Human segmentation by fusing visible-light and thermal imaginary

Jian Zhao; Sen Ching S. Cheung

doi:10.1109/ICCVW.2009.5457476

Human segmentation by fusing visible-light and thermal imaginary

Jian Zhao, Sen Ching S. Cheung

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Scopus citations

Abstract

This paper describes a system for robust segmentation of human in video sequences by fusing the visible-light and thermal imaginary. The system first performs a simple calibration procedure to rectify the two camera views without knowing the cameras' intrinsic characteristics. Then a blob-to-blob homography is learned on-the-fly by estimating the disparity of each blob so that a pixel level registration can be achieved. The multi-modality information is then combined under a two-tier tracking algorithm and a unified background model to attain precise segmentation. Preliminary experimental results shows significant improvements over existing schemes under various difficult scenarios.

Original language	English
Title of host publication	2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009
Pages	1185-1192
Number of pages	8
DOIs	https://doi.org/10.1109/ICCVW.2009.5457476
State	Published - 2009
Event	2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009 - Kyoto, Japan Duration: Sep 27 2009 → Oct 4 2009

Publication series

Name	2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

Conference

Conference	2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009
Country/Territory	Japan
City	Kyoto
Period	9/27/09 → 10/4/09

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/ICCVW.2009.5457476

Cite this

@inproceedings{424a559713504f4a9af730ed4d26e245,

title = "Human segmentation by fusing visible-light and thermal imaginary",

abstract = "This paper describes a system for robust segmentation of human in video sequences by fusing the visible-light and thermal imaginary. The system first performs a simple calibration procedure to rectify the two camera views without knowing the cameras' intrinsic characteristics. Then a blob-to-blob homography is learned on-the-fly by estimating the disparity of each blob so that a pixel level registration can be achieved. The multi-modality information is then combined under a two-tier tracking algorithm and a unified background model to attain precise segmentation. Preliminary experimental results shows significant improvements over existing schemes under various difficult scenarios.",

author = "Jian Zhao and Cheung, {Sen Ching S.}",

year = "2009",

doi = "10.1109/ICCVW.2009.5457476",

language = "English",

isbn = "9781424444427",

series = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009",

pages = "1185--1192",

booktitle = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009",

note = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009 ; Conference date: 27-09-2009 Through 04-10-2009",

}

Zhao, J & Cheung, SCS 2009, Human segmentation by fusing visible-light and thermal imaginary. in 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009., 5457476, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, pp. 1185-1192, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, Kyoto, Japan, 9/27/09. https://doi.org/10.1109/ICCVW.2009.5457476

Human segmentation by fusing visible-light and thermal imaginary. / Zhao, Jian; Cheung, Sen Ching S.
2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. 2009. p. 1185-1192 5457476 (2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Human segmentation by fusing visible-light and thermal imaginary

AU - Zhao, Jian

AU - Cheung, Sen Ching S.

PY - 2009

Y1 - 2009

N2 - This paper describes a system for robust segmentation of human in video sequences by fusing the visible-light and thermal imaginary. The system first performs a simple calibration procedure to rectify the two camera views without knowing the cameras' intrinsic characteristics. Then a blob-to-blob homography is learned on-the-fly by estimating the disparity of each blob so that a pixel level registration can be achieved. The multi-modality information is then combined under a two-tier tracking algorithm and a unified background model to attain precise segmentation. Preliminary experimental results shows significant improvements over existing schemes under various difficult scenarios.

AB - This paper describes a system for robust segmentation of human in video sequences by fusing the visible-light and thermal imaginary. The system first performs a simple calibration procedure to rectify the two camera views without knowing the cameras' intrinsic characteristics. Then a blob-to-blob homography is learned on-the-fly by estimating the disparity of each blob so that a pixel level registration can be achieved. The multi-modality information is then combined under a two-tier tracking algorithm and a unified background model to attain precise segmentation. Preliminary experimental results shows significant improvements over existing schemes under various difficult scenarios.

UR - http://www.scopus.com/inward/record.url?scp=77953176859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953176859&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2009.5457476

DO - 10.1109/ICCVW.2009.5457476

M3 - Conference contribution

AN - SCOPUS:77953176859

SN - 9781424444427

T3 - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

SP - 1185

EP - 1192

BT - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

T2 - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

Y2 - 27 September 2009 through 4 October 2009

ER -

Human segmentation by fusing visible-light and thermal imaginary

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this