Unsupervised pedestrian sample extraction for model training

Hao Yu, Daryl Maples, Ying Liu, Zhijie Xu

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

1 Citation (Scopus)

Abstract

Many researches on pedestrian detection use benchmarking datasets such as INRIA for model training. However, models trained with standard video database do not usually obtain satisfying performance in real-life conditions. Hence, supervised training through manually labelled instances is often required to help achieving better detection result. In this research, an innovative unsupervised training approach is proposed. By analyzing the histogram of adjacent pixels modelled from the video sequences, separated pedestrians can be extracted without manual intervention. Experiments have shown consistent performance that is superior over the state-of-the-art methods.

Original languageEnglish
Title of host publicationMulti Conference on Computer Science and Information Systems, MCCSIS 2019 - Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2019, Game and Entertainment Technologies 2019 and Computer Graphics, Visualization, Computer Vision and Image Processing 2019
EditorsKatherine Blashki, Yingcai Xiao, Luis Rodrigues
PublisherIADIS Press
Pages291-298
Number of pages8
ISBN (Electronic)9789898533913
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event13th International Conference on Interfaces and Human Computer Interaction 2019, IHCI 2019, 12th International Conference on Game and Entertainment Technologies 2019, GET 2019 and 13th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing 2019, CGVCVIP 2019 - Porto, Portugal
Duration: 16 Jul 201918 Jul 2019

Publication series

NameMulti Conference on Computer Science and Information Systems, MCCSIS 2019 - Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2019, Game and Entertainment Technologies 2019 and Computer Graphics, Visualization, Computer Vision and Image Processing 2019

Conference

Conference13th International Conference on Interfaces and Human Computer Interaction 2019, IHCI 2019, 12th International Conference on Game and Entertainment Technologies 2019, GET 2019 and 13th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing 2019, CGVCVIP 2019
Country/TerritoryPortugal
CityPorto
Period16/07/1918/07/19

Keywords

  • Crowd Analysis
  • Pedestrian Detection
  • Unsupervised Learning

Fingerprint

Dive into the research topics of 'Unsupervised pedestrian sample extraction for model training'. Together they form a unique fingerprint.

Cite this