Transactions of the Korean Society of Mechanical Engineers A (대한기계학회논문집A)

The Korean Society of Mechanical Engineers (대한기계학회)
권호 표지
DOI QR코드

DOI QR Code

People Tracking and Accompanying Algorithm for Mobile Robot Using Kinect Sensor and Extended Kalman Filter

키넥트센서와 확장칼만필터를 이용한 이동로봇의 사람추적 및 사람과의 동반주행

  • Park, Kyoung Jae (Dept. of Mechatronics Engineering, Chungnam Nat'l Univ.) ;
  • Won, Mooncheol (Dept. of Mechatronics Engineering, Chungnam Nat'l Univ.)
  • 박경재 (충남대학교 메카트로닉스 공학과) ;
  • 원문철 (충남대학교 메카트로닉스 공학과)
  • Received : 2012.11.29
  • Accepted : 2014.03.07
  • Published : 2014.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a real-time algorithm for estimating the relative position and velocity of a person with respect to a robot using a Kinect sensor and an extended Kalman filter (EKF). Additionally, we propose an algorithm for controlling the robot in the proximity of a person in a variety of modes. The algorithm detects the head and shoulder regions of the person using a histogram of oriented gradients (HOG) and a support vector machine (SVM). The EKF algorithm estimates the relative positions and velocities of the person with respect to the robot using data acquired by a Kinect sensor. We tested the various modes of proximity movement for a human in indoor situations. The accuracy of the algorithm was verified using a motion capture system.

본 논문에서는 키넥트센서(Kinect sensor)와 확장칼만필터(Extended Kalman Filter : EKF)를 이용하여 사람과 로봇간의 상대위치 및 각도와 상대속도를 실시간으로 추정하는 알고리즘을 제안한다. 또한, 다양한 이동모드에 따른 모바일로봇의 사람과의 근접동반이동 제어를 수행한다. HOG 및 SVM을 이용한 사람 두부 및 어깨 검출 알고리즘을 통해 사람을 검출하고, 키넥트센서의 정보를 이용해 EKF 알고리즘을 거쳐 사람과 로봇간의 상대위치 및 속도를 추정한다. EKF 알고리즘의 결과를 이용해 실내 환경에서 사람과 같이 근접동반주행을 하기 위한 다양한 모드의 제어 실험을 수행한다. 또한, 모션캡처장비(VICON)를 이용해 알고리즘의 정확도를 검증하였다.

Keywords

References

  1. http://www.care-o-bot.de/
  2. http://accompanyproject.eu/
  3. http://www.microsoft.com/en-us/kinectforwindows/
  4. TurtleBot, http://www.turtlebot.com/
  5. Roh, H. K. and Lee, S. W., 2001. "Multiple People Tracking Using an Appearance Model Based on Temporal Color," In Proc. Int. Conf. On Pattern Recognition, Vol. 4, pp. 643-646.
  6. Khoshelham, K., 2011, "Accuracy Analysis of Kinect Depth Data," In ISPRS Workshop Laser Scanning, volume XXXVIII.
  7. Dalal, N. and Triggs, B., 2005, "Histogram of Oriented Gradients for Human Detection," IEEE Conference on Computer Vision and Pattern Recognition CVPR. 177, USA, Vol. 1, pp. 886-893.
  8. Schapire, R. E., 2002, "The Boosting Approach to Machine Learning, an Overview," In MSRI Workshop on Nonlinear Estimation and Classification. Berkeley, CA, USA.
  9. Savtchenko, C. and Spletzer, J. R., "Sidewalk-Level People Tracking with a Low-Cost 3D LIDAR System."
  10. Ess, A., Schindler, K., Leibe, B. and L. Gool, V., 2010, "Object Detection and Tracking for Autonomous Navigation in Dynamic Environments," IJRR, Vol. 29, No. 14, pp. 1707-1725.
  11. Lee, J.-U., Sun, J.-Y. and Won, M., 2013, "Real Time Algorithm for Relative Position Estimation Between Person and Robot Using a Monocular Camera," Trans. Korean Soc. Mech. Eng. A, Vol. 37, No. 12, pp. 1445-1452. https://doi.org/10.3795/KSME-A.2013.37.12.1445

Cited by

  1. A Parallel Kalman Filter for Estimation of Magnetic Disturbance and Orientation Based on Nine-axis Inertial/Magnetic Sensor Signals vol.40, pp.7, 2016, https://doi.org/10.3795/KSME-A.2016.40.7.659
  2. Comparison of Acceleration-Compensating Mechanisms for Improvement of IMU-Based Orientation Determination vol.40, pp.9, 2016, https://doi.org/10.3795/KSME-A.2016.40.9.783