A Vision-based Solution for Track Misalignment Detection
Derailment is one of the most frequent ways railway accidents happen. Track defects such as buckling and hogging that cause misalignment of tracks can easily lead to derailments. While railway tracks get laterally misaligned due to buckling, vertical misalignments can result from hogging. Such misalignments are visibly recognizable, and we can even automate the recognition using data-driven models. This paper discusses how we build such data-driven models. There are no public datasets available to build such models; therefore, we introduce TMD (Track Misalignment Detection) dataset. It consists of misaligned and normal track images. The problem we try to solve here is essentially a binary image classification problem, which we solve by exploring the feature extraction approach to transfer learning (TL). In this approach, we employ a pre-trained network to extract rich features, which are then supplied with annotations to a learning algorithm for building a candidate TL model. Several pre-trained networks and learning algorithms exist, resulting in many TL models; therefore, it becomes essential to identify effective ones. We propose an evaluation criterion to decide which are effective ones even before we test them. Our experiments demonstrate that the TL models selected based on our proposed evaluation criterion really perform better than other candidate TL models during testing.