Human Re-Identification with a Robot Thermal Camera using Entropy-based Sampling

Date

2019-05-15

Advisors

Journal Title

Journal ISSN

ISSN

Volume Title

Publisher

Springer

Type

Article

Peer reviewed

Yes

Abstract

Human re-identification is an important feature of domestic service robots, in particular for elderly monitoring and assistance, because it allows them to perform personalized tasks and human-robot interactions. However vision-based reidentification systems are subject to limitations due to human pose and poor lighting conditions. This paper presents a new re-identification method for service robots using thermal images. In robotic applications, as the number and size of thermal datasets is limited, it is hard to use approaches that require huge amount of training samples. We propose a re-identification system that can work using only a small amount of data. During training, we perform entropy-based sampling to obtain a thermal dictionary for each person. Then, a symbolic representation is produced by converting each video into sequences of dictionary elements. Finally, we train a classifier using this symbolic representation and geometric distribution within the new representation domain. The experiments are performed on a new thermal dataset for human re-identification, which includes various situations of human motion, poses and occlusion, and which is made publicly available for research purposes. The proposed approach has been tested on this dataset and its improvements over standard approaches have been demonstrated.

Description

open access article

Keywords

Service robots, Re-identification, Elderly care, Thermal camera, Occlusion, Body motion

Citation

Coşar, S., Bellotto, N. (2019) Human Re-Identification with a Robot Thermal Camera Using Entropy-Based Sampling. Journal of Intelligent & Robotic Systems,

Rights

Research Institute

Institute of Engineering Sciences (IES)