FINITE-ELEMENT METHOD FOR DETERMINATION OF OPTICAL-FLOW

被引:12
作者
KIRCHNER, H
NIEMANN, H
机构
[1] Universität Erlangen-Nürnberg, W-8520 Erlangen
关键词
OPTICAL FLOW; MOTION ESTIMATION; FINITE ELEMENT METHOD;
D O I
10.1016/0167-8655(92)90044-Z
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper the application of the finite element method is presented to compute the optical flow field. Using this approach homogeneous areas are roughly triangulated. And vice versa, a fine partition at motion boundaries ensures a flow field with high resolution. This drastically reduces the computational effort without loss of accuracy. We will describe the adaption of the image partition to the variance of the gray level gradients as well as the basic steps for solving the variational problem. Experimental results are presented using synthetic and natural image sequences. Finally, the approach is compared to results computed by the finite difference method (grid method), used up to now.
引用
收藏
页码:131 / 141
页数:11
相关论文
共 17 条
[1]  
FORSYTHE GE, 1967, FINITE DIFFERENCE ME
[2]   DETERMINING OPTICAL-FLOW [J].
HORN, BKP ;
SCHUNCK, BG .
ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) :185-203
[3]  
HUEBNER KH, 1975, FINITE ELEMENT METHO
[4]  
Martin H.C., 1973, INTRO FINITE ELEMENT
[5]  
Nagel H., 1986, Eighth International Conference on Pattern Recognition. Proceedings (Cat. No.86CH2342-4), P1174
[6]   ON A CONSTRAINT EQUATION FOR THE ESTIMATION OF DISPLACEMENT RATES IN IMAGE SEQUENCES [J].
NAGEL, HH .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (01) :13-30
[7]   AN INVESTIGATION OF SMOOTHNESS CONSTRAINTS FOR THE ESTIMATION OF DISPLACEMENT VECTOR-FIELDS FROM IMAGE SEQUENCES [J].
NAGEL, HH ;
ENKELMANN, W .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (05) :565-593
[8]   ON THE ESTIMATION OF OPTICAL-FLOW - RELATIONS BETWEEN DIFFERENT APPROACHES AND SOME NEW RESULTS [J].
NAGEL, HH .
ARTIFICIAL INTELLIGENCE, 1987, 33 (03) :299-324
[9]  
Niemann H., 1988, 9th International Conference on Pattern Recognition (IEEE Cat. No.88CH2614-6), P1094, DOI 10.1109/ICPR.1988.28450
[10]  
Pease M., 1965, METHODS MATRIX ALGEB