Cross-Camera Trajectories Help Person Retrieval in a Camera Network

TL;DR

This paper introduces a novel pedestrian retrieval framework that leverages cross-camera trajectory generation, integrating spatial and temporal information to improve person re-identification across non-overlapping camera networks.

Contribution

It proposes a new spatio-temporal model and trajectory extraction method that incorporate walking habits and camera layout, along with a trajectory re-ranking technique.

Findings

Effective in real surveillance scenarios

Robust against variations in pedestrian movement

Outperforms existing methods in accuracy

Abstract

We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of the camera network. To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information. To obtain pedestrian trajectories, we propose a novel cross-camera spatio-temporal model that integrates pedestrians' walking habits and the path layout between cameras to form a joint probability distribution. Such a spatio-temporal model among a camera network can be specified using sparsely sampled pedestrian data. Based on the spatio-temporal model, cross-camera trajectories can be extracted by the conditional random field model and further optimized by restricted non-negative matrix factorization. Finally, a trajectory re-ranking technique is proposed to improve the pedestrian retrieval results. To verify the effectiveness of our method, we construct the first cross-camera pedestrian trajectory dataset, the Person Trajectory Dataset, in real surveillance scenarios. Extensive experiments verify the effectiveness and robustness of the proposed method.