Deep Background Subtraction of Thermal and Visible Imagery for Pedestrian Detection in Videos

Yijun Yan, Huimin Zhao, Fu Jen Kao, Valentin Masero Vargas, Sophia Zhao, Jinchang Ren (Lead / Corresponding author)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper, we introduce an efficient framework to subtract the background from both visible and thermal imagery for pedestrians’ detection in the urban scene. We use a deep neural network (DNN) to train the background subtraction model. For the training of the DNN, we first generate an initial background map and then employ randomly 5% video frames, background map, and manually segmented ground truth. Then we apply a cognition-based post-processing to further smooth the foreground detection result. We evaluate our method against our previous work and 11 recently widely cited method on three challenge video series selected from a publicly available color-thermal benchmark dataset OCTBVS. Promising results have been shown that the proposed DNN-based approach can successfully detect the pedestrians with good shape in most scenes regardless of illuminate changes and occlusion problem.

Original languageEnglish
Title of host publicationAdvances in Brain Inspired Cognitive Systems
Subtitle of host publication9th International Conference, BICS 2018, Proceedings
EditorsAmir Hussain, Bin Luo, Jiangbin Zheng, Xinbo Zhao, Cheng-Lin Liu, Jinchang Ren, Huimin Zhao
Place of PublicationSwitzerland
PublisherSpringer
Pages75-84
Number of pages10
Edition1
ISBN (Electronic)9783030005634
ISBN (Print)9783030005627
DOIs
Publication statusPublished - 2018
Event9th International Conference on Brain-Inspired Cognitive Systems, BICS 2018 - Xi'an, China
Duration: 7 Jul 20188 Jul 2018

Publication series

NameLecture Notes in Computer Science
Volume10989
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference9th International Conference on Brain-Inspired Cognitive Systems, BICS 2018
Country/TerritoryChina
CityXi'an
Period7/07/188/07/18

Keywords

  • Deep neural network (DNN)
  • Pedestrian detection
  • Video salient objects

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Deep Background Subtraction of Thermal and Visible Imagery for Pedestrian Detection in Videos'. Together they form a unique fingerprint.

Cite this