Path edge recognition method and system for a crane metal structure climbing robot
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of metal structures and robots, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of low recognition accuracy
Active Publication Date: 2021-06-04
WUHAN UNIV OF TECH
View PDF2 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] In view of this, the present invention provides a path edge recognition method and system for a crane metal structure climbing robot to solve or at least partially solve the technical problem of low recognition accuracy in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0084] This embodiment provides a path edge recognition method for a crane metal structure climbing robot, please refer to figure 1 , the method includes:
[0085] Step S1: Preprocessing the path image collected by the robot CMOS camera to obtain a grayscale image of the path.
[0086] Specifically, the camera carried by the climbing robot used to lift heavy metal structures can acquire path images, and then preprocess the acquired images to facilitate the identification of subsequent path edges.
[0087] Step S2: Use the line segmentation detection algorithm to detect the path grayscale image, detect all the straight line segments satisfying the constraint rules in the path image, and obtain the straight line segment detection image.
[0088] Specifically, the line segmentation detection algorithm is the straight line segment detection algorithm LSD. The present invention adopts the improved line segment detection algorithm, sets the constraint rules in advance, and then use...
Embodiment 2
[0162] This embodiment provides a path edge recognition system for a crane metal structure climbing robot, please refer to Figure 8 , the system consists of:
[0163] The preprocessing module 201 is used to preprocess the path image collected by the robot CMOS camera to obtain a path grayscale image;
[0164] The line segmentation detection module 202 is used to detect the grayscale image of the path by using the line segmentation detection algorithm, detect all the straight line segments satisfying the constraint rules in the path image, and obtain the straight line segment detection image;
[0165] The clustering module 203 is used to perform feature extraction on the straight line segment detection image including all straight line segments, as a clustering sample, the nearest neighbor propagation clustering algorithm is used for clustering operation, and the straight line segments constituting the edge of the path are screened out;
[0166] The fitting module 204 is conf...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a path edge recognition method and system for a crane metal structure climbing robot. First, the path image collected by the robot CMOS camera is preprocessed to obtain the path grayscale image; The path grayscale image is detected, and all straight line segments satisfying the constraint rules in the path image are detected, and the straight line segment detection image is obtained; then, feature extraction is performed on the straight line segment detection image including all straight line segments, and based on the extracted features, the nearest neighbor propagation clustering is used The algorithm performs a clustering operation and screens out the straight line segments that constitute the edge of the path; finally, for all the selected straight line segments that constitute the edge of the path, the coordinates of the endpoints are extracted as the fitting points, and the least square method is used for fitting, and the fitted straight line The segment is used as the final identified path edge line. The invention realizes the technical effect of improving the accuracy of straight line segment clustering and edge path identification.
Description
technical field [0001] The invention relates to the technical field of machine vision, in particular to a path edge recognition method and system for a crane metal structure climbing robot. Background technique [0002] For large hoisting machinery, the defect detection of metal structures is related to the normal operation and safety of the equipment. At present, the defect detection of metal structures of hoisting machinery at home and abroad mainly relies on manual climbing, which is risky and inefficient. Therefore, the development of a climbing robot suitable for the detection of metal structure defects in large-scale hoisting machinery can effectively reduce the risk of maintenance, maintenance, and inspection of hoisting machinery and improve work efficiency. [0003] Path edge recognition of climbing robots is mainly used in structured paths such as metal structures of lifting machinery. At present, common structured path edge recognition includes highway lane line...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more