RGB-D sensor based SLAM and human tracking with Bayesian framework for wheelchair robots

Bing-Fei Wu, Cheng Lung Jen, Wun Fang Li, Tai Yu Tsou, Pin Yi Tseng, Kai Tse Hsiao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Scopus citations

Abstract

In this paper, we present an approach to visual SLAM and human tracking for a wheelchair robot equipped with a Microsoft Kinect sensor that which is a novel sensing system that captures RGB and depth (RGB-D) images simultaneously. The speeded-up robust feature (SURF) algorithm is employed to provide the robust description of feature for environments and the target person from RGB images. Based on the environmental SURF features, we present the natural landmark based simultaneous localization and mapping with the extended Kalman filter suing RGB-D data. Meanwhile, a depth clustering based human detection is proposed to extract human candidates. Accordantly, the target person tracking is achieved with an online learned RGB-D appearance model by integrating histogram orientation of gradient descriptor, color, depth, and position information from the body of the identified caregiver. Moreover, a fuzzy based controller provides dynamical human following for the wheelchair robot with a desired interval. Consequently, the experimental results demonstrated the effectiveness and feasibility in real world environments.

Original languageEnglish
Title of host publication2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013 - Conference Proceedings
Pages110-115
Number of pages6
DOIs
StatePublished - 9 Sep 2013
Event2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013 - Tainan, Taiwan
Duration: 3 May 20132 Jun 2013

Publication series

Name2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013 - Conference Proceedings

Conference

Conference2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013
CountryTaiwan
CityTainan
Period3/05/132/06/13

Keywords

  • extended Kalman filter
  • human tracking
  • RGB-D
  • simultaneous localization and mapping
  • speeded up robust features

Fingerprint Dive into the research topics of 'RGB-D sensor based SLAM and human tracking with Bayesian framework for wheelchair robots'. Together they form a unique fingerprint.

  • Cite this

    Wu, B-F., Jen, C. L., Li, W. F., Tsou, T. Y., Tseng, P. Y., & Hsiao, K. T. (2013). RGB-D sensor based SLAM and human tracking with Bayesian framework for wheelchair robots. In 2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013 - Conference Proceedings (pp. 110-115). [6573544] (2013 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2013 - Conference Proceedings). https://doi.org/10.1109/ARIS.2013.6573544