Cargando…

Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF

One of the main challenges in intelligent vehicles concerns pedestrian detection for driving assistance. Recent experiments have showed that state-of-the-art descriptors provide better performances on the far-infrared (FIR) spectrum than on the visible one, even in daytime conditions, for pedestrian...

Descripción completa

Detalles Bibliográficos
Autores principales: Besbes, Bassem, Rogozan, Alexandrina, Rus, Adela-Maria, Bensrhair, Abdelaziz, Broggi, Alberto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4431237/
https://www.ncbi.nlm.nih.gov/pubmed/25871724
http://dx.doi.org/10.3390/s150408570
_version_ 1782371305076555776
author Besbes, Bassem
Rogozan, Alexandrina
Rus, Adela-Maria
Bensrhair, Abdelaziz
Broggi, Alberto
author_facet Besbes, Bassem
Rogozan, Alexandrina
Rus, Adela-Maria
Bensrhair, Abdelaziz
Broggi, Alberto
author_sort Besbes, Bassem
collection PubMed
description One of the main challenges in intelligent vehicles concerns pedestrian detection for driving assistance. Recent experiments have showed that state-of-the-art descriptors provide better performances on the far-infrared (FIR) spectrum than on the visible one, even in daytime conditions, for pedestrian classification. In this paper, we propose a pedestrian detector with on-board FIR camera. Our main contribution is the exploitation of the specific characteristics of FIR images to design a fast, scale-invariant and robust pedestrian detector. Our system consists of three modules, each based on speeded-up robust feature (SURF) matching. The first module allows generating regions-of-interest (ROI), since in FIR images of the pedestrian shapes may vary in large scales, but heads appear usually as light regions. ROI are detected with a high recall rate with the hierarchical codebook of SURF features located in head regions. The second module consists of pedestrian full-body classification by using SVM. This module allows one to enhance the precision with low computational cost. In the third module, we combine the mean shift algorithm with inter-frame scale-invariant SURF feature tracking to enhance the robustness of our system. The experimental evaluation shows that our system outperforms, in the FIR domain, the state-of-the-art Haar-like Adaboost-cascade, histogram of oriented gradients (HOG)/linear SVM (linSVM) and MultiFtrpedestrian detectors, trained on the FIR images.
format Online
Article
Text
id pubmed-4431237
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-44312372015-05-19 Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF Besbes, Bassem Rogozan, Alexandrina Rus, Adela-Maria Bensrhair, Abdelaziz Broggi, Alberto Sensors (Basel) Article One of the main challenges in intelligent vehicles concerns pedestrian detection for driving assistance. Recent experiments have showed that state-of-the-art descriptors provide better performances on the far-infrared (FIR) spectrum than on the visible one, even in daytime conditions, for pedestrian classification. In this paper, we propose a pedestrian detector with on-board FIR camera. Our main contribution is the exploitation of the specific characteristics of FIR images to design a fast, scale-invariant and robust pedestrian detector. Our system consists of three modules, each based on speeded-up robust feature (SURF) matching. The first module allows generating regions-of-interest (ROI), since in FIR images of the pedestrian shapes may vary in large scales, but heads appear usually as light regions. ROI are detected with a high recall rate with the hierarchical codebook of SURF features located in head regions. The second module consists of pedestrian full-body classification by using SVM. This module allows one to enhance the precision with low computational cost. In the third module, we combine the mean shift algorithm with inter-frame scale-invariant SURF feature tracking to enhance the robustness of our system. The experimental evaluation shows that our system outperforms, in the FIR domain, the state-of-the-art Haar-like Adaboost-cascade, histogram of oriented gradients (HOG)/linear SVM (linSVM) and MultiFtrpedestrian detectors, trained on the FIR images. MDPI 2015-04-13 /pmc/articles/PMC4431237/ /pubmed/25871724 http://dx.doi.org/10.3390/s150408570 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Besbes, Bassem
Rogozan, Alexandrina
Rus, Adela-Maria
Bensrhair, Abdelaziz
Broggi, Alberto
Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title_full Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title_fullStr Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title_full_unstemmed Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title_short Pedestrian Detection in Far-Infrared Daytime Images Using a Hierarchical Codebook of SURF
title_sort pedestrian detection in far-infrared daytime images using a hierarchical codebook of surf
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4431237/
https://www.ncbi.nlm.nih.gov/pubmed/25871724
http://dx.doi.org/10.3390/s150408570
work_keys_str_mv AT besbesbassem pedestriandetectioninfarinfrareddaytimeimagesusingahierarchicalcodebookofsurf
AT rogozanalexandrina pedestriandetectioninfarinfrareddaytimeimagesusingahierarchicalcodebookofsurf
AT rusadelamaria pedestriandetectioninfarinfrareddaytimeimagesusingahierarchicalcodebookofsurf
AT bensrhairabdelaziz pedestriandetectioninfarinfrareddaytimeimagesusingahierarchicalcodebookofsurf
AT broggialberto pedestriandetectioninfarinfrareddaytimeimagesusingahierarchicalcodebookofsurf