Combining Intensity and Motion for Incremental Segmentation and Tracking over Long Image Sequences
Abstract
This paper presents a method for incrementally segmenting images over time using both intensity and motion information. This is done by formulating a model of physically significant image resgions using local constraints on intensity and motion and then finding the optimal segmentation over time using an incremental stochastic minimization technique. The result is a robust and dynamic segmentation of the scene over a sequence of images. The approach has a number of benefits. First, discontinuities are extracted and tracked simultaneously. Second, a segmentation is always available and it improves over time. Finally, by combining motion and intensity, the structural properties of discontinuities can be recovered; that is, discontinuities can be classified as surface markings or actual surface boundaries .
Cite
Text
Black. "Combining Intensity and Motion for Incremental Segmentation and Tracking over Long Image Sequences." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_54Markdown
[Black. "Combining Intensity and Motion for Incremental Segmentation and Tracking over Long Image Sequences." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/black1992eccv-combining/) doi:10.1007/3-540-55426-2_54BibTeX
@inproceedings{black1992eccv-combining,
title = {{Combining Intensity and Motion for Incremental Segmentation and Tracking over Long Image Sequences}},
author = {Black, Michael J.},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {485-493},
doi = {10.1007/3-540-55426-2_54},
url = {https://mlanthology.org/eccv/1992/black1992eccv-combining/}
}