A New Diverse Dataset and Comparison of Algorithms for Pedestrian Detection in Top-View Fisheye Images

Sheng Ho Chiang, Tsai-Pei Wang, Yi Fu Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Pedestrian detection in images has been extensively researched, however existing detectors designed for perspective images usually fail to detect people on top-view fisheye images due to the various appearances of people. In this paper, we establish a new diverse fisheye dataset which consist of indoor and outdoor fisheye images from public and private datasets. We also adapt three types of spatial transformation to make the visual look of the pedestrians as upright as possible and four commonly used algorithms for pedestrian detection without retraining of the detector models. In addition, we analyze the pedestrian detection results with different conditions to figure out the reason of the results.

Original languageEnglish
Title of host publicationISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems
Subtitle of host publication5G Dream to Reality, Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665419512
DOIs
StatePublished - 2021
Event2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021 - Hualien, Taiwan
Duration: 16 Nov 202119 Nov 2021

Publication series

NameISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems: 5G Dream to Reality, Proceeding

Conference

Conference2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021
Country/TerritoryTaiwan
CityHualien
Period16/11/2119/11/21

Keywords

  • Fisheye Cameras
  • Omnidirectional Cameras
  • Pedestrian Detection

Fingerprint

Dive into the research topics of 'A New Diverse Dataset and Comparison of Algorithms for Pedestrian Detection in Top-View Fisheye Images'. Together they form a unique fingerprint.

Cite this