Context-guided coarse-to-fine detection model for bird nest detection on high-speed railway catenary

Abstract As a critical component of ensuring the safe and stable operation trains, detection bird’s nests on rail catenary has always been essential. Low-resolution images lack labelled data, however, make it difficult to detect smaller (those occupying small pixels in input image). Previous solution relies manual online patrol or offline video playback, which severely limits efficiency. Previously, this challenge was addressed by We propose work context-guided coarse-to-fine model (CG-CFDM) for solving nest problem. This consists context reasoning module network. By detecting domains matching templates, generates new bounding boxes, thereby reducing burden annotation. result its delicately designed architecture powerful representation learning ability, trained network further facilitates an efficient accurate manner. Extensive experiments demonstrate that proposed approach is superior existing methods terms performance great deal potential nests.