By Topic

Single image based depth estimation for robotic applications

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Anupa Sabnis ; Interdisciplinary Programme in Systems and Control, Indian Institute of Technology Bombay, Mumbai, India - 400076 ; Leena Vachhani

Goal of the robot vision is to exploit power of visual sensing to observe and perceive the environment and react it. Visual feedback is used to manipulate the robot among objects by estimating their depths. This paper presents a depth estimation technique based on the defocus blur associated with a camera setting. A sharp image of an object is obtained from a defocused image of the same object by applying sharpening filter. The defocused and sharp images of the object are used to calculate the spread parameter which is related to the object depth. The method calculates the constant camera parameters. The main advantage of this method is use of a single image by the robot to estimate depth. The method is independent of illumination condition and can be applied to the images with different edge orientations. Experiments on real scene images have demonstrated the feasibility of the proposed method for depth estimation. The results indicate that the depth estimation average errors are within two percent of true values. The proposed method is compared with the existing methods.

Published in:

Recent Advances in Intelligent Computational Systems (RAICS), 2011 IEEE

Date of Conference:

22-24 Sept. 2011