Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates

TLDR

The MRF graph represents a grid of local video regions with spatial and temporal links between neighboring nodes. The study proposes a space‑time Markov random field model to detect abnormal activities in video. The model learns normal optical flow patterns at each node using a mixture of probabilistic principal component analyzers, then applies the MRF graph to compute a MAP estimate of normality for new flows and updates parameters incrementally as new observations arrive. Experiments on surveillance videos demonstrate that the space‑time MRF accurately localizes atomic abnormal activities and simultaneously detects global abnormalities arising from irregular interactions among local activities.

Abstract

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 activity at each local node, we capture the distribution of its typical 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 estimate of the degree of normality at each local node. Further, we show how to incrementally update the current model parameters 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 detects abnormal activities both in a local and global sense: not only does it accurately localize the atomic abnormal activities in a crowded video, but at the same time it captures the global-level abnormalities caused by irregular interactions between local activities.