Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors
Abstract
This paper proposes a method for human detection in crowded scene from static images. An individual human is modeled as an assembly of natural body parts. We introduce edgelet features, which are a new type of silhouette oriented features. Part detectors, based on these features, are learned by a boosting method. Responses of part detectors are combined to form a joint likelihood model that includes cases of multiple, possibly inter-occluded humans. The human detection problem is formulated as maximum a posteriori (MAP) estimation. We show results on a commonly used previous dataset as well as new data sets that could not be processed by earlier methods.
Cite
Text
Wu and Nevatia. "Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.74Markdown
[Wu and Nevatia. "Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/wu2005iccv-detection/) doi:10.1109/ICCV.2005.74BibTeX
@inproceedings{wu2005iccv-detection,
title = {{Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors}},
author = {Wu, Bo and Nevatia, Ramakant},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2005},
pages = {90-97},
doi = {10.1109/ICCV.2005.74},
url = {https://mlanthology.org/iccv/2005/wu2005iccv-detection/}
}