The Research of Group Re-identification from Multiple Cameras

TL;DR

This paper proposes a novel multi-granularity and multi-order matching approach for group re-identification across multiple cameras, addressing challenges like viewpoint variation and group dynamics to improve accuracy.

Contribution

It introduces a multi-granularity feature extraction and a multi-order adaptive matching scheme specifically designed for group re-identification, which is less explored in existing research.

Findings

Effective in handling viewpoint and pose variations.

Improves matching reliability for dynamic groups.

Demonstrates superior performance on multiple datasets.

Abstract

Object re-identification is of increasing importance in visual surveillance. Most existing works focus on re-identify individual from multiple cameras while the application of group re-identification (Re-ID) is rarely discussed. We redefine Group Re-identification as a process which includes pedestrian detection, feature extraction, graph model construction, and graph matching. Group re-identification is very challenging since it is not only interfered by view-point and human pose variations in the traditional re-identification tasks, but also suffered from the challenges in group layout change and group member variation. To address the above challenges, this paper introduces a novel approach which leverages the multi-granularity information inside groups to facilitate group re-identification. We first introduce a multi-granularity Re-ID process, which derives features for multi-granularity objects (people/people-subgroups) in a group and iteratively evaluates their importances during group Re-ID, so as to handle group-wise misalignments due to viewpoint change and group dynamics. We further introduce a multi-order matching scheme. It adaptively selects representative people/people-subgroups in each group and integrates the multi-granularity information from these people/people-subgroups to obtain group-wise matching, hence achieving a more reliable matching score between groups. Experimental results on various datasets demonstrate the effectiveness of our approach.