A Novel Multi-Target Multi-Camera Tracking Approach Based On Feature Grouping

Multi-target multi-camera tracking systems track many pedestrians through videos taken from multiple cameras. Generally, multi-target multi-camera tracking comprises three steps, namely, detection, feature extraction, and data association. It also involves a number of marginal post-processing procedures, such as pruning and interpolating. The task is a complicated and challenging problem. In this work, we mainly focus on the process of data association. When correlation clustering-based algorithms are adopted in data association, serious information loss may be observed, especially when pedestrians in a video run into occlusion. Thus, we propose a method called feature group which mitigates the decline in accuracy under occlusions. The proposed method is intuitional but easy to implement without changing the original framework. After comprehensive experiments, the proposed method is proved effective and is able to make substantial improvements on the DukeMTMC dataset. The feature group method is also competitive relative to other state-of-the-art methods.