Image classification towards transmission line fault detection via learning deep quality-aware fine-grained categorization

Abstract Object detection and image classification are basic tasks in computer vision. In this paper, we introduce fault detection towards transmission line. Traditional fault detection methods in the transmission line are prone to be affected by the noise and transient magnitude. To overcome these limitations, we propose a novel fault zone detection method, where quality-aware fine-grained categorization model is well encoded for category cues discovery. The goal of our approach is to recognize the most discriminative image patches for classification. The key techniques of our method include quality-based discriminative feature extraction and wavelet-support vector machine. We extract the features of the line currents by leveraging Fast R-CNN based image samples decomposition, where quality module is utilized to choose the most discriminative regions. Afterwards, the extracted features are fed into a SVM to recognize the fault. We conduct comprehensive experiment on transmission line fault identification to verify the availability and superiority of our proposed method.