Video Anomaly Detection using Selective Spatio-Temporal Interest Points and Convolutional Sparse Coding

Finding substantial features is a significant approach to cope the challenges of video anomaly detection and localization. The specific important representation are selected to detect an event in video. State-of-the-art models explore this fashion by do seeking interest points both spatially and temporally. However, it has to very selective towards undesired object or background. Selective Spatio-Temporal Interest Points (SSTIP) address this issue. While, Convolutional Sparse Coding (CSC) with the capability to detect an anomaly event by produce more error in the reconstruction, is preferred rather than patch-based. It demonstrates that utilization SSTIP and CSC yields promising performance.