Evaluation distance metrics for pedestrian retrieval

Zhong Zhang; Meiyan Huang; Shuang  Liu; Tariq S. Durrani

doi:10.1007/978-981-13-6504-1_140

Evaluation distance metrics for pedestrian retrieval

Zhong Zhang, Meiyan Huang, Shuang Liu, Tariq S. Durrani

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter

31 Downloads (Pure)

Abstract

Pedestrian retrieval is an important technique of searching for a specific pedestrian from a large gallery. In this paper, we introduce three types of distance metrics for pedestrian retrieval, including learning-free distance metric methods, metric learning methods, and convolution neural network (CNN) methods, and evaluate the performance of different distance metrics using the Market-1501 database. The experiment shows that the CNN methods achieve the best results.

Original language	English
Title of host publication	Communications, Signal Processing, and Systems
Subtitle of host publication	Proceedings of the 2018 CSPS Volume II: Signal Processing
Editors	Qilian Liang, Xin Liu, Zhenyu Na, Wei Wang, Jiasong Mu, Baoju Zhang
Place of Publication	Singapore
Publisher	Springer
Pages	1176-1183
Number of pages	8
ISBN (Electronic)	9789811365041
ISBN (Print)	9789811365034
DOIs	https://doi.org/10.1007/978-981-13-6504-1_140
Publication status	Published - 14 Aug 2019
Event	7th International Conference on Communications, Signal Processing, and Systems - Dalian, China Duration: 14 Jul 2018 → 16 Jul 2018

Publication series

Name	Lecture Notes in Electrical Engineering
Publisher	Springer
Volume	516
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	7th International Conference on Communications, Signal Processing, and Systems
Abbreviated title	CSPS 2018
Country/Territory	China
City	Dalian
Period	14/07/18 → 16/07/18

Keywords

pedestrian retrieval
learning-free distance metric methods
metric learning methods
CNN methods

Access to Document

10.1007/978-981-13-6504-1_140

Zhang-etal-CSPS-2018-Evaluation-distance-metrics-for-pedestrian-retrievalAccepted author manuscript, 1.19 MBLicence: Strath_1

Cite this

Zhang, Z., Huang, M., Liu, S., & Durrani, T. S. (2019). Evaluation distance metrics for pedestrian retrieval. In Q. Liang, X. Liu, Z. Na, W. Wang, J. Mu, & B. Zhang (Eds.), Communications, Signal Processing, and Systems: Proceedings of the 2018 CSPS Volume II: Signal Processing (pp. 1176-1183). (Lecture Notes in Electrical Engineering; Vol. 516). Springer. https://doi.org/10.1007/978-981-13-6504-1_140

Zhang, Zhong ; Huang, Meiyan ; Liu, Shuang et al. / Evaluation distance metrics for pedestrian retrieval. Communications, Signal Processing, and Systems: Proceedings of the 2018 CSPS Volume II: Signal Processing. editor / Qilian Liang ; Xin Liu ; Zhenyu Na ; Wei Wang ; Jiasong Mu ; Baoju Zhang. Singapore : Springer, 2019. pp. 1176-1183 (Lecture Notes in Electrical Engineering).

@inbook{365766e00c5149699f41ba26fbe8fd7c,

title = "Evaluation distance metrics for pedestrian retrieval",

abstract = "Pedestrian retrieval is an important technique of searching for a specific pedestrian from a large gallery. In this paper, we introduce three types of distance metrics for pedestrian retrieval, including learning-free distance metric methods, metric learning methods, and convolution neural network (CNN) methods, and evaluate the performance of different distance metrics using the Market-1501 database. The experiment shows that the CNN methods achieve the best results.",

keywords = "pedestrian retrieval, learning-free distance metric methods, metric learning methods, CNN methods",

author = "Zhong Zhang and Meiyan Huang and Shuang Liu and Durrani, {Tariq S.}",

year = "2019",

month = aug,

day = "14",

doi = "10.1007/978-981-13-6504-1_140",

language = "English",

isbn = "9789811365034",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "1176--1183",

editor = "Qilian Liang and Xin Liu and Zhenyu Na and Wei Wang and Jiasong Mu and Baoju Zhang",

booktitle = "Communications, Signal Processing, and Systems",

note = "7th International Conference on Communications, Signal Processing, and Systems, CSPS 2018 ; Conference date: 14-07-2018 Through 16-07-2018",

}

Zhang, Z, Huang, M, Liu, S & Durrani, TS 2019, Evaluation distance metrics for pedestrian retrieval. in Q Liang, X Liu, Z Na, W Wang, J Mu & B Zhang (eds), Communications, Signal Processing, and Systems: Proceedings of the 2018 CSPS Volume II: Signal Processing. Lecture Notes in Electrical Engineering, vol. 516, Springer, Singapore, pp. 1176-1183, 7th International Conference on Communications, Signal Processing, and Systems, Dalian, China, 14/07/18. https://doi.org/10.1007/978-981-13-6504-1_140

Evaluation distance metrics for pedestrian retrieval. / Zhang, Zhong; Huang, Meiyan; Liu, Shuang et al.
Communications, Signal Processing, and Systems: Proceedings of the 2018 CSPS Volume II: Signal Processing. ed. / Qilian Liang; Xin Liu; Zhenyu Na; Wei Wang; Jiasong Mu; Baoju Zhang. Singapore: Springer, 2019. p. 1176-1183 (Lecture Notes in Electrical Engineering; Vol. 516).

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Evaluation distance metrics for pedestrian retrieval

AU - Zhang, Zhong

AU - Huang, Meiyan

AU - Liu, Shuang

AU - Durrani, Tariq S.

PY - 2019/8/14

Y1 - 2019/8/14

N2 - Pedestrian retrieval is an important technique of searching for a specific pedestrian from a large gallery. In this paper, we introduce three types of distance metrics for pedestrian retrieval, including learning-free distance metric methods, metric learning methods, and convolution neural network (CNN) methods, and evaluate the performance of different distance metrics using the Market-1501 database. The experiment shows that the CNN methods achieve the best results.

AB - Pedestrian retrieval is an important technique of searching for a specific pedestrian from a large gallery. In this paper, we introduce three types of distance metrics for pedestrian retrieval, including learning-free distance metric methods, metric learning methods, and convolution neural network (CNN) methods, and evaluate the performance of different distance metrics using the Market-1501 database. The experiment shows that the CNN methods achieve the best results.

KW - pedestrian retrieval

KW - learning-free distance metric methods

KW - metric learning methods

KW - CNN methods

U2 - 10.1007/978-981-13-6504-1_140

DO - 10.1007/978-981-13-6504-1_140

M3 - Chapter

SN - 9789811365034

T3 - Lecture Notes in Electrical Engineering

SP - 1176

EP - 1183

BT - Communications, Signal Processing, and Systems

A2 - Liang, Qilian

A2 - Liu, Xin

A2 - Na, Zhenyu

A2 - Wang, Wei

A2 - Mu, Jiasong

A2 - Zhang, Baoju

PB - Springer

CY - Singapore

T2 - 7th International Conference on Communications, Signal Processing, and Systems

Y2 - 14 July 2018 through 16 July 2018

ER -

Zhang Z, Huang M, Liu S, Durrani TS. Evaluation distance metrics for pedestrian retrieval. In Liang Q, Liu X, Na Z, Wang W, Mu J, Zhang B, editors, Communications, Signal Processing, and Systems: Proceedings of the 2018 CSPS Volume II: Signal Processing. Singapore: Springer. 2019. p. 1176-1183. (Lecture Notes in Electrical Engineering). Epub 2018 Jul 22. doi: 10.1007/978-981-13-6504-1_140