in the image, setting a threshold value a on the assumption that the pixel value is I, selecting 16 pixel points on a circle with the radius of 3 and the pixel point P as the center, and if the pixel value of continuous N points in the 16 pixel points is greater than I + a or less than I-a, determining the current pixel point P as a characteristic point. The characteristic points in the image can be extracted by executing the operation on each pixel point.
then, in the image feature matching module 202, a fast approximate nearest neighbor algorithm (FLANN) is used to perform image matching on two adjacent frames of images, so as to obtain two sets of well-matched point sets.
Because a Kinect depth camera is used, the matched point pairs are two 3D coordinates, an ICP algorithm is used in the data processing module 203 to solve the motion estimation problem between the matched two groups of points, the solution result is the motion relationship of the camera between two frames of images, and the ICP algorithm solution formula is as follows:
Error for defining the ith 3D match point:
ei＝pi-(Rpi+t)
In the formula, e is the solution erroriFor the point of the previous image, piAnd (3) matching points corresponding to adjacent images, wherein R and t are camera pose transformation matrixes to be solved, R is a rotation matrix, and t is a translation matrix.
constructing a least square problem for n matching points of two frames of images, solving to enable the sum of squares of errors to reach R and t which are extremely small, wherein the extremely small threshold can be set by self:
The solution formula derived by derivation is as follows:
Defining a matrix:
wherein q isiAnd q'iFor the centroid-removed coordinates of this point, the calculation is as follows:
Then carrying out SVD on the W matrix:
W＝U∑VT
solving to obtain R, t is:
R＝UVT
And calculating to obtain R which is a rotation matrix, namely the rotation relation of the camera relative to three coordinate axes between two frames of images, and t which is a translation matrix, namely the translation amount of the camera in the X, Y and Z directions.
by adding the obtained t, the coordinate t of the current camera, namely the inspection robot relative to the initial coordinate system can be obtainedsIf t at each time is to besThe moving track of the camera from the initial position, namely the moving track of the inspection robot, can be obtained.
The obtained moving track is output to the inspection robot and a computer of the convertor station through the output module 304, and the inspection robot and the staff can obtain the position information of the inspection robot in real time.
The above embodiments are only for illustrating the technical concept and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention accordingly, and not to limit the protection scope of the present invention accordingly. All equivalent changes or modifications made in accordance with the spirit of the present disclosure are intended to be covered by the scope of the present disclosure.
Claims (3)
1. The utility model provides an infrared robot positioning system that patrols and examines in valve room, includes: the vision sensor and the robot control machine are arranged on the robot, and the vision sensor is electrically connected with the robot control machine; the method is characterized in that: the robot manual control machine is provided with an image feature extraction module, an image feature matching module, a data processing module and an output module; the image feature matching module is electrically connected with the image feature extraction module and the data processing module respectively; the data processing module is electrically connected with the output module.
2. The infrared inspection robot positioning system of the valve hall according to claim 1, characterized in that: the vision sensor employs a depth camera.
3. The infrared inspection robot positioning system of the valve hall according to claim 1, characterized in that: the feature points extracted by the image feature extraction module are SIFT, SURF or ORB feature points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730462.1A CN110579170A (en) | 2019-08-08 | 2019-08-08 | valve hall infrared inspection robot positioning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730462.1A CN110579170A (en) | 2019-08-08 | 2019-08-08 | valve hall infrared inspection robot positioning system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110579170A true CN110579170A (en) | 2019-12-17 |
Family
ID=68810891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910730462.1A Pending CN110579170A (en) | 2019-08-08 | 2019-08-08 | valve hall infrared inspection robot positioning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110579170A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8564657B2 (en) * | 2009-05-29 | 2013-10-22 | Honda Research Institute Europe Gmbh | Object motion detection system based on combining 3D warping techniques and a proper object motion detection |
| CN108133486A (en) * | 2018-05-03 | 2018-06-08 | 常州市盈能电气有限公司 | Crusing robot displacement distance computational methods |
| CN108839056A (en) * | 2018-06-25 | 2018-11-20 | 盐城工学院 | A kind of robot method for tracing and follow-up mechanism |
| CN108908344A (en) * | 2018-08-17 | 2018-11-30 | 云南电网有限责任公司昆明供电局 | A kind of crusing robot mechanical arm tail end space-location method |
| CN109300161A (en) * | 2018-10-24 | 2019-02-01 | 四川阿泰因机器人智能装备有限公司 | A kind of localization method and device based on binocular vision |
| CN110579187A (en) * | 2019-08-26 | 2019-12-17 | 武汉光迅科技股份有限公司 | Information determination method, electronic equipment and computer readable storage medium |
-
2019
- 2019-08-08 CN CN201910730462.1A patent/CN110579170A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8564657B2 (en) * | 2009-05-29 | 2013-10-22 | Honda Research Institute Europe Gmbh | Object motion detection system based on combining 3D warping techniques and a proper object motion detection |
| CN108133486A (en) * | 2018-05-03 | 2018-06-08 | 常州市盈能电气有限公司 | Crusing robot displacement distance computational methods |
| CN108839056A (en) * | 2018-06-25 | 2018-11-20 | 盐城工学院 | A kind of robot method for tracing and follow-up mechanism |
| CN108908344A (en) * | 2018-08-17 | 2018-11-30 | 云南电网有限责任公司昆明供电局 | A kind of crusing robot mechanical arm tail end space-location method |
| CN109300161A (en) * | 2018-10-24 | 2019-02-01 | 四川阿泰因机器人智能装备有限公司 | A kind of localization method and device based on binocular vision |
| CN110579187A (en) * | 2019-08-26 | 2019-12-17 | 武汉光迅科技股份有限公司 | Information determination method, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈劭 等: "移动机器人ＲGB-D视觉SLAM算法", 《农业机械学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107186708B (en) | Hand-eye servo robot grabbing system and method based on deep learning image segmentation technology | |
| CN105729468B (en) | A kind of robotic workstation based on the enhancing of more depth cameras | |
| Jiang et al. | An overview of hand-eye calibration | |
| CN111243017B (en) | Intelligent robot grabbing method based on 3D vision | |
| CN107662195A (en) | A kind of mechanical hand principal and subordinate isomery remote operating control system and control method with telepresenc | |
| CN107030693B (en) | A kind of hot line robot method for tracking target based on binocular vision | |
| CN105234943A (en) | Industrial robot demonstration device and method based on visual recognition | |
| CN113450408A (en) | Irregular object pose estimation method and device based on depth camera | |
| CN113284179B (en) | Robot multi-object sorting method based on deep learning | |
| CN110136211A (en) | A kind of workpiece localization method and system based on active binocular vision technology | |
| CN113103235B (en) | Method for vertically operating cabinet surface equipment based on RGB-D image | |
| CN109465830B (en) | Robot monocular stereoscopic vision calibration system and method | |
| CN111360821A (en) | Picking control method, device and equipment and computer scale storage medium | |
| CN113379849A (en) | Robot autonomous recognition intelligent grabbing method and system based on depth camera | |
| CN112372641B (en) | Household service robot character grabbing method based on visual feedforward and visual feedback | |
| CN112288815A (en) | Target mode position measuring method, system, storage medium and equipment | |
| CN114474056A (en) | Grabbing operation-oriented monocular vision high-precision target positioning method | |
| CN114299039B (en) | Robot and collision detection device and method thereof | |
| CN115042175A (en) | Method for adjusting tail end posture of mechanical arm of robot | |
| Sheng et al. | Mobile robot localization and map building based on laser ranging and PTAM | |
| Vo et al. | Development of Multi-Robotic Arm System for Sorting System Using Computer Vision | |
| CN110579170A (en) | valve hall infrared inspection robot positioning system | |
| CN115194774A (en) | Binocular vision-based control method for double-mechanical-arm gripping system | |
| CN113920191A (en) | 6D data set construction method based on depth camera | |
| CN114217280A (en) | Calibration method for external parameters of external rotary two-dimensional laser radar |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191217 |