For feature point detection with variable scale, rotation, variable illumination and variable 3D view port, a feature point detection and tracking method combining scale invariant feature transform (SIFT) and KLT (Kanade-Lucas-Tomasi) is proposed in this paper. SIFT feature point detection method is improved and it is used to detect feature points of image, and then KLT method is used to track the feature points continuously. In order to verify the feasibility of the proposed method, simulation experiments are carried out in real scene image sequences with different complexity using this method, better results of detection and tracking are obtained and the obtained feature point is more stable than conventional method.

Date Published: 1 December 2009
PDF: 10 pages
Proc. SPIE 7506, 2009 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments, 75062N (1 December 2009); doi: 10.1117/12.838618

Published in SPIE Proceedings Vol. 7506:
2009 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments
Yongtian Wang; Yunlong Sheng; Kimio Tatsuno, Editor(s)