Automatic defect detection based on improved Faster RCNN for substation equipment. (May 2020)

• Record Type: Journal Article
• Authors: Shouguo, Lv; Liu, Kai; Qiao, Yaohua; Wang, Qi; Yang, Sun; Li, Zhenyu
• Is Part Of: Journal of physics. Volume 1544(2020)
• Publication Date: 2020-05
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1544/1/012157
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Defect detection methods based on machine learning extremely accelerate the substation routine inspection process. In this paper, we propose an automatic defect detection method based on improved Faster RCNN. For one thing, random feature pyramid (RFP) structure is introduced for the highly discriminative feature map construction; for another thing, we execute the detection boxes selection by soft non-maximum suppression (SNMS), keeping the detection of defects which distribute densely. Finally, online hard example mining (OHEM) is employed to deal with the imbalance problem. Experimental results demonstrate that the proposed approach obtains competitive performance compared with state-of-the-art deep learning object detection methods.