Title :
Simultaneous parameter estimation and object segmentation from image sequences
Author :
Matthews, Kristine E. ; Namazi, Nader M.
Author_Institution :
Dept. of Electr. Eng., Catholic Univ. of America, Washington, DC, USA
Abstract :
Previously (see Proc. ICIP, vol.1, p.542-5, 1995) we proposed a method for segmenting an image in a sequence of images into regions of stationary, moving, and uncovered background pixels and simultaneously estimating parameters of each region. This previous work focused on the viability of the idea and considered only moving and stationary pixels. In this paper we present an extension of the formulation to include uncovered background pixels and multiple object segmentation. We show segmentations and reconstructed image frames for synthetic image sequences
Keywords :
image reconstruction; image segmentation; image sequences; maximum likelihood estimation; motion compensation; motion estimation; parameter estimation; EM algorithm; expectation-maximisation algorithm; multiple object segmentation; parameter estimation; reconstructed image frames; synthetic image sequences; uncovered background pixels; Additive white noise; Background noise; Gaussian noise; Image segmentation; Image sequences; Motion detection; Motion estimation; Object segmentation; Parameter estimation; Pixel;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.544839
