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...

基于局部模型匹配的几何活动轮廓跟踪

DOI: 10.11834/jig.20150508

Keywords: 局部模型,超像素,EMD相似性度量,噪声模型,水平集

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的在复杂背景下,传统轮廓跟踪方法只考虑了目标的整体特征或显著性特征,没有充分利用目标的局部特征信息,尤其是目标发生遮挡时,容易发生跟踪漂移,甚至丢失目标.针对上述问题,提出一种基于局部模型匹配的几何活动轮廓(LM-GAC)跟踪算法.方法首先,利用超像素技术将图像中的颜色特征相似的像素点归为一类,形成由一些像素点组成的超像素,从而把目标分割成若干个超像素块,再结合EMD(earthmover'sdistance)相似性度量构建局部特征模型.然后,进行局部模型匹配,引入噪声模型来估算局部模型参数θ,这样可以增强特征模型的自适应性,提高局部模型匹配的准确性.最后,结合粒子滤波的水平集分割方法提取目标轮廓,实现目标轮廓精确跟踪.结果本文算法与多种目标轮廓跟踪算法进行对比,在部分遮挡、目标形变、光照变化、复杂背景等条件的基准图像序列均具有较高的跟踪成功率,平均成功率为79.6%.结论实验结果表明,根据不同的图像序列,可以自适应地实时改变噪声模型参数和粒子的权重,使得本文算法具有较高的准确性和鲁棒性.特别是在复杂的背景下,算法能较准确地进行目标轮廓跟踪.

References

[1]  Zhang K,Somh H.Real-time visual tracking via online weighted multiple instance learning[J].Pattern Recognition, 2013,46(1):397-411.
[2]  Ganta R R,Zaheeruddin S,Baddiri N.Segmentation of oil spill images with illumination-reflectance based adaptive level set mo-del[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012, 5(5):1394-1402.[DOI:10.1109/JSTARS.2012.2201249]
[3]  Wu J W,Hu S.3D object tracking using mean-shift and similarity-based aspect-graph modeling[C]// The 33rd Annual Conference of the IEEE Industrial Electronics Society. Taipei, Taiwan, China: IEEE, 2007,5(8): 2383-2388.
[4]  Mukherjee D P, Acton S T. Affine and projective active contour models[J]. Pattern Recognition, 2007, 40(3): 920-930.
[5]  Cavallaro A, Steiger O, Ebrahimi T. Tracking video objects in cluttered background[J]. IEEE Transactions on Circuits Systems for Video Technology, 2005,15(4): 575-584.
[6]  Rathi Y, Vaswani N, Tannenbaum A. A generic framework for tracking using particle filter with dynamic shape prior[J].IEEE Transactions on Image Processing, 2007, 16(5):1370-1382.
[7]  Freedman D, Zhang T. Active contours for tracking distrbutions[J]. IEEE Transactions on Image Processing, 2004, 13(4):518-526.
[8]  Zhang T, Freedman D. Improving performance of distribution tracking through background matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(2):282-287.
[9]  Wu Y W, Ma B. Learning distribution metric for object contour tracking[C]// Proceedings of International Conference on Multi-media Technology. Hangzhou:IEEE,2011,3120-3123. [DOI:10.1109/ICMT.2011.6001851]
[10]  Ning J F, Zhang L, Zhang D. Joint registration and active contour segmentation for object tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013,23(9):1589-1597.
[11]  Boltz S, Nielsen F. Earth mover\'s distance on super-pixels [C]// Proceedings of IEEE International Conference on Image Processing. Hong Kong, China: IEEE,2010:4597-4600.
[12]  Zhao Q, Yang Z, Tao H. Differential earth mover\'s distance with Its applications to visual tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,32(2):274-287.[DOI:10.1109/TPAMI.2008.299]
[13]  Heller I, Tompkins C. “An extension of a theorem of Dan-tzig\'s” in linear inequalities and related systems [J]. Annals of Mathematics Study,1956, 247-254.
[14]  Yu Z, Herman G. On the earth mover\'s distance as a hist-ogram similarity metric for image retrieval[C]// Proceedings of IEEE International Conference on Multimedia and Expo. Washington DC: IEEE, 2005,40(2),99-121.[DOI:10.1109/ICME.2005.1521516]
[15]  Oron S, Hillel A, Levi D. Locally orderless tracking [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence RI: IEEE,2012:1940-1947.
[16]  Clement J, Novas N, Gazqufz J. An active contour computer algorithm for the classification[J].Computers and Electronics in Agriculture,2013,92(3):75-81.
[17]  Yuan Y R, Wang J. Using local saliency for object tracking with particle filters[C]// Proceedings of IEEE International Conference on Signal Processing, Communications and Computing. GuiLin,Guangxi,China: IEEE,2014: 388-393.
[18]  Morel J,YU G. A new framework for fully affine invariant image comparison[C]// Proceedings of IEEE Conference on Acoustics, Speech and Signal Processing.Washington DC: IEEE,2009,1(31):1283-1290.
[19]  Wang F,Fang S.Visual tracking based on the discriminative dictionary and weighted local features[J]. Journal of Image and Graphics,2014,19(9):1316-1323.[王飞,房胜.加权局部特征结合判别式字典的目标跟踪[J]. 中国图象图形学报,2014,19(9):1316-1323.] [DOI:10.11834/jig. 20140908]
[20]  Yang B,Lin G Y,Zhang W G, et al.Robust object tracking incorporating residual unscented particle filter and discriminative sparse representation[J]. Journal of Image and Graphics,2014,19(5): 730-738.[杨彪,林国余,张为公,等. 融合残差Unscented 粒子滤波和区别性稀疏表示的鲁棒目标跟踪[J]. 中国图象图形学报,2014,19(5): 730-738.] [DOI: 10. 11834 /jig. 20140511]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133