Abnormal behavior detection using a novel behavior representation

Abnormal behavior detection refers to the problem of finding patterns in data that do not conform to expected behavior. Detection of abnormal behavior is an important area of research in computer vision and is also driven by a wide of application domains, such as smart video surveillance. In this paper, we present a novel based-energy approach for abnormal behavior detection. Use an adaptive optical flow model to operate on moving particles instead of objects and fuses features with the shape and trajectory information. To detect the abnormal behavior, experimental results on the Institute of Automation, Chinese Academy of Science multi-view behavior database and self-photo videos demonstrate the robustness and effectiveness of our method.