Directional-Aware Automatic Defect Detection in High-Speed Railway Catenary System

It is crucial to detect the defect objects that could be a hidden danger in high-speed catenary system. Instead of detecting objects based on horizontal rectangle, we propose an end-to-end trainable directional-aware defect detection network (D3-Net) which can automatic select the defective components. D3-Net is composed of two streams, including a directional-aware locator that regresses an inclined rectangle and a channel-wise classifier to diagnose the defects of object. Specifically, we make full use of the directionality characteristic of the man-made objects in the localization stream, which can predict the inclined rectangle with an angle parameter. Besides, we introduce a channel attention module (CAM) in the classification stream to obtain discriminative features for better distinguishing the normal and defective objects. Experimental results on two datasets, Dropper and Insulator, demonstrate that our proposed model outperforms the traditional horizontal detection methods.