[1]ZHANG Yuan-yuan,WU Xiao-juan,LI Xiu-yuan,et al.Extraction of 3D coordinates using parallel lines in monocular images[J].CAAI Transactions on Intelligent Systems,2010,5(1):24-29.
Copy

Extraction of 3D coordinates using parallel lines in monocular images

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 5 Number of periods: 2010 1 Page number: 24-29 Column: 学术论文—人工智能基础 Public date: 2010-02-25
Title:
Extraction of 3D coordinates using parallel lines in monocular images
Author(s):
ZHANG Yuan-yuan1;  WU Xiao-juan1;  LI Xiu-yuan1;  RUAN Qiu-qi2
1.School of Information Science and Technology, Shandong University, Ji’nan 250100, China;
2. Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China
Keywords:
3D reconstruction;  monocular camera;  parallel lines constraint;  coordinate conversion factor;  coordinates recovery
CLC:
TP391
DOI:
-
Abstract:
A method was proposed to simplify the extraction of 3D coordinates from spatial points in 2D images captured by a monocular camera. Assume that two parallel lines could be known in the image, and also that their relative positions with respect to the video camera were known. In the camera coordinate system, the projection of any spatial point in the plane determined by parallel lines to the image plane of the camera could be measured. By applying the knowledge of projection geometry, a coordinate conversion factor (CCF) for the given point was then calculated; these were used to estimate 3D spatial coordinates. Estimations of the paths of people walking were then done to analyze the effectiveness of this method. Results showed that the proposed algorithm is simple and effective, and has low computational costs.
References:
［1］马颂德,张正友.计算机视觉［M］.北京：科学出版社，1998： 5298.
?［2］李立冬, 刘教民. 单目视图下相机标定和平面测距研究［J］. 河北科技大学学报， 2005, 26(1): 4750.
LI Lidong, LIU Jiaomin. Research on camera calibration and plane measurement from a single view［J］. Journal of Hebei University of Science and Technology, 2005, 26(1):4750.
［3］CHEUNG K M, BAKER S, KANADE T. Shape from silhouette of articulated objects and its use for human body kinematics estimation and motion capture［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, 1: 1820. 
［4］CHEUNG K M, BAKER S, HODGINS J K, et al. Markerless human motion transfer［C］// Proceedings of 2nd International Symposium on 3D Data Processing, Visualization and Transmission. Thessaloniki, Greece, 2004: 373378.
［5］CHEUNG K M, BAKER S, KANADE T. Shape from silhouette across time, part I: theory and algorithms［J］. International Journal of Computer Vision, 2005, 62(3): 221 247.
［6］MIKIC I, TRIVEDI M, HUNTER E, et al. Human body model acquisition and tracking using voxel data［J］. International Journal of Computer Vision, 2003, 33(3): 199223. .
［7］SMINCHISESCU C, TELEA A. Human pose estimation from silhouettes: a consistent approach using distance level sets［C］//International Conference in Central Europe on Computer Graphics, Visualization. PlzenBory, Czech Republic, 2002: 413420.
［8］AVIDAN S, SHASHUA A. Trajectory triangulation: 3D reconstruction of moving points from a monocular image sequence［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(4): 348357.
［9］PONSA D, LOPEZ A, LUMBRERAS F, et al. 3D vehicle sensor based on monocular vision［C］// Proceedings of IEEE Conference on Intelligent Transportation Systems. Vienna, Austria, 2005: 10961101.
［10］HILD M. Estimation of 3D motion trajectory and velocity from monocular image sequences in the context of human gait recognition［C］//Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK, 2004: 231235.
Similar References:

Memo

-

Last Update: 2010-04-06

Copyright © CAAI Transactions on Intelligent Systems