|
Anomaly detection in a crowd scene usingtheinteraction force model |
|---|---|
| รหัสดีโอไอ | |
| Creator | Chonthisa Wateosot |
| Title | Anomaly detection in a crowd scene usingtheinteraction force model |
| Contributor | Nikom Suvonvorn |
| Publisher | Research and Technology Transfer Affairs Division.Khon Kaen University. |
| Publication Year | 2560 |
| Journal Title | Asia-Pacific Journal of Science and Technology (APST) |
| Journal Vol. | 22 |
| Journal No. | 3 |
| Page no. | 1-8 |
| Keyword | computer vision, optical flow, energy force |
| URL Website | https://tci-thaijo.org/index.php/APST/index |
| Website title | https://tci-thaijo.org/index.php/APST/article/view/101488 |
| ISSN | 2539-6293 |
| Abstract | Anomalydetection in crowded scenesis an important issue inthe field ofcomputer vision. Many researches have studied and tried to describecrowd behavior. In this paper,we introduce a novel social-basedmethod for detecting abnormal events in crowded scenes called Interaction Energy Force. The method is designed for low-level features without object extraction and tracking. The force modeling is based on optical flow fields,and its interactions are defined by an energy force inspiring energy propagation phenomena that depend on directions and velocities. An energy map isdesigned to represent the interaction forces corresponding to events, where the abnormal events are detected using a thresholding method. Our method wasevaluatedusingthe well-known UMN dataset. The results show the efficiency of our approach with high accuracy invarious conditions. It is a technique that is competitive with the state-of-the-art methodscurrently employed. |
