Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries

Ming XU; Xiaosheng YU; Chengdong WU; Dongyue CHEN

doi:10.1587/transfun.E101.A.306

Regular Section

Saliency Detection Based Region Extraction for Pedestrian Detection System with Thermal Imageries

Ming XU, Xiaosheng YU, Chengdong WU, Dongyue CHEN

Author information

Keywords: pedestrian detection, thermal infrared imageries, saliency detection, deep convolutional network

JOURNAL RESTRICTED ACCESS

2018 Volume E101.A Issue 1 Pages 306-310

DOI https://doi.org/10.1587/transfun.E101.A.306

Details

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.

Corresponding author

Register with J-STAGE for free!