Graph Mining for Object Tracking in Videos
Abstract
This paper shows a concrete example of the use of graph mining for tracking objects in videos with moving cameras and without any contextual information on the objects to track. To make the mining algorithm efficient, we benefit from a video representation based on dynamic (evolving through time) planar graphs. We then define a number of constraints to efficiently find our so-called spatio-temporal graph patterns. Those patterns are linked through an occurrences graph to allow us to tackle occlusion or graph features instability problems in the video. Experiments on synthetic and real videos show that our method is effective and allows us to find relevant patterns for our tracking application.
Cite
Text
Diot et al. "Graph Mining for Object Tracking in Videos." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2012. doi:10.1007/978-3-642-33460-3_31Markdown
[Diot et al. "Graph Mining for Object Tracking in Videos." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2012.](https://mlanthology.org/ecmlpkdd/2012/diot2012ecmlpkdd-graph/) doi:10.1007/978-3-642-33460-3_31BibTeX
@inproceedings{diot2012ecmlpkdd-graph,
title = {{Graph Mining for Object Tracking in Videos}},
author = {Diot, Fabien and Fromont, Élisa and Jeudy, Baptiste and Marilly, Emmanuel and Martinot, Olivier},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2012},
pages = {394-409},
doi = {10.1007/978-3-642-33460-3_31},
url = {https://mlanthology.org/ecmlpkdd/2012/diot2012ecmlpkdd-graph/}
}