Illumination invariant feature-based motion estimation

Dong Wang; Yue Lu; Zhigang Wang; Wei Wang; Xiaoming Xu

doi:10.1117/12.441569

Illumination invariant feature-based motion estimation

Dong Wang, Yue Lu, Zhigang Wang, Wei Wang, Xiaoming Xu

Shanghai Jiao Tong University

Research output: Contribution to journal › Conference article › peer-review

Abstract

Illumination variance will reduce the correctness of motion estimation result. To improve ME algorithms' robustness, some algorithms have been proposed. All those algorithms are based on the intensity illumination models and many important color information are ignored. Therefore, in this paper, starting from the color reflection model, we propose a novel illumination invariant feature named NACD. Based on NACD, the improved ME algorithm, FC-ME, is designed to deal with the illumination variant image sequences. The experiments indicate that with the acceptable additional operations, the new algorithm's robustness to illumination variance is improved obviously.

Original language	English
Pages (from-to)	50-55
Number of pages	6
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4553
DOIs	https://doi.org/10.1117/12.441569
State	Published - 2001
Externally published	Yes
Event	Visualization and Optimization Techniques - Wuhan, China Duration: 22 Oct 2001 → 24 Oct 2001

Keywords

Feature-based
Illumination invariant
Motion estimation

Access to Document

10.1117/12.441569

Cite this

@article{118266e1d4be48489da15419c5864684,

title = "Illumination invariant feature-based motion estimation",

abstract = "Illumination variance will reduce the correctness of motion estimation result. To improve ME algorithms' robustness, some algorithms have been proposed. All those algorithms are based on the intensity illumination models and many important color information are ignored. Therefore, in this paper, starting from the color reflection model, we propose a novel illumination invariant feature named NACD. Based on NACD, the improved ME algorithm, FC-ME, is designed to deal with the illumination variant image sequences. The experiments indicate that with the acceptable additional operations, the new algorithm's robustness to illumination variance is improved obviously.",

keywords = "Feature-based, Illumination invariant, Motion estimation",

author = "Dong Wang and Yue Lu and Zhigang Wang and Wei Wang and Xiaoming Xu",

year = "2001",

doi = "10.1117/12.441569",

language = "英语",

volume = "4553",

pages = "50--55",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Visualization and Optimization Techniques ; Conference date: 22-10-2001 Through 24-10-2001",

}

TY - JOUR

T1 - Illumination invariant feature-based motion estimation

AU - Wang, Dong

AU - Lu, Yue

AU - Wang, Zhigang

AU - Wang, Wei

AU - Xu, Xiaoming

PY - 2001

Y1 - 2001

N2 - Illumination variance will reduce the correctness of motion estimation result. To improve ME algorithms' robustness, some algorithms have been proposed. All those algorithms are based on the intensity illumination models and many important color information are ignored. Therefore, in this paper, starting from the color reflection model, we propose a novel illumination invariant feature named NACD. Based on NACD, the improved ME algorithm, FC-ME, is designed to deal with the illumination variant image sequences. The experiments indicate that with the acceptable additional operations, the new algorithm's robustness to illumination variance is improved obviously.

AB - Illumination variance will reduce the correctness of motion estimation result. To improve ME algorithms' robustness, some algorithms have been proposed. All those algorithms are based on the intensity illumination models and many important color information are ignored. Therefore, in this paper, starting from the color reflection model, we propose a novel illumination invariant feature named NACD. Based on NACD, the improved ME algorithm, FC-ME, is designed to deal with the illumination variant image sequences. The experiments indicate that with the acceptable additional operations, the new algorithm's robustness to illumination variance is improved obviously.

KW - Feature-based

KW - Illumination invariant

KW - Motion estimation

UR - https://www.scopus.com/pages/publications/0035768287

U2 - 10.1117/12.441569

DO - 10.1117/12.441569

M3 - 会议文章

AN - SCOPUS:0035768287

SN - 0277-786X

VL - 4553

SP - 50

EP - 55

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Visualization and Optimization Techniques

Y2 - 22 October 2001 through 24 October 2001

ER -

Illumination invariant feature-based motion estimation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this