Title :
Binocular Vision-SLAM Using Improved SIFT Algorithm
Author_Institution :
Commun. & Inf. Eng. Coll., Xi´an Univ. of Sci. & Technol., Xi´an, China
Abstract :
SIFT (Scale Invariant Feature Transform) algorithm is used in mobile robot Simultaneous Localization and Mapping (SLAM) based on visual information. But this algorithm is complicated and computation time is long. Two improvements are introduced to optimize its performance. Firstly, the linear combination of cityblock distance and chessboard distance is comparability measurement; secondly, partial features are used to matching. SLAM is completed by fusing the information of SIFT features and robot information with EKF. The simulation experiment indicate that the proposed method reduce computational complexity, and with high localization precision in indoor environments.
Keywords :
Kalman filters; SLAM (robots); feature extraction; mobile robots; robot vision; stereo image processing; transforms; EKF; SIFT algorithm; binocular vision; chessboard distance; cityblock distance; extended Kalman filter; mobile robot; scale invariant feature transform; simultaneous localization and mapping; Cameras; Computational modeling; Data mining; Feature extraction; Filters; Indoor environments; Mobile robots; Pixel; Robot vision systems; Simultaneous localization and mapping;
Conference_Titel :
Intelligent Systems and Applications (ISA), 2010 2nd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5872-1
Electronic_ISBN :
978-1-4244-5874-5
DOI :
10.1109/IWISA.2010.5473273
