For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries
Ming XU Xiaosheng YU Chengdong WU Dongyue CHEN
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2018/01/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
pedestrian detection, thermal infrared imageries, saliency detection, deep convolutional network,
Full Text: PDF(2MB)>>
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.