Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance

TL;DR

This paper introduces a unified global trajectory analysis method for video surveillance that combines graph partitioning and matching, using probabilistic inference to improve long-range object tracking amidst occlusion and clutter.

Contribution

It presents a novel joint framework for spatial graph partitioning and temporal graph matching, leveraging Bayesian inference and MCMC for robust trajectory recovery from short video sequences.

Findings

Outperforms state-of-the-art methods on public surveillance datasets.

Effectively handles occlusion, interruption, and background clutter.

Provides accurate long-range trajectory analysis from limited frames.

Abstract

In order to track the moving objects in long range against occlusion, interruption, and background clutter, this paper proposes a unified approach for global trajectory analysis. Instead of the traditional frame-by-frame tracking, our method recovers target trajectories based on a short sequence of video frames, e.g. $15$ frames. We initially calculate a foreground map at each frame, as obtained from a state-of-the-art background model. An attribute graph is then extracted from the foreground map, where the graph vertices are image primitives represented by the composite features. With this graph representation, we pose trajectory analysis as a joint task of spatial graph partitioning and temporal graph matching. The task can be formulated by maximizing a posteriori under the Bayesian framework, in which we integrate the spatio-temporal contexts and the appearance models. The probabilistic inference is achieved by a data-driven Markov Chain Monte Carlo (MCMC) algorithm. Given a peroid of observed frames, the algorithm simulates a ergodic and aperiodic Markov Chain, and it visits a sequence of solution states in the joint space of spatial graph partitioning and temporal graph matching. In the experiments, our method is tested on several challenging videos from the public datasets of visual surveillance, and it outperforms the state-of-the-art methods.