Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspections
This work addresses the challenge of limited anomaly data in railroad maintenance inspections, offering a domain-specific solution for automating visual inspections.
The study tackled the problem of automating visual inspection of rolling stock underfloor equipment by proposing a supervised anomaly detection method using generative adversarial networks and 3D computer graphics to generate synthetic anomaly images, which enabled training an anomaly detection model that successfully detected anomalies without complex adjustments.
The external visual inspections of rolling stock's underfloor equipment are currently being performed via human visual inspection. In this study, we attempt to partly automate visual inspection by investigating anomaly inspection algorithms that use image processing technology. As the railroad maintenance studies tend to have little anomaly data, unsupervised learning methods are usually preferred for anomaly detection; however, training cost and accuracy is still a challenge. Additionally, a researcher created anomalous images from normal images by adding noise, etc., but the anomalous targeted in this study is the rotation of piping cocks that was difficult to create using noise. Therefore, in this study, we propose a new method that uses style conversion via generative adversarial networks on three-dimensional computer graphics and imitates anomaly images to apply anomaly detection based on supervised learning. The geometry-consistent style conversion model was used to convert the image, and because of this the color and texture of the image were successfully made to imitate the real image while maintaining the anomalous shape. Using the generated anomaly images as supervised data, the anomaly detection model can be easily trained without complex adjustments and successfully detects anomalies.