Anomaly detection by exploiting the tracking trajectory in surveillance videos

Xue Z X, Wu W

Sci China Inf Sci, 2020, 63(5): 154101

Surveillance systems have become increasingly ubiquitous, which has led to a requirement to detect anomalies for efficiently preventing terrorism and reducing crimes. The increasing number of surveillance networks has imposed major technical challenges on intelligent anomaly detection because of the inconsistent appearance of pedestrians owing to posture deformation and clutter in video streams. Furthermore, partial occlusions significantly increase the difficulty of anomaly detection in case of a single camera view.
PDF Slides

Demo

Presentation