Title :
Image registration based on KLT feature tracker in image mosaicing application
Author :
Zhilong, Shu ; Qiuqi, Ruan
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
Image mosaicing has many applications, such as generating panoramas, video surveillance, MPEG-4 encoding, image based rendering, etc. The critical technique of image mosaicing is image registration. In this paper a new, efficient and robust method based on phase correlation and KLT feature tracker is developed for image registration and applied in image mosaicing. The KLT feature tracker refines the result of phase correlation and gives a better initial value for the Levenberg-Marquard (L-M) algorithm, so a global optimal solution can be obtained
Keywords :
Karhunen-Loeve transforms; correlation methods; feature extraction; image registration; image segmentation; KLT feature tracker; L-M algorithm; Levenberg-Marquard algorithm; MPEG-4 encoding; efficient method; image based rendering; image mosaicing; image registration; optimal solution; panorama generation; phase correlation; robust method; video surveillance; Fourier transforms; Image coding; Image registration; Information science; Karhunen-Loeve transforms; MPEG 4 Standard; Phase noise; Rendering (computer graphics); Robustness; Video surveillance;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891743
