Abstract
Power transmission line icing (PTLI) problems, which cause tremendous damage to the power grids, has drawn much attention. Existing three-dimensional measurement methods based on binocular stereo vision was recently introduced to measure the ice thickness in PTLI, but failed to meet requirements of practical applications due to inefficient keypoint matching in the complex PTLI scene. In this paper, a new keypoint matching method is proposed based on the local multi-layer convolutional neural network (CNN) features, termed Local Convolutional Features (LCFs). LCFs are deployed to extract more discriminative features than the conventional CNNs. Particularly in LCFs, a multi-layer features fusion scheme is exploited to boost the matching performance. Together with a location constraint method, the correspondence of neighboring keypoints is further refined. Our approach achieves 1.5%, 5.3%, 13.1%, 27.3% improvement in the average matching precision compared with SIFT, SURF, ORB and MatchNet on the public Middlebury dataset, and the measurement accuracy of ice thickness can reach 90.9% compared with manual measurement on the collected PTLI dataset.
Highlights
The development of the smart grid makes higher demands on power transmission line design, operation, and maintenance
To extract the robust and internal features, we introduce a novel multi-scale feature description method based on local convolutional features
This paper proposes a new keypoint matching method based on the local convolutional features
Summary
The development of the smart grid makes higher demands on power transmission line design, operation, and maintenance. An effective power transmission line icing (PTLI) monitoring and predictive alarm system is critical to ensure power grid safety. To this end, some traditional PTLI monitoring methods have been widely used, such as artificial inspection [1], installing pressure sensors [2], building meteorological models [3,4] and so on. The ice thickness can be calculated through the ratio of pixel widths between edges in normal and icing situations These algorithms have poor performance under complex context or low visibility conditions. This 2D estimation method cannot obtain the comprehensive information of icing.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
