AN ERROR ANALYSIS OF GRADIENT-BASED METHODS

被引:5
作者
LEE, JH
KIM, SD
机构
[1] Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Taejon, 305-701, 373-1, Kusong-Dong, Yusong-Gu
关键词
VELOCITY COMPUTATION; ERROR ANALYSIS; QUANTIZATION ERROR; SAMPLING;
D O I
10.1016/0165-1684(94)90044-2
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This short communication derives an estimate for the relative error in the velocity computed through gradient-based methods. The effects caused by the image quantization and sampling process are analyzed separately. For the sake of simplicity, we deal with the one-dimensional image brightness translating with a constant velocity. It is hoped that the results obtained will be utilized for an improved estimation of the velocity.
引用
收藏
页码:157 / 162
页数:6
相关论文
共 4 条
[1]  
Beers, Introduction to the Theory of Error, pp. 1-36, (1957)
[2]  
Bevington, Data Reduction and Error Analysis for the Physical Sciences, pp. 1-65, (1969)
[3]  
Horn, Schunck, Determining optical flow, Artificial Intelligence, 17, pp. 185-203, (1981)
[4]  
Kamgar-Parsi, Kamgar-Parsi, Evaluation of quantization error in computer vision, IEEE Transactions on Pattern Analysis and Machine Intelligence, 9 PAMI, pp. 929-940, (1989)