MOTION DISPLACEMENT ESTIMATION USING AN AFFINE MODEL FOR IMAGE MATCHING

被引:42
作者
FUH, CS
MARAGOS, P
机构
[1] Harvard Univ, Cambridge, MA
关键词
VISUAL COMMUNICATIONS; IMAGE MOTION ANALYSIS; DISPLACEMENT ESTIMATION; BLOCK MATCHING; AFFINE MODELS;
D O I
10.1117/12.55885
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
A model is developed for estimating the displacement field in spatio-temporal image sequences that allows for affine shape deformations of corresponding spatial regions and for affine transformations of the image intensity range. This model includes the block matching method as a special case. The model parameters are found by using a least-squares algorithm. We demonstrate experimentally that the affine matching algorithm performs better in estimating displacements than other standard approaches, especially for long-range motion with possible changes in scene illumination. The algorithm is successfully applied to various classes of moving imagery, including the tracking of cloud motion.
引用
收藏
页码:881 / 887
页数:7
相关论文
共 20 条
  • [1] ON THE COMPUTATION OF MOTION FROM SEQUENCES OF IMAGES - A REVIEW
    AGGARWAL, JK
    NANDHAKUMAR, N
    [J]. PROCEEDINGS OF THE IEEE, 1988, 76 (08) : 917 - 935
  • [2] VECTOR MEDIAN FILTERS
    ASTOLA, J
    HAAVISTO, P
    NEUVO, Y
    [J]. PROCEEDINGS OF THE IEEE, 1990, 78 (04) : 678 - 689
  • [3] Biemond J., 1988, Proceedings of the SPIE - The International Society for Optical Engineering, V1001, P917, DOI 10.1117/12.969043
  • [4] Brockett R. W., 1990, Journal of Visual Communication and Image Representation, V1, P3, DOI 10.1016/1047-3203(90)90012-K
  • [5] Cafforio C., 1983, P IM SEQ PROC DYN SC, P104
  • [6] CORNELIUS N, 1983, MOTION REPRESENTATIO
  • [7] Costa M. S., 1990, Proceedings. 10th International Conference on Pattern Recognition (Cat. No.90CH2898-5), P233, DOI 10.1109/ICPR.1990.118101
  • [8] GILGE M, 1990, P SOC PHOTO-OPT INS, V1244, P355, DOI 10.1117/12.19525
  • [9] HILDRETH EC, 1986, AIL919 MIT MEM
  • [10] DETERMINING OPTICAL-FLOW
    HORN, BKP
    SCHUNCK, BG
    [J]. ARTIFICIAL INTELLIGENCE, 1981, 17 (1-3) : 185 - 203