Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images
Abstract
Results are presented for a new method to identify images of moving objects in a sequence of scene images, e.g. from a TV-camera observing a street intersection. The reported approach exploits the assumption that systematic greyvalue differences-based on second order statistics- between consecutive frames are due to images of moving objects. No knowledge is assumed about size, shape, or texture for images of stationary or non-stationary scene components. 1.
Cite
Text
Jain et al. "Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images." International Joint Conference on Artificial Intelligence, 1977.Markdown
[Jain et al. "Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images." International Joint Conference on Artificial Intelligence, 1977.](https://mlanthology.org/ijcai/1977/jain1977ijcai-separating/)BibTeX
@inproceedings{jain1977ijcai-separating,
title = {{Separating Non-Stationary from Stationary Scene Components in a Sequence of Real World TV Images}},
author = {Jain, Ramesh C. and Militzer, D. and Nagel, Hans-Hellmut},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1977},
pages = {612-618},
url = {https://mlanthology.org/ijcai/1977/jain1977ijcai-separating/}
}