[1]HE Yulan,GU Renshu,YUAN Jie.A 3D motion vector algorithm in a free angle system[J].CAAI Transactions on Intelligent Systems,2012,7(2):115-120.
Copy

A 3D motion vector algorithm in a free angle system

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 7 Number of periods: 2012 2 Page number: 115-120 Column: 学术论文—人工智能基础 Public date: 2012-04-25
Title:
A 3D motion vector algorithm in a free angle system
Author(s):
HE Yulan;  GU Renshu;  YUAN Jie
School of Electronic Science and Engineering, Nanjing University, Nanjing 210093, China
Keywords:
motion vector algorithm;  motion estimation;  point correspondence;  linear equation set;  QR decomposition
CLC:
TP301.6
DOI:
-
Abstract:
In order to solve a 3D motion vector calculation, a new algorithm was proposed. This algorithm is a linear method that calculates the rigidbody movement from twodimensional views based on the static 3D reconstruction. The QR decomposition was adopted to obtain the minimum mean square error of a linear equation set and an iterative process enables the method to eliminate outliers and thus obtain motion vector. This algorithm does not require camera calibration, and it is realtime, which enables smooth video. The experimental results show the algorithm has good robustness.
References:
［1］PAPADIMITRIOU T, STRINTZIS M G, ROUMELIOTIS M. Robust estimation of rigid body 3D motion parameters based on point correspondences［J］. IEEE Trans on Circuits and Systems for Video Technology, 2000, 10(4): 541549.
［2］WENG J, HUANG T S, AHUJA N. Motion and structure from two perspective views: algorithms, error analysis, and error estimation［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 1989, 11(5): 451476.
［3］HARTLEY R. In defense of the 8point algorithm［C］//IEEE International Conference on Computer Vision. Cambridge, USA, 1995: 10641070.
［4］EBRAHIMNEZHAD H, ROBUST H G. Motion from space curves and 3D reconstruction from multiviews using perpendicular double stereo rigs［J］. Image and Vision Computing, 2008, 26(10): 13971420. 
［5］MONTIEL J M M, TARDOHS J D, MONTANO L. Structure and motion from straight line segments［J］. Pattern Recognition, 2000, 33(8): 12951307.
［6］STEINBACH E G, EISERT P, GIROD B. Modelbased 3D shape and motion estimation using sliding textures［C］//Proc Vision Modeling and Visualization Conference. Berlin, Germany, 2001: 375382.
［7］NEUMANN J, FERMULLER C, ALOIMONOS Y. Polydioptric camera design and 3D motion estimation［C］//Proc IEEE Conf Computer Vision and Pattern Recognition. Madison, USA, 2003: 294301.
［8］ROACH J W, AGGARWAL J K. Determining the movement of objects from a sequence of images［J］. IEEE Trans on Pattern Anal and Machine Intell, 1980, 7(4): 554562.
［9］OLIENSISA J. Multiframe structure from motion algorithm under perspective projection［J］. International Journal of Computer Vision, 1999, 34(2): 163192.
［10］付永庆，宋宝森，吴建芳.边缘分类SIFT算法［J］. 哈尔滨工程大学学报, 2010, 31(5): 163171.
FU Yongqing， SONG Baosen， WU Jianfang. Edge classification of the SIFT alogorithm［J］. Journal of Harbin Engineering University, 2010, 31(5): 163171.
［11］SAND P, TELLER S. Particle video: longrange motion estimation using point trajectories［J］. International Journal of Computer Vision, 2008, 80(1): 7291.
［12］MATEI B, MEER P. A general method for errorsinvariables problems in computer vision［C］//Proc IEEE Conf Computer Vision and Pattern Recognition. Hilton Head, USA, 2000: 1825.
［13］FIROOZFAM P, NEGAHDARIPOUR S. Theoretical accuracy analysis of nocular vision systems for scene reconstruction, motion estimation, and positioning problems in computer vision［C］//Proc 2nd Int Symposium on 3D Data Processing, Visualization, and Transmission. Washington, DC, USA, 2004: 88895.
［14］SHEIKH Y, HAKEEM A, SHAH M. On the direct estimation of the fundamental matrix［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Minnesota, USA, 2007: 17.
［15］CHEN P. Why not use the LevenbergMarquardt method for fundamental matrix estimation［J］. IET Computer Vision, 2010, 4(4): 286294.
［16］WU H H P, CHANG S H. Fundamental matrix of planar catadioptric stereo systems［J］. IET Computer Vision, 2010, 4(2): 85104.
［17］SZELISKI R. Computer vision: algorithms and applications［M］. Berlin: SpringerVerlag, 2010: 343374.
Similar References:

Memo

-

Last Update: 2012-07-12

Copyright © CAAI Transactions on Intelligent Systems