全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

动态跟踪中背景补偿与目标运动估计

Keywords: 目标跟踪,背景补偿,目标运动估计,均值迁移

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对目标的观测位置信息中混入了背景运动的问题,提出一种特征点集与稀疏光流场相结合的背景补偿方法.通过Harris算子找出一组特征点,在相邻帧中通过计算每个特征点的局部最优匹配区域得到稀疏点集的光流向量.根据其光流方向概率分布,最终计算出背景的偏移量.通过背景补偿,得到目标的真实偏移量序列,带入Kalman滤波方程,对下一帧中目标的运动状态进行实时估计.实验表明,背景补偿后的预测精度在10个像素之内,每个均值迁移跟踪单元大约需要10ms,提高了跟踪的稳定性,有效减少了迭代次数.新的跟踪器能满足动态实时跟踪的要求.

References

[1]  David G. Object recognition from local scale-invariant features //Proceedings of the International Conference on Computer Vision. Corfu, Greece: , 1999:1150 1157.
[2]  Herbert B, Tinne T, Luc V G. Surf: speeded up robust features //Proceedings of 9th European Conference on Computer Vision. Graz, Austria: , 2006:404 417.
[3]  Matas J, Chum O, Urban M. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing, 2004(6):384 393.
[4]  David G. Distinctive image features from scale-invariant key points, cascade filtering approach[J]. International Journal of Computer Vision, 2004(6):91 110.
[5]  Timor K, Andrew Z, Michael B. An affine invariant salient region detector //Proceedings of 8th European Conference on Computer Vision. Prague, Czech Republic: , 2004:228 241.
[6]  Carlo T, Takeo K. Shape and motion from image streams under orthography: a factorization method[J]. International Journal of Computer Vision, 1992(9):137 154.
[7]  Kelson R, Andre M, Adelardo A. Optical flow using color information: preliminary results //Proceedings of 2008 ACM Symposium on Applied Computing. Fortaleza, Brazil: , 2008:1607 1611.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133