Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos

TL;DR

This paper introduces a novel group sparsity-based temporal attention method to improve pedestrian attribute recognition in occluded videos by effectively handling occlusion and attribute correlation.

Contribution

It proposes a group sparsity-based temporal attention module that enhances occlusion handling and attribute correlation modeling in video-based pedestrian attribute recognition.

Findings

Achieved higher F1-score than state-of-the-art methods

Effectively handles occlusion in pedestrian videos

Improves attribute recognition accuracy

Abstract

Occlusion processing is a key issue in pedestrian attribute recognition (PAR). Nevertheless, several existing video-based PAR methods have not yet considered occlusion handling in depth. In this paper, we formulate finding non-occluded frames as sparsity-based temporal attention of a crowded video. In this manner, a model is guided not to pay attention to the occluded frame. However, temporal sparsity cannot include a correlation between attributes when occlusion occurs. For example, "boots" and "shoe color" cannot be recognized when the foot is invisible. To solve the uncorrelated attention issue, we also propose a novel group sparsity-based temporal attention module. Group sparsity is applied across attention weights in correlated attributes. Thus, attention weights in a group are forced to pay attention to the same frames. Experimental results showed that the proposed method achieved a higher F1-score than the state-of-the-art methods on two video-based PAR datasets.