Abstract
In recent years, machine vision detection technology has been widely used in various fields, and deep learning, as an emerging visual detection technology, has shown excellent detection performance. In this paper, aiming at the bolt fastening end operation device of the live working robot on the transmission line, the visual detection algorithm is studied to improve the efficiency of the robot operation. In view of the poor robustness and high false detection rate of the visual detection algorithm designed by Hough and SVM, it is proposed to use the Faster R-CNN network with leading performance in deep learning to design the bolt detection algorithm. The size of bolts appearing in the camera is analyzed, and suitable RPN parameters are proposed. Aiming at the problem that the network model cannot be fitted due to insufficient samples, a sample expansion method is proposed to increase the number of samples. Finally, the bolt detection network is obtained through joint training. Experiments prove that the designed Faster R-CNN detection algorithm can effectively detect bolts, greatly improving the efficiency of robot operations, and has broad application prospects.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.