Home > Archive > 2020 > Volume 10 Number 2 (Feb. 2020) >
IJMLC 2020 Vol.10(2): 393-399 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2020.10.2.948

A Hybrid Approach for Dynamic Observer to Detect and Track Dynamic Obstacles

Sudeepta Ranjan Sahoo and P. V. Manivannan

Abstract—This paper deals with the detection of a dynamic obstacle with the use of a low-cost monocular camera mounted on a dynamic vehicle. An algorithm has been developed to integrate feature tracking, Image transformation, and optical flow. Optical flow method is used to detect a moving obstacle in a static environment. Camera motion causes the environment to be dynamic with the point of view of the observer thereby leading to the failure of optical flow algorithm. The difficulty in distinguishing the difference between moving and a stationary body can be overcome with the use of image transformation technique, which transforms the newly captured image to the coordinate frame of the previous image. The optical flow algorithm can now be applied to detect a dynamic obstacle. To further find the position of the obstacle in 3D space with respect to the camera, Stereo vision system is used. The developed algorithm has been tested in a virtual environment using V-rep and Matlab. The algorithm has also been validated experimentally with the use of a stereo camera system on a mobile platform-P3-DX.

Index Terms—Optical flow, feature point matching, first corner method, image transformation, stereo vision, V-rep, P3-DX, VICON.

The authors are with Department of Mechanical Enginearing IIT Madras, Chennai-600036 India (e-mail: sahoo.sudeepta71@gmail.com, pvm@iitm.ac.in).


Cite: Sudeepta Ranjan Sahoo and P. V. Manivannan, "A Hybrid Approach for Dynamic Observer to Detect and Track Dynamic Obstacles," International Journal of Machine Learning and Computing vol. 10, no. 2, pp. 393-399, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net

Article Metrics in Dimensions