Orientation Driven Bag of Appearances for Person Re-identification

TL;DR

This paper introduces a novel person re-identification method that leverages body structure and orientation information to improve feature representation and matching accuracy across camera views.

Contribution

It proposes the Body-Structure Based Feature Representation (BSFR) and Orientation Driven Bag of Appearances (ODBoA), incorporating body structure and orientation cues for enhanced re-identification.

Findings

Outperforms existing methods on multiple datasets

Effectively handles pose and viewpoint variations

Demonstrates the benefit of body structure and orientation info

Abstract

Person re-identification (re-id) consists of associating individual across camera network, which is valuable for intelligent video surveillance and has drawn wide attention. Although person re-identification research is making progress, it still faces some challenges such as varying poses, illumination and viewpoints. For feature representation in re-identification, existing works usually use low-level descriptors which do not take full advantage of body structure information, resulting in low representation ability. %discrimination. To solve this problem, this paper proposes the mid-level body-structure based feature representation (BSFR) which introduces body structure pyramid for codebook learning and feature pooling in the vertical direction of human body. Besides, varying viewpoints in the horizontal direction of human body usually causes the data missing problem, $i.e.$, the appearances obtained in different orientations of the identical person could vary significantly. To address this problem, the orientation driven bag of appearances (ODBoA) is proposed to utilize person orientation information extracted by orientation estimation technic. To properly evaluate the proposed approach, we introduce a new re-identification dataset (Market-1203) based on the Market-1501 dataset and propose a new re-identification dataset (PKU-Reid). Both datasets contain multiple images captured in different body orientations for each person. Experimental results on three public datasets and two proposed datasets demonstrate the superiority of the proposed approach, indicating the effectiveness of body structure and orientation information for improving re-identification performance.