Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates

We propose a space-time Markov Random Field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activ- ity at each local node, we capture the distribution of its typ- ical optical flow with a Mixture of Probabilistic Principal Component Analyzers. For any new optical flow patterns detected in incoming video clips, we use the learned model and MRF graph to compute a maximum a posteriori esti- mate of the degree of normality at each local node. Further, we show how to incrementally update the current model pa- rameters as new video observations stream in, so that the model can efficiently adapt to visual context changes over a long period of time. Experimental results on surveillance videos show that our space-time MRF model robustly de- tects abnormal activities both in a local and global...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Jaechul Kim (University of Texas at Austin), Kristen Grauman (University of Texas at Austin)
• Keywords: Computer Vision, CVPR 2009, Detecting Abnormal Activities, Space-Time MRF