基于时空纹理的实时群体行为检测（英文）

Real-time crowd anomalydetection based on spatio-temporal texture model

描述一套全新的基于时空纹理特征的群体行为模型并对其特征进行分析。该模型针对实时环境中的安检应用,使用丰富的底层图像特征及简洁的行为识别算法,另外定义并提取视频图像中群体行为的纹理特征,使用同性随机场加以描述。所建模型可以方便地定位出异常群体行为的发生位置及时间。通过实验可证明,该方法能快速有效地提取及分析视频异常行为,并能在基于闭路电视的智能安检系统中发挥其优势。

An innovative spatio-temporal texture based on crowd modelling technique and its corresponding pattern analysis methods are introduced.The algorithm is designed for real time applications by deploying low level statistical features and avoiding complicated machine learning and recognition processes.Through extracting and integrating those crowd textures from live or recorded videos,the so called homogeneous random features are deployed in the research for behavioural template matching.Experiment results show that the abnormality appearing in crowd scenes can be effectively and efficiently identified by using the devised methods.This new approach is expected to facilitate a wide spectrum of crowd analysis applications in the future through laying a solid theoretical foundation and implementation strategy for automating existing Closed Circuit Television（CCTV）based surveillance systems.