A Methodology Review on Multi-view Pedestrian Detection

Rui Qiu, Ming Xu*, Yuyao Yan, Jeremy S. Smith

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingChapterpeer-review

2 Citations (Scopus)

Abstract

Although surprisingly good progress has been made in monocular pedestrian detection with emerging deep learning techniques, the existing algorithms still suffer from heavy occlusion between people. To cope with this problem, multiple cameras are often used to provide complimentary information. This chapter presents a comprehensive review on the algorithms for multi-view pedestrian detection. The existing methods are sorted into low-level fusion, intermediate-level fusion, high-level fusion and deep-learning based fusion, in terms of the degree of information fusion. The challenges in developing deep multi-view algorithms are also described in this chapter.

Original languageEnglish
Title of host publicationRecent Advancements in Multi-View Data Analytics
PublisherSpringer Science and Business Media Deutschland GmbH
Pages317-339
Number of pages23
DOIs
Publication statusPublished - 2022

Publication series

NameStudies in Big Data
Volume106
ISSN (Print)2197-6503
ISSN (Electronic)2197-6511

Keywords

  • Data fusion
  • Multi-view
  • Pedestrian detection
  • Video surveillance

Fingerprint

Dive into the research topics of 'A Methodology Review on Multi-view Pedestrian Detection'. Together they form a unique fingerprint.

Cite this