Robust System for Partially Occluded People Detection in RGB Images

Marcos Baptista-Ríos, Marta Marrón-Romera, Cristina Losada-Gutiérrez, José Angel Cruz-Lozano, Antonio del Abril

2017

Abstract

This work presents a robust system for people detection in RGB images. The proposal increases the robustness of previous approaches against partial occlusions, and it is based on a bank of individual detectors whose results are combined using a multimodal association algorithm. Each individual detector is trained for a different body part (full body, half top, half bottom, half left and half right body parts). It consists of two elements: a feature extractor that obtains a Histogram of Oriented Gradients (HOG) descriptor, and a Support Vector Machine (SVM) for classification. Several experimental tests have been carried out in order to validate the proposal, using INRIA and CAVIAR datasets, that have been widely used by the scientific community. The obtained results show that the association of all the body part detections presents a better accuracy that any of the parts individually. Regarding the body parts, the best results have been obtained for the full body and half top body.

Paper Citation

in Harvard Style

Baptista-Ríos M., Marrón-Romera M., Losada-Gutiérrez C., Angel Cruz-Lozano J. and del Abril A. (2017). Robust System for Partially Occluded People Detection in RGB Images . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 532-539. DOI: 10.5220/0006165005320539

in Bibtex Style

@conference{visapp17,
author={Marcos Baptista-Ríos and Marta Marrón-Romera and Cristina Losada-Gutiérrez and José Angel Cruz-Lozano and Antonio del Abril},
title={Robust System for Partially Occluded People Detection in RGB Images},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={532-539},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006165005320539},
isbn={978-989-758-225-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Robust System for Partially Occluded People Detection in RGB Images
SN - 978-989-758-225-7
AU - Baptista-Ríos M.
AU - Marrón-Romera M.
AU - Losada-Gutiérrez C.
AU - Angel Cruz-Lozano J.
AU - del Abril A.
PY - 2017
SP - 532
EP - 539
DO - 10.5220/0006165005320539