Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor

Kouyou Shimura; Yoshinobu Ando; Takashi Yoshimi; Makoto Mizukawa

doi:10.1109/SII.2014.7028055

Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor

Kouyou Shimura, Yoshinobu Ando, Takashi Yoshimi, Makoto Mizukawa

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

9 Citations (Scopus)

Abstract

In this study, we develop a person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. The sensor system is composed of multiple Kinect sensors, we call it 'Multi-Kinect'. Since the field of view of a single Kinect sensor is narrow, this sensor makes it wider by using three Kinect sensors. Furthermore, the system selects a person who raises hand or says 'Start' as the target of following at the beginning. Then, the system can identify a person from the person location and characteristics of clothes and re-recognizes the target of following when an occlusion occurs. Herewith, a mobile robot with this sensor accomplishes a human detection and follows only the target of following even if more than two people is located around the robot.

Original language	English
Title of host publication	2014 IEEE/SICE International Symposium on System Integration, SII 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	304-309
Number of pages	6
ISBN (Electronic)	9781479969449
DOIs	https://doi.org/10.1109/SII.2014.7028055
Publication status	Published - 2014 Jan 30
Event	7th IEEE/SICE International Symposium on System Integration, SII 2014 - Tokyo, Japan Duration: 2014 Dec 13 → 2014 Dec 15

Other

Other	7th IEEE/SICE International Symposium on System Integration, SII 2014
Country	Japan
City	Tokyo
Period	14/12/13 → 14/12/15

ASJC Scopus subject areas

Control and Systems Engineering
Computer Networks and Communications
Information Systems

Access to Document

10.1109/SII.2014.7028055

Fingerprint Dive into the research topics of 'Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor'. Together they form a unique fingerprint.

Cite this

Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. / Shimura, Kouyou; Ando, Yoshinobu ; Yoshimi, Takashi; Mizukawa, Makoto.

2014 IEEE/SICE International Symposium on System Integration, SII 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 304-309 7028055.

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

Shimura, K, Ando, Y , Yoshimi, T & Mizukawa, M 2014, Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. in 2014 IEEE/SICE International Symposium on System Integration, SII 2014., 7028055, Institute of Electrical and Electronics Engineers Inc., pp. 304-309, 7th IEEE/SICE International Symposium on System Integration, SII 2014, Tokyo, Japan, 14/12/13. https://doi.org/10.1109/SII.2014.7028055

@inproceedings{ef83069b7ba044b3843bafda70272f25,

title = "Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor",

abstract = "In this study, we develop a person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. The sensor system is composed of multiple Kinect sensors, we call it 'Multi-Kinect'. Since the field of view of a single Kinect sensor is narrow, this sensor makes it wider by using three Kinect sensors. Furthermore, the system selects a person who raises hand or says 'Start' as the target of following at the beginning. Then, the system can identify a person from the person location and characteristics of clothes and re-recognizes the target of following when an occlusion occurs. Herewith, a mobile robot with this sensor accomplishes a human detection and follows only the target of following even if more than two people is located around the robot.",

author = "Kouyou Shimura and Yoshinobu Ando and Takashi Yoshimi and Makoto Mizukawa",

year = "2014",

month = jan,

day = "30",

doi = "10.1109/SII.2014.7028055",

language = "English",

pages = "304--309",

booktitle = "2014 IEEE/SICE International Symposium on System Integration, SII 2014",

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

address = "United States",

note = "7th IEEE/SICE International Symposium on System Integration, SII 2014 ; Conference date: 13-12-2014 Through 15-12-2014",

}

TY - GEN

T1 - Research on person following system based on RGB-D features by autonomous robot with multi-Kinect sensor

AU - Shimura, Kouyou

AU - Ando, Yoshinobu

AU - Yoshimi, Takashi

AU - Mizukawa, Makoto

PY - 2014/1/30

Y1 - 2014/1/30

N2 - In this study, we develop a person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. The sensor system is composed of multiple Kinect sensors, we call it 'Multi-Kinect'. Since the field of view of a single Kinect sensor is narrow, this sensor makes it wider by using three Kinect sensors. Furthermore, the system selects a person who raises hand or says 'Start' as the target of following at the beginning. Then, the system can identify a person from the person location and characteristics of clothes and re-recognizes the target of following when an occlusion occurs. Herewith, a mobile robot with this sensor accomplishes a human detection and follows only the target of following even if more than two people is located around the robot.

AB - In this study, we develop a person following system based on RGB-D features by autonomous robot with multi-Kinect sensor. The sensor system is composed of multiple Kinect sensors, we call it 'Multi-Kinect'. Since the field of view of a single Kinect sensor is narrow, this sensor makes it wider by using three Kinect sensors. Furthermore, the system selects a person who raises hand or says 'Start' as the target of following at the beginning. Then, the system can identify a person from the person location and characteristics of clothes and re-recognizes the target of following when an occlusion occurs. Herewith, a mobile robot with this sensor accomplishes a human detection and follows only the target of following even if more than two people is located around the robot.

UR - http://www.scopus.com/inward/record.url?scp=84988264985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988264985&partnerID=8YFLogxK

U2 - 10.1109/SII.2014.7028055

DO - 10.1109/SII.2014.7028055

M3 - Conference contribution

AN - SCOPUS:84988264985

SP - 304

EP - 309

BT - 2014 IEEE/SICE International Symposium on System Integration, SII 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th IEEE/SICE International Symposium on System Integration, SII 2014

Y2 - 13 December 2014 through 15 December 2014

ER -