論文

査読有り
2014年5月

Automatic calibration of laser range finder positions for pedestrian tracking based on social group detections

ADVANCED ROBOTICS
  • Dylan F. Glas
  • ,
  • Florent Ferreri
  • ,
  • Takahiro Miyashita
  • ,
  • Hiroshi Ishiguro
  • ,
  • Norihiro Hagita

28
9
開始ページ
573
終了ページ
588
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1080/01691864.2013.879272
出版者・発行元
TAYLOR & FRANCIS LTD

Laser range finders (LRF's) are non-invasive sensors which can be used for high-precision and anonymous tracking of pedestrians in social environments. Such sensor networks can be used in robotics to assist in navigation and human-robot interaction. Typically, multiple LRF's are used together for such tasks, and the relative positions of these sensors must be precisely calibrated. We propose a technique for estimating relative LRF positions using observations of social groups in the pedestrian flow as keypoint features for determining coarse estimates of relative sensor offsets. The most likely offset is estimated using a generalized Hough transform and used to identify sets of possible shared observations of individual pedestrians between pairs of sensors. Outliers are rejected using the RANSAC technique, and the resulting shared observations from each sensor pair are combined into a constraint matrix for the sensor network, which is solved using least-squares minimization. Results show calibration accuracy of sensor positions within 34 mm and 0.51 degrees, and an analysis of pedestrian data collected from ubiquitous networks in three public and commercial spaces shows that the proposed calibration technique enables pedestrian tracking within 11 cm accuracy.

Web of Science ® 被引用回数 : 7

リンク情報
DOI
https://doi.org/10.1080/01691864.2013.879272
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000335932000001&DestApp=WOS_CPL
URL
http://dblp.uni-trier.de/db/journals/ar/ar28.html#journals/ar/GlasFMIH14

エクスポート
BibTeX RIS