Detecting interleaved sequences and groups in camera streams for human behavior sensing

Deployments of camera security systems are capable of capturing long data sequences about human activity. This paper deals with processing of detected sequences at a more macroscopic level to detect chains of events based on a prior given specification. In our problem, sensed interactions between people are modeled as sequences of pairwise events that are interleaved with other interactions taking place in the background. We formulate the problem as an isomorphic subgraph matching problem and solve it to detect a chain of events, its participants and their roles. We further evaluate our solution in the presence of background interference from other interactions and give analytical and empirical results about the performance of our algorithm.