Visual Fault Detection of Multi-scale Key Components in Freight Trains
This work addresses safety-critical fault detection in railway transportation, offering a more efficient and accurate solution for domain-specific applications.
The paper tackles the problem of visual fault detection for multi-scale key components in freight train braking systems, proposing a lightweight anchor-free framework that achieves 98.44% accuracy with a model size of 22.5 MB, outperforming state-of-the-art detectors.
Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety. Despite the frequently employed methods based on deep learning, these fault detectors are highly reliant on hardware resources and are complex to implement. In addition, no train fault detectors consider the drop in accuracy induced by scale variation of fault parts. This paper proposes a lightweight anchor-free framework to solve the above problems. Specifically, to reduce the amount of computation and model size, we introduce a lightweight backbone and adopt an anchor-free method for localization and regression. To improve detection accuracy for multi-scale parts, we design a feature pyramid network to generate rectangular layers of different sizes to map parts with similar aspect ratios. Experiments on four fault datasets show that our framework achieves 98.44% accuracy while the model size is only 22.5 MB, outperforming state-of-the-art detectors.