OS2-3 Distance measurement algorithm based on the object recognition

Title:	OS2-3 Distance measurement algorithm based on the object recognition
Publication:	ICAROB2018
Volume:	23
Pages:	290-293
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2018.OS2-3
Author(s):	Ho-sun Kang, Na-hyun Lee, Jang-myoung Lee
Publication Date:	February 2, 2018
Keywords:	Autonomous navigation system, key-point matching algorithm
Abstract:	This paper implements an algorithm that recognized an object using a vision system and measured the distance to the object. Autonomous navigation systems such as UAV (Unmanned Aerial Vehicle) and AUV (Autonomous Underwater Vehicle) have been a world-wide trend in recent year. To operate these systems safely, it is necessary to recognize obstacles on the moving path accurately and quickly. Generally, various sensors are used to recognize the surrounding environment. These methods are affected by disturbance caused by the surrounding environment. To overcome these drawbacks, this paper proposes an obstacle recognition algorithm using a stereo camera. For obstacle recognition, disparity is obtained by removing the remaining part of the object except the recognized object from the image to improve the computation speed. Finally, after calculating the distance, we confirm the algorithm by comparing with the actual distance.
PDF File:	https://alife-robotics.co.jp/members2018/icarob/data/html/data/OS_pdf/OS2/OS2-3.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

HOME