Anomaly Detection in Crowded Scenes

被引：714

作者：

Mahadevan, Vijay ^{[1
]}

Li, Weixin ^{[1
]}

Bhalodia, Viral ^{[1
]}

Vasconcelos, Nuno ^{[1
]}

机构：

[1] Univ Calif San Diego, Dept Elect & Comp Engn, San Diego, CA 92103 USA

来源：

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2010年

关键词：

MODEL;

D O I：

10.1109/CVPR.2010.5539872

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel framework for anomaly detection in crowded scenes is presented. Three properties are identified as important for anomaly detection in such scenes: 1) joint modeling of appearance and dynamics of the scene, and the abilities to detect 2) temporal, and 3) spatial abnormalities. The model for normal crowd behavior is based on mixtures of dynamic textures and outliers under this model are labeled as anomalies. Temporal anomalies are equated to events of low-probability, while spatial anomalies are handled using discriminant saliency. An experimental evaluation is conducted with a new dataset of croweded scenes, composed of 100 video sequences and five well defined abnormality categories. The proposed representation is shown to outperform various state of the art anomaly detection techniques.

引用

页码：1975 / 1981

页数：7