A Semi-Supervised Railway Foreign Object Detection Method Based on GAN
Yanqi Chen, Shuzhen Tong, Xiaobo Lu, Yun Wei
Abstract
The rapid development of deep learning provides new technical means for railway foreign object detection. However, in practical applications, the datasets of railways with foreign objects are scarce. In order to solve this problem, by improving the loss function and anomaly image evaluation standard, this paper proposes a new semi-supervised anomaly detection method based on GAN (Generative Adversarial Networks). Experiments show that our method can achieve railway foreign object detection without anomaly prior knowledge. Regarding anomaly recognition, a 0.058 AUC (Area Under Curve) and a 6% classification accuracy relative improvement for the railway dataset used in this paper are obtained.
Topics & Concepts
Anomaly detectionComputer scienceObject (grammar)Artificial intelligenceObject detectionAnomaly (physics)Function (biology)Pattern recognition (psychology)Image (mathematics)Generative grammarData miningMachine learningComputer visionCondensed matter physicsEvolutionary biologyBiologyPhysicsAnomaly Detection Techniques and ApplicationsInfrastructure Maintenance and MonitoringGait Recognition and Analysis