A robust pedestrian detection approach in thermal infrared imageries for an all-day surveillance is proposed. Firstly, the candidate regions which are likely to contain pedestrians are extracted based on a saliency detection method. Then a deep convolutional network with a multi-task loss is constructed to recognize the pedestrians. The experimental results show the superiority of the proposed approach in pedestrian detection.
Ming XU
Northeastern University
Xiaosheng YU
Northeastern University
Chengdong WU
Northeastern University
Dongyue CHEN
Northeastern University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Ming XU, Xiaosheng YU, Chengdong WU, Dongyue CHEN, "Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 1, pp. 306-310, January 2018, doi: 10.1587/transfun.E101.A.306.
Abstract: A robust pedestrian detection approach in thermal infrared imageries for an all-day surveillance is proposed. Firstly, the candidate regions which are likely to contain pedestrians are extracted based on a saliency detection method. Then a deep convolutional network with a multi-task loss is constructed to recognize the pedestrians. The experimental results show the superiority of the proposed approach in pedestrian detection.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.306/_p
Copy
@ARTICLE{e101-a_1_306,
author={Ming XU, Xiaosheng YU, Chengdong WU, Dongyue CHEN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries},
year={2018},
volume={E101-A},
number={1},
pages={306-310},
abstract={A robust pedestrian detection approach in thermal infrared imageries for an all-day surveillance is proposed. Firstly, the candidate regions which are likely to contain pedestrians are extracted based on a saliency detection method. Then a deep convolutional network with a multi-task loss is constructed to recognize the pedestrians. The experimental results show the superiority of the proposed approach in pedestrian detection.},
keywords={},
doi={10.1587/transfun.E101.A.306},
ISSN={1745-1337},
month={January},}
Copy
TY - JOUR
TI - Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 306
EP - 310
AU - Ming XU
AU - Xiaosheng YU
AU - Chengdong WU
AU - Dongyue CHEN
PY - 2018
DO - 10.1587/transfun.E101.A.306
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2018
AB - A robust pedestrian detection approach in thermal infrared imageries for an all-day surveillance is proposed. Firstly, the candidate regions which are likely to contain pedestrians are extracted based on a saliency detection method. Then a deep convolutional network with a multi-task loss is constructed to recognize the pedestrians. The experimental results show the superiority of the proposed approach in pedestrian detection.
ER -