Human detection and tracking in an assistive living service robot through multimodal data fusion

Renxi Qiu; Alexandre Noyvirt

doi:10.1109/INDIN.2012.6301153

Human detection and tracking in an assistive living service robot through multimodal data fusion

Renxi Qiu
, Alexandre Noyvirt

Institute for Research in Applicable Computing (IRAC)

Cardiff University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

A new method is proposed for using a combination of measurements from a laser range finder and a depth camera in a data fusion process that benefits from each modality's strong side. The combination leads to a significantly improved performance of the human detection and tracking in comparison with what is achievable from the singular modalities. The useful information from both laser and depth camera is automatically extracted and combined in a Bayesian formulation that is estimated using a Markov Chain Monte Carlo (MCMC) sampling framework. The experiments show that this algorithm can track robustly multiple people in real world assistive robotics applications.

Original language	English
Title of host publication	nan
Publisher	Institute of Electrical and Electronics Engineers Inc.
DOIs	https://doi.org/10.1109/INDIN.2012.6301153
Publication status	Published - 13 Sept 2012
Event	IEEE 10th International Conference on Industrial Informatics - Beijing Duration: 25 Jul 2012 → 27 Jul 2012

Conference

Conference	IEEE 10th International Conference on Industrial Informatics
City	Beijing
Period	25/07/12 → 27/07/12
Other	IEEE 10th International Conference on Industrial Informatics (25/07/2012-27/07/2012, Beijing)

Keywords

Robotics
service robotics

Access to Document

10.1109/INDIN.2012.6301153

https://ieeexplore.ieee.org/document/6301153

Handle.net

Persistent link

Cite this

@inproceedings{908f3892776a40eeb930caf9dc8a8cf1,

title = "Human detection and tracking in an assistive living service robot through multimodal data fusion",

abstract = "A new method is proposed for using a combination of measurements from a laser range finder and a depth camera in a data fusion process that benefits from each modality's strong side. The combination leads to a significantly improved performance of the human detection and tracking in comparison with what is achievable from the singular modalities. The useful information from both laser and depth camera is automatically extracted and combined in a Bayesian formulation that is estimated using a Markov Chain Monte Carlo (MCMC) sampling framework. The experiments show that this algorithm can track robustly multiple people in real world assistive robotics applications.",

keywords = "Robotics, service robotics",

author = "Renxi Qiu and Alexandre Noyvirt",

year = "2012",

month = sep,

day = "13",

doi = "10.1109/INDIN.2012.6301153",

language = "English",

booktitle = "nan",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "IEEE 10th International Conference on Industrial Informatics ; Conference date: 25-07-2012 Through 27-07-2012",

}

TY - GEN

T1 - Human detection and tracking in an assistive living service robot through multimodal data fusion

AU - Qiu, Renxi

AU - Noyvirt, Alexandre

PY - 2012/9/13

Y1 - 2012/9/13

N2 - A new method is proposed for using a combination of measurements from a laser range finder and a depth camera in a data fusion process that benefits from each modality's strong side. The combination leads to a significantly improved performance of the human detection and tracking in comparison with what is achievable from the singular modalities. The useful information from both laser and depth camera is automatically extracted and combined in a Bayesian formulation that is estimated using a Markov Chain Monte Carlo (MCMC) sampling framework. The experiments show that this algorithm can track robustly multiple people in real world assistive robotics applications.

AB - A new method is proposed for using a combination of measurements from a laser range finder and a depth camera in a data fusion process that benefits from each modality's strong side. The combination leads to a significantly improved performance of the human detection and tracking in comparison with what is achievable from the singular modalities. The useful information from both laser and depth camera is automatically extracted and combined in a Bayesian formulation that is estimated using a Markov Chain Monte Carlo (MCMC) sampling framework. The experiments show that this algorithm can track robustly multiple people in real world assistive robotics applications.

KW - Robotics

KW - service robotics

U2 - 10.1109/INDIN.2012.6301153

DO - 10.1109/INDIN.2012.6301153

M3 - Conference contribution

BT - nan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE 10th International Conference on Industrial Informatics

Y2 - 25 July 2012 through 27 July 2012

ER -

Human detection and tracking in an assistive living service robot through multimodal data fusion

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this