Human Abnormal Behavior Detection Based on Region Optical Flow Energy
Jian Liu, Lin Qiu, Enyang Gao
Available Online April 2016.
- https://doi.org/10.2991/emim-16.2016.216How to use a DOI?
- Anomaly detection; Foreground extraction; Vibe algorithm; Optical flow calculation; Energy histogram
- In the light of the hysteresis of video surveillance call video in public places, as well as the current video surveillance function of a single, in order to improve the real-time performance of monitoring, a detection method of human abnormal behavior based on optical flow method is proposed. The foreground regions of the video sequence is obtained by Vibe algorithm and update the background model adaptively; Regional markers for the future by the nearest neighbor method, accurately extract moving regions; Optical flow of moving region is calculated by Lucas-Kanada method; Weighted energy histogram is used to describe the abnormal changes of human behavior. The video sequences of different scenarios are simulated; the experimental results verify the effectiveness of the proposed method.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Jian Liu AU - Lin Qiu AU - Enyang Gao PY - 2016/04 DA - 2016/04 TI - Human Abnormal Behavior Detection Based on Region Optical Flow Energy BT - 6th International Conference on Electronic, Mechanical, Information and Management Society PB - Atlantis Press SP - 1050 EP - 1057 SN - 2352-538X UR - https://doi.org/10.2991/emim-16.2016.216 DO - https://doi.org/10.2991/emim-16.2016.216 ID - Liu2016/04 ER -