Title :
A flexible method for 3D reconstruction of urban building
Author :
Xin Du ; Yun-fang Zhu
Author_Institution :
Dept. of Inf. & Electron. Eng., Zhejiang Univ., Hangzhou
Abstract :
In this paper, a new method for 3D reconstruction of urban building based on computer vision was presented. Sequence of images was captured by a single camera. Feature points in the images were firstly extracted and tracked, and then the trajectories were analyzed. Intrinsic and external parameters of camera were derived from self-calibration, and then 3D information of objective building was finally reconstructed. Experimental results indicated that the proposed method was effective and flexible. It could be applied to city planning, building measurement, virtual reality, etc.
Keywords :
computer vision; feature extraction; image reconstruction; image sequences; matrix algebra; 3D information; 3D reconstruction; computer vision; image sequence; self-calibration; single camera; urban building; Buildings; Cameras; Computer vision; Data acquisition; Equations; Image reconstruction; Layout; Stereo vision; Urban planning; Virtual reality;
Conference_Titel :
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2178-7
Electronic_ISBN :
978-1-4244-2179-4
DOI :
10.1109/ICOSP.2008.4697383
