自动化学报2003，Vol.29Issue(3)：321-331,11.
无需跟踪的场景事件识别
Scene Event Recognition Without Tracking
摘要
Abstract
We present a novel approach to behaviour recognition in visual surveillance under which scene events corresponding to object behaviours are modelled as groups of affiliated autonomous pixel-level events automatically detected using Pixel Change Histories (PCHs). The Expectation-Maximisation (EM) algorithm is employed to cluster these pixel-level events into semantically more meaningful blob-level scene events, with automatic model order selection using modified Minimum Description Length (MDL). The method is computationally efficient allowing for real-time performance. Experiments are presented to demonstrate the effectiveness of recognising these scene events without object trajectory matching.关键词
行为识别/事件识别/基于轨迹表达的相对事件Key words
Activity and behaviour recognition/event recognition/event versus trajectory based representation分类
信息技术与安全科学引用本文复制引用
ShaogangGong,TaoXiang..无需跟踪的场景事件识别[J].自动化学报,2003,29(3):321-331,11.基金项目
Supported by the UK EPSRC and DTI under the Management of Information Programme （）
