Translator Disclaimer
8 February 2019 Missing pins detection for power equipment firmware using unmanned aerial vehicle images
Author Affiliations +
Proceedings Volume 10843, 9th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices for Sensing and Imaging; 108430S (2019) https://doi.org/10.1117/12.2506338
Event: Ninth International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT2018), 2018, Chengdu, China
Abstract
Maintenance of power equipment is of great significance to ensure the safety and reliability of power equipment. This paper focuses on detecting missing pins of power equipment using Unmanned Aerial Vehicle (UAV) acquired images. We proposed a detection method based on image color histogram and scale invariant feature transform (SIFT). The first step calculates the H-S color histogram of screw image, utilizing histogram back projection method to obtain candidate regions of screw image in the to-be-matched image, applied Bhattacharyya distance as a measurement to compare the similarity of two histograms. Then, the SIFT feature is extracted from the screw image and the key points are matched with the SIFT feature of the candidate regions to detect the screws. Finally, this paper designs a method which uses convolutional neural network to judge whether the screw misses the pin. Experiments show that the proposed algorithm of missing pins detection based on UAV image can achieve competitive results to detect the defects in special scenes, and has good robustness, which satisfies the real-time and accuracy requirements.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bingxin Huai, Ruiling Wang, Yuhan Liu, Li Song, and Zhenming Peng "Missing pins detection for power equipment firmware using unmanned aerial vehicle images", Proc. SPIE 10843, 9th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices for Sensing and Imaging, 108430S (8 February 2019); https://doi.org/10.1117/12.2506338
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top