Anomaly event detection has been extensively researched in computer vision in recent years. Most conventional anomaly event\ndetection methods can only leverage the single-modal cues and not deal with the complementary information underlying other\nmodalities in videos. To address this issue, in this work, we propose a novel two-stream convolutional networks model for\nanomaly detection in surveillance videos. Specifically, the proposed model consists of RGB and Flow two-stream networks, in\nwhich the final anomaly event detection score is the fusion of those of two networks. Furthermore, we consider two fusion\nsituations, including the fusion of two streams with the same or different number of layers respectively. The design insight is to\nleverage the information underlying each stream and the complementary cues of RGB and Flow two-stream sufficiently. Two\ndatasets (UCF-Crime and ShanghaiTech) are used to validate the effectiveness of proposed solution.
Loading....