Detecting Anomaly Using the Scene Modeling Based on Time Delayed Statistical Data
文献类型：会议论文
| 作者 | Lixin Chen; Huiwen Guo; Min Wang; Yen-Lun Chen; Xinyu Wu |
| 出版日期 | 2015 |
| 会议名称 | IEEE International Conference on Information and Automation |
| 会议地点 | Lijiang |
| 英文摘要 | We propose a novel approach for the crowd anomaly detection in multiple cameras with non-overlapping view. In this paper, we refer to the activities of crowd in far-field scenes. Firstly, we present a model for learning all of the motion patterns under single camera view, which are regarded as the normal situation. In the surveillance region, we mark the entrances and exits under the single camera view and acquire the crowd flow model by the K-means clustering algorithm. Secondly, we analyze the crowd flow model based on the time delayed statistical data between two camera views. And then we acquire the relative location among the entrances and exits in the different regions. Thirdly, we analyze the crowd transferring probabilistic model on the global scene based on the log-likelihood function and Dirichlet distribution to detect the crowd anomaly. We set up the empirical threshold value of probability P e . If the probability of detected model is less than P e , the detected model is marked as the crowd anomaly. Our approach is evaluated on the simulated data set and the real data set in far-field scenes. Experimental results show the anomaly detection is precise. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6781]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | Lixin Chen,Huiwen Guo,Min Wang,et al. Detecting Anomaly Using the Scene Modeling Based on Time Delayed Statistical Data[C]. 见:IEEE International Conference on Information and Automation. Lijiang. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。