Leveraging Localization for Multi-camera Association

TL;DR

This paper introduces McAssoc, a deep learning method that improves multi-camera detection association by leveraging localization information, demonstrating its importance especially with similar-looking objects.

Contribution

The paper presents a novel 3-branch architecture and a new metric, IPAA, for better multi-camera association, emphasizing the role of localization information.

Findings

Localization is crucial for accurate cross-camera association.

The proposed method outperforms existing approaches in association accuracy.

Localization information significantly improves association in challenging scenarios.

Abstract

We present McAssoc, a deep learning approach to the as-sociation of detection bounding boxes in different views ofa multi-camera system. The vast majority of the academiahas been developing single-camera computer vision algo-rithms, however, little research attention has been directedto incorporating them into a multi-camera system. In thispaper, we designed a 3-branch architecture that leveragesdirect association and additional cross localization infor-mation. A new metric, image-pair association accuracy(IPAA) is designed specifically for performance evaluationof cross-camera detection association. We show in the ex-periments that localization information is critical to suc-cessful cross-camera association, especially when similar-looking objects are present. This paper is an experimentalwork prior to MessyTable, which is a large-scale bench-mark for instance association in mutliple cameras.