Insulator Detection in Aerial Images Based on Faster Regions with Convolutional Neural Network

With the widely application of Unmanned Aerial Vehicle (UAV) in transmission lines inspection, the aerial images taken by UAVs can be utilized to detect insulator and its fault for further maintenance. In this paper, we propose a detection method for insulator and its fault based on Faster Regions with Convolutional Neural Network (Faster R-CNN). The proposed method contains a convolutional network followed by a region proposal network and a object detector. The results show that the proposed method can realize effective detection of insulators and achieve a precision of 94% and a recall of 88% on the testing dataset. Additionally, the computation cost of the proposed method meets the requirements of real-time detection.