DocumentCode :
1964028
Title :
Illumination-invariant change detection
Author :
Toth, Daniel ; Aach, Til ; Metzler, Volker
Author_Institution :
Ist. for Signal Process., Lubeck Univ., Germany
fYear :
2000
fDate :
2000
Firstpage :
3
Lastpage :
7
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
Keywords :
filtering theory; image sequences; motion estimation; object detection; video signal processing; approximate separation; grey-level difference; homomorphic filter; illumination-invariant change detection; image sequences; motion detection; moving object detection; reflectance; system performance; time-varying illumination; video data; Cameras; Filters; Image analysis; Image sequence analysis; Image sequences; Layout; Lighting; Motion detection; Object detection; Reflectivity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Analysis and Interpretation, 2000. Proceedings. 4th IEEE Southwest Symposium
Conference_Location :
Austin, TX
Print_ISBN :
0-7695-0595-3
Type :
conf
DOI :
10.1109/IAI.2000.839561
Filename :
839561
Link To Document :
بازگشت