Feature fusion based insulator detection for aerial inspection

This paper presents a detection method of insulator stings for aerial inspection based on feature-fusion. The local sub-images of insulator strings are firstly collected from aerial videos and tagged to establish a training dataset. The fusion feature is then composed by the histogram of oriented gradients (HOG) feature and local binary pattern (LBP) feature after the principal component analysis (PCA) dimension reduction separately. A training model is developed by SVM algorithm with the fusion feature. At the detection phase, threshold segmentation and morphological operation are adopted to preprocess the images. The sliding window method is then used to search the candidate region and the non-maximum suppression (NMS) method is adopted to fuse the candidate windows. Finally, the position of the insulator strings can be calculated by linear fitting. Both the efficiency and the effectiveness of the proposed method are verified through experiments on locating the multi-angle insulator strings under complex backgrounds.