Navigable points estimation for mobile robots using binary image skeletonization

Fernando Martinez S.; Edwar Jacinto G.; Holman Montiel A.

doi:10.1117/12.2267042

8 February 2017 Navigable points estimation for mobile robots using binary image skeletonization

Fernando Martinez S., Edwar Jacinto G., Holman Montiel A.

Proceedings Volume 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016); 1022505 (2017) https://doi.org/10.1117/12.2267042
Event: Eighth International Conference on Graphic and Image Processing, 2016, Tokyo, Japan

Abstract

This paper describes the use of image skeletonization for the estimation of all the navigable points, inside a scene of mobile robots navigation. Those points are used for computing a valid navigation path, using standard methods. The main idea is to find the middle and the extreme points of the obstacles in the scene, taking into account the robot size, and create a map of navigable points, in order to reduce the amount of information for the planning algorithm. Those points are located by means of the skeletonization of a binary image of the obstacles and the scene background, along with some other digital image processing algorithms. The proposed algorithm automatically gives a variable number of navigable points per obstacle, depending on the complexity of its shape. As well as, the way how the algorithm can change some of their parameters in order to change the final number of the resultant key points is shown. The results shown here were obtained applying different kinds of digital image processing algorithms on static scenes.

Citation Download Citation

Fernando Martinez S., Edwar Jacinto G., and Holman Montiel A. "Navigable points estimation for mobile robots using binary image skeletonization", Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 1022505 (8 February 2017); https://doi.org/10.1117/12.2267042

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available