Person Re-Identification with Effectively Designed Parts

• 来源期刊: 清华大学学报自然科学版（英文版）
• 年，卷（期）: 2020,（3）
• 页码范围: 415-424
• 页数: 10页
• 语种: 英文
• DOI: 10.26599/TST.2019.9010031

摘要

Person re-IDentification (re-ID) is an important research topic in the computer vision community,with significance for a range of applications.Pedestrians are well-structured objects that can be partitioned,although detection errors cause slightly misaligned bounding boxes,which lead to mismatches.In this paper,we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works,and thereby obtain more effective feature descriptors.Specifically,we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network (CNN) descriptors on the Market-1501 dataset.We also investigate the complementarity among different parts using combination and ablation studies,and provide novel insights into this issue.Compared with the state-of-the-art,our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets (Market-1501 and CUHK03) and one small-scale dataset (VIPeR).