DocumentCode :
2343184
Title :
Combining motion from texture and lines for visual navigation
Author :
Bitsakos, Konstantinos ; Yi, Li ; Fermüller, Cornelia
Author_Institution :
Univ. of Maryland, College Park
fYear :
2007
fDate :
Oct. 29 2007-Nov. 2 2007
Firstpage :
232
Lastpage :
239
Abstract :
Two novel methods for computing 3D structure information from video for a piecewise planar scene are presented. The first method is based on a new line constraint, which clearly separates the estimation of distance from the estimation of slant. The second method exploits the concepts of phase correlation to compute from the change of image frequencies of a textured plane, distance and slant information. The two different estimates together with structure estimates from classical image motion are combined and integrated over time using an extended Kalman filter. The estimation of the scene structure is demonstrated experimentally in a motion control algorithm that allows the robot to move along a corridor. We demonstrate the efficacy of each individual method and their combination and show that the method allows for visual navigation in textured as well as un-textured environments.
Keywords :
Kalman filters; image motion analysis; image texture; motion control; navigation; video signal processing; 3D structure information; extended Kalman filter; image frequencies; motion control; phase correlation; piecewise planar scene; textured plane; visual navigation; Cameras; Computer vision; Frequency; Layout; Motion estimation; Navigation; Optical computing; Robustness; Simultaneous localization and mapping; Speech processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-0912-9
Electronic_ISBN :
978-1-4244-0912-9
Type :
conf
DOI :
10.1109/IROS.2007.4399568
Filename :
4399568
Link To Document :
بازگشت