Person re-identification is an important technique towards automatic recognition of a person across non- overlapping cameras. In this paper, a novel patch selection method based on parsing and saliency de- tection is proposed. The algorithm is divided into two stages. The first stage, primary selection: Deep Decompositional Network (DNN) is adopted to parse a pedestrian image into semantic regions, then slid- ing window and color matching techniques are proposed to select pedestrian patches and remove back- ground patches. The second stage, secondary selection: saliency detection is utilized to select reliable patches according to saliency map. Finally, PHOG, HSV and SIFT features are extracted from these patches and fused with the global feature LOMO to compensate for the inherent errors of saliency detection. By applying the proposed method on such datasets as VIPeR, PRID2011, CUHK01, CUHK03, PRID 450S and iLIDS-VID, it is found that the proposed descriptor can produce results superior to many state-of-the-art feature representation methods for person identification.
Bibliographical noteFunding Information:
Sonya Coleman (M11) received the B.Sc. (Hons) degree in mathematics, statistics, and computing and the Ph.D. degree in mathematics from the University of Ulster, Londonberry, U.K., in 1999 and 2003, respectively. She is currently a Lecturer in the School of Computing and Intelligent System, Magee College, University of Ulster. She has more than 50 publications primarily in the field of mathematical image processing, and much of the recent research undertaken by her has been supported by funding from EPSRC award EP/C006283/11, the Leverhulme Trust, and the Nuffield Foundation. Additionally, she is co-investigator on the EU FP7 funded project RUBICON. She is the author or coauthor of over 70 research papers on image processing, robotics, and computational neuroscience. Dr. Coleman was awarded the Distinguished Research Fellowship by the University of Ulster in recognition of her contribution to research in 2009.
The research is supported by Fund Project of the Key Laboratory of Aerospace System Simulation (No. 61403120111), National Natural Science Foundation of China (No. 61973066 , 61471110 ), and the Distinguished Creative Talent Program of Shenyang (RC170490).
© 2019 Elsevier B.V.
Copyright 2019 Elsevier B.V., All rights reserved.
- person re-identification
- patch selection
- pedestrian parsing
- saliency detection
- Feature fusion
- Pedestrian parsing
- Person re-identification
- Patch selection
- Saliency detection