Illumination-Invariant Change Detection

D. Toth; T. Aach; V. Metzler

doi:10.1109/IAI.2000.839561

Illumination-Invariant Change Detection

D. Toth, T. Aach, V. Metzler

Institute of Signal Processing

87 Citations (Scopus)

Abstract

Moving objects in image sequences acquired by a static camera can be detected by analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes a method for motion detection that is considerably less sensitive to time-varying illumination. It is based on combining a motion detection algorithm with an homomorphic filter which effectively suppresses variable scene illumination. To this end, the acquired image sequence is modelled as being generated by an illumination and a reflectance component that are approximately separated by the filter. Detection of changes in the reflectance component is directly related to scene changes, i.e., object motion. Real video data are used to illustrate the system's performance.

Original language	English
Title of host publication	4th IEEE Southwest Symposium on Image Analysis and Interpretation
Number of pages	5
Publisher	IEEE
Publication date	01.01.2000
Pages	3-7
Article number	839561
ISBN (Print)	0-7695-0595-3
DOIs	https://doi.org/10.1109/IAI.2000.839561
Publication status	Published - 01.01.2000
Event	4th IEEE Southwest Symposium on Image Analysis and Interpretation - Austin, United States Duration: 02.04.2000 → 04.04.2000 Conference number: 116495

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1109/IAI.2000.839561

Cite this

@inproceedings{268cdd03d8da4229816e3694903b9a9f,

title = "Illumination-Invariant Change Detection",

abstract = "Moving objects in image sequences acquired by a static camera can be detected by analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes a method for motion detection that is considerably less sensitive to time-varying illumination. It is based on combining a motion detection algorithm with an homomorphic filter which effectively suppresses variable scene illumination. To this end, the acquired image sequence is modelled as being generated by an illumination and a reflectance component that are approximately separated by the filter. Detection of changes in the reflectance component is directly related to scene changes, i.e., object motion. Real video data are used to illustrate the system's performance.",

author = "D. Toth and T. Aach and V. Metzler",

year = "2000",

month = jan,

day = "1",

doi = "10.1109/IAI.2000.839561",

language = "English",

isbn = " 0-7695-0595-3",

series = "IEEE Proceedings",

publisher = "IEEE",

pages = "3--7",

booktitle = "4th IEEE Southwest Symposium on Image Analysis and Interpretation",

note = "4th IEEE Southwest Symposium on Image Analysis and Interpretation <br/>, SSIAI 2000 ; Conference date: 02-04-2000 Through 04-04-2000",

}

TY - GEN

T1 - Illumination-Invariant Change Detection

AU - Toth, D.

AU - Aach, T.

AU - Metzler, V.

N1 - Conference code: 116495

PY - 2000/1/1

Y1 - 2000/1/1

N2 - Moving objects in image sequences acquired by a static camera can be detected by analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes a method for motion detection that is considerably less sensitive to time-varying illumination. It is based on combining a motion detection algorithm with an homomorphic filter which effectively suppresses variable scene illumination. To this end, the acquired image sequence is modelled as being generated by an illumination and a reflectance component that are approximately separated by the filter. Detection of changes in the reflectance component is directly related to scene changes, i.e., object motion. Real video data are used to illustrate the system's performance.

AB - Moving objects in image sequences acquired by a static camera can be detected by analyzing the grey-level difference between successive frames. Direct motion detection, however, will also detect fast variations of scene illumination. This paper describes a method for motion detection that is considerably less sensitive to time-varying illumination. It is based on combining a motion detection algorithm with an homomorphic filter which effectively suppresses variable scene illumination. To this end, the acquired image sequence is modelled as being generated by an illumination and a reflectance component that are approximately separated by the filter. Detection of changes in the reflectance component is directly related to scene changes, i.e., object motion. Real video data are used to illustrate the system's performance.

UR - https://www.scopus.com/pages/publications/84950256727

U2 - 10.1109/IAI.2000.839561

DO - 10.1109/IAI.2000.839561

M3 - Conference contribution

SN - 0-7695-0595-3

T3 - IEEE Proceedings

SP - 3

EP - 7

BT - 4th IEEE Southwest Symposium on Image Analysis and Interpretation

PB - IEEE

T2 - 4th IEEE Southwest Symposium on Image Analysis and Interpretation <br/>

Y2 - 2 April 2000 through 4 April 2000

ER -

Illumination-Invariant Change Detection

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this