Local and Global Information in Obstacle Detection on Railway Tracks

TL;DR

This paper introduces a shallow neural network approach for railway obstacle detection that combines local pattern recognition with global context hallucination, improving detection accuracy on railway images.

Contribution

It presents a novel method using a shallow network to learn railway segmentation and incorporate global information through hallucination, addressing dataset limitations.

Findings

Outperforms baseline methods in obstacle detection accuracy

Effectively focuses on railway-specific patterns

Utilizes limited receptive field to prevent overconfidence

Abstract

Reliable obstacle detection on railways could help prevent collisions that result in injuries and potentially damage or derail the train. Unfortunately, generic object detectors do not have enough classes to account for all possible scenarios, and datasets featuring objects on railways are challenging to obtain. We propose utilizing a shallow network to learn railway segmentation from normal railway images. The limited receptive field of the network prevents overconfident predictions and allows the network to focus on the locally very distinct and repetitive patterns of the railway environment. Additionally, we explore the controlled inclusion of global information by learning to hallucinate obstacle-free images. We evaluate our method on a custom dataset featuring railway images with artificially augmented obstacles. Our proposed method outperforms other learning-based baseline methods.