Abnormal Behavior Detection Based on Time-Channel Topology Decoupling Graph Convolution

‍ ‍With the development of pose estimation technology， human skeleton data can be used instead of conventional pixel data for abnormal behavior detection. This anomaly detection method overcomes the problems caused by illumination， view angle， and background noise in conventional pixel-based methods. However， the existing graph convolutional network （GCN） usually uses a fixed adjacency matrix for information aggregation when processing human skeleton data， which limits the flexibility of the model in extracting behavioral features. To solve this problem， this study proposes a time-channel topology decoupling graph convolution network （TCTD-GCN）. TCTD-GCN adopts topological learning to learn an adaptive adjacency matrix in the time and channel dimensions， respectively， so as to realize their effective decoupling. The learned adaptive adjacency matrix can aggregate features more precisely and promote the accurate representation of human behavior. In addition， we propose a virtual anomaly-guided self-supervised anomaly detection （VASAD） strategy to improve the detection accuracy. VASAD treats the anomaly detection problem as a multi-classification problem， and treats different classes of normal behavior as “virtual anomalies” to assist model training， thus distinguishing normal and abnormal behavior more accurately in the testing phase. This strategy enhances the model’s learning of the inherent differences in normal behavior and improves the discrimination ability of true anomalies. The model was tested on three mainstream datasets， ShanghaiTech Campus， CUHK Avenue， and USCD Ped2， and the frame-level area under the curve reached 76.6%， 87.7%， and 95.3%， respectively. Compared with mainstream models， the proposed model significantly improved the detection performance on the ShanghaiTech Campus and CUHK Avenue datasets， which verifies its effectiveness and superiority.