Evaluation distance metrics for pedestrian retrieval

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

Research output: Chapter in Book/Report/Conference proceedingChapter

13 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 languageEnglish
Title of host publicationCommunications, Signal Processing, and Systems
Subtitle of host publicationProceedings of the 2018 CSPS Volume II: Signal Processing
EditorsQilian Liang, Xin Liu, Zhenyu Na, Wei Wang, Jiasong Mu, Baoju Zhang
Place of PublicationSingapore
PublisherSpringer
Pages1176-1183
Number of pages8
ISBN (Electronic)9789811365041
ISBN (Print)9789811365034
DOIs
Publication statusPublished - 14 Aug 2019
Event7th International Conference on Communications, Signal Processing, and Systems - Dalian, China
Duration: 14 Jul 201816 Jul 2018

Publication series

NameLecture Notes in Electrical Engineering
PublisherSpringer
Volume516
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference7th International Conference on Communications, Signal Processing, and Systems
Abbreviated titleCSPS 2018
Country/TerritoryChina
CityDalian
Period14/07/1816/07/18

Keywords

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

Cite this