Active Online Anomaly Detection Using Dirichlet Process Mixture Model and Gaussian Process Classification
2017 IEEE Winter Conference on Applications of Computer Vision (WACV)(2017)
摘要
We present a novel anomaly detection (AD) system for streaming videos. Different from prior methods that rely on unsupervised learning of clip representations, that are usually coarse in nature, and batch-mode learning, we propose the combination of two non-parametric models for our task: (i) Dirichlet process mixture models (DPMM) based modeling of object motion and directions in each cell, and (ii) Gaussian process based active learning paradigm involving labeling by a domain expert. Whereas conventional clip representation methods adopt quantizing only motion directions leading to a lossy, coarse representation that are inadequate, our clip representation approach results in fine grained clusters at each cell that model the scene activities (both direction and speed) more effectively. For active anomaly detection, we adapt a Gaussian Process framework to process incoming samples (video snippets) sequentially, seek labels for confusing or informative samples and and update the AD model online. Furthermore, the proposed video representation along with a novel query criterion to select informative samples for labeling that incorporates both exploration and exploitation criteria is proposed, and is found to outperform competing criteria on two challenging traffic scene datasets.
更多查看译文
关键词
active online anomaly detection,Dirichlet process mixture model,Gaussian process classification,AD system,video streaming,nonparametric models,DPMM based modeling,object motion,object directions,Gaussian process-based active learning paradigm,clip representation approach,fine-grained clusters,active anomaly detection,video snippets,online AD model update,video representation,query criterion,exploration criteria,exploitation criteria,traffic scene datasets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络