The condition of railway tracks needs to be periodically monitored to ensure passenger safety. Cameras mounted on a moving vehicle such as a hi-rail can generate large volumes of high-resolution images. Extracting accurate information from those images has been challenging due to the clutter in the railroad environment. In this paper, we describe a novel approach to visual track inspection using semantic segmentation using BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation.
This project implements rail-track detection using fast semantic segmentation for high-resolution images from bisenetv2 algorithm.
This project trains bisenetv2 on a modified version of RailSem19 dataset with only three labels ("rail-raised", "rail-track", "background"). Please follow here if you want to download the original dataset.
Dataset:
In this paper, we introduce the first public dataset for semantic scene understanding for trains and trams: RailSem19. This dataset consists of 8500 annotated short sequences from the ego-perspective of trains, including over 1000 examples with railway crossings and 1200 tram scenes. Since it is the first image dataset targeting the rail domain, a novel label policy has been designed from scratch. It focuses on rail-specific labels not covered by any other datasets. In addition to manual annotations in the form of geometric shapes, we also supply dense pixel-wise semantic labeling. The dense labeling is a semantic-aware combination of (a) the geometric shapes and (b) weakly supervised annotations generated by existing semantic segmentation networks from the road domain. Finally, multiple experiments give a first impression on how the new dataset can be used to improve semantic scene understanding in the rail environment. We present prototypes for the image-based classification of trains, switches, switch states, platforms, buffer stops, rail traffic signs and rail traffic lights.
Comments