Simultaneous Localization and Mapping with Identification of Landmarks Based on Monocular Vision

Abstract:

Article Preview

How to identify objects is a hot issue of robot simultaneous localization and mapping (SLAM) with monocular vision. In this paper, an algorithm of wheeled robot’s simultaneous localization and mapping with identification of landmarks based on monocular vision is proposed. In observation steps, identifying landmarks and locating position are performed by image processing and analyzing, which converts vision image projection of wheeled robots and geometrical relations of spatial objects into calculating robots’ relative landmarks distance and angle. The integral algorithm procedure follows the recursive order of prediction, observation, data association, update, mapping to have simultaneous localization and map building. Compared with Active Vision algorithm, Three dimensional vision and stereo vision algorithm, the proposed algorithm is able to identify environmental objects and conduct smooth movement as well.

Info:

Periodical:

Edited by:

Helen Zhang and David Jin

Pages:

90-94

DOI:

10.4028/www.scientific.net/AMR.366.90

Citation:

Y. M. YI and Y. Hui, "Simultaneous Localization and Mapping with Identification of Landmarks Based on Monocular Vision", Advanced Materials Research, Vol. 366, pp. 90-94, 2012

Online since:

October 2011

Authors:

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.