Interpretable Railway Object Classification Using Part-Prototype Networks

Enhancing safety and operational efficiency in railway systems ben-
efits from robust AI-powered perception, particularly for reliable obstacle and
pedestrian detection. However, the prevalent black-box nature of contemporary
deep learning models presents significant challenges for verification and trust,
especially within safety-critical railway environments characterised by dynamic
weather, illumination changes, and high speed, which create undesirable effects
such as cluttered backgrounds, and motion blur, which may hinder the perfor-
mance of computer vision approaches. This paper addresses the need for more
transparent models by proposing the application of Prototypical Part Networks
(ProtoPNet) for interpretable obstacle and pedestrian classification within the
railway domain. Experiments with the OSDaR23 dataset demonstrate that train-
ing with a careful selection of data augmentation processes enhances key metrics
such as precision, recall and F1-score while yielding transparent results with vi-
sually robust prototypes.