ML Anthology

Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps

Antonio Hernández-Vela, Nadezhda Zlateva, Alexander Marinov, Miguel Reyes, Petia Radeva, Dimo Dimov, Sergio Escalera
CVPR 2012 pp. 726-732
doi:10.1109/CVPR.2012.6247742 /cvpr/2012/hernandezvela2012cvpr-graph/

Abstract

We present a generic framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs in depth maps. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α-β swap Graph-cuts algorithm. Moreover, depth of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.

PDF CVPR Semantic Scholar

Cite

Text

Hernández-Vela et al. "Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247742

Markdown

[Hernández-Vela et al. "Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/hernandezvela2012cvpr-graph/) doi:10.1109/CVPR.2012.6247742

BibTeX

@inproceedings{hernandezvela2012cvpr-graph,
  title     = {{Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps}},
  author    = {Hernández-Vela, Antonio and Zlateva, Nadezhda and Marinov, Alexander and Reyes, Miguel and Radeva, Petia and Dimov, Dimo and Escalera, Sergio},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {726-732},
  doi       = {10.1109/CVPR.2012.6247742},
  url       = {https://mlanthology.org/cvpr/2012/hernandezvela2012cvpr-graph/}
}