Segmented-Aggregated Framework With Internal–External Constraint Mechanism for Unsupervised Track Anomaly Detection
Yang Gao, Zhiwei Cao, Yong Qin, Lirong Lian, Linlin Kou, Yaguan Wang · IEEE Transactions on Instrumentation and Measurement · 2025
The track is the basis of railway, and track defect detection is very important for train safety. Currently, the supervised track defect detection methods focus on detecting known category defects, but these methods cannot cover all categories of defects. Furthermore, the serious interference of complex environments also poses a significant challenge to the unknown category track defect detection. To address the deficiencies, this article proposes an unsupervised track anomaly detection algorithm using segmented-aggregated framework with internal-external constraint mechanism, comprising three fundamental modules. First, the regional segmentation module is proposed to facilitate the precise regionalization of key track components at the pixel level, minimizing the complex background interference. Second, a novel self-generating feature parameterization module is proposed, which employs a self-generating feature aggregation network and fitting function to obtain the optimal fitting parameters. Finally, this article presents an internal-external constraint metric anomaly score calculation module to detect anomalies complementally. The external constraint considers the difference between the test image and normal images, while the internal constraint complements measurement of internal difference in the test image. The efficacy of the algorithm is verified on the track anomaly dataset and publicly available dataset. The results indicate that the image AUROC and pixel AUROC of the proposed algorithm can reach 97.82% and 99.85%, respectively. And the image F1 can reach 88.34% and is markedly superior to other state-of-the-art anomaly detection algorithms.