Conference/ProceedingsVisual Communications and Image Processing (VCIP), IS&T/SPIE's Electronic Imaging 2009
Start date18.01.2009
End date22.01.2009
AddressSan Jose, CA, USA
Author(s)Mustafa Karaman, Lutz Goldmann, Thomas Sikora
TitleImproving object segmentation by reflection detection and removal
AbstractFor object analysis in videos such as in video surveillance systems, the preliminary segmentation step is very important. Many segmentation methods using static camera have been proposed in the last decade, but they all suffer in occurrance of object reflection especially on the ground, i.e. reflected regions are also segmented as foregrounds. We present a new method which detects the border between the real object and its reflection. Experiments show that an outstanding improvement
of segmentation results are obtained by removing the reflection part of the over-segmented objects.
Key wordsobject segmentation, reflection detection, background subtraction