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...

基于超像素的点追踪方法

DOI: 10.11834/jig.20140313

Keywords: 超像素,目标定位,点追踪,金字塔Lucas-Kanade

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的由于当前大多数的追踪算法都是使用目标外观模型和特征进行目标的匹配,在长时间的目标追踪过程中,目标的尺度和形状均会发生变化,再加上计算机视觉误差,都会导致追踪的失误。提出一种高效的目标模型用于提高追踪的效率和成功率。方法采用分割后提取的目标特征来进行建模表示外观结构,利用图像分割的方法,将被追踪的目标区域分割成多个超像素块,结合SIFT特征,形成词汇本,并计算每个词在词汇本中的权值,作为目标的外观模型。利用外观模型确定目标对象的关键点位置后,通过使用金字塔Lucas-Kanade追踪器预测关键点在下一帧图像中的位置,并移动追踪窗口位置。结果结合点位移的加权计算有效地克服目标尺度和形状变化产生的问题。结论实验结果表明在目标发生形变或光照变化的情况下,算法也能准确地、实时地追踪到目标。

References

[1]  Kim K, Chalidabhongse T H, Harwood D, et al.Background modeling and subtraction by codebook construction[C]//Proceedings of IEEE International Conference on Image Proceedings.Singapore: IEEE Computer Society, 2004: 3061-3064.
[2]  Fulkerson B, Vedaldi A, Soatto S.Class segmentation and object localization with superpixel neighborhoods[C]//Proceedings of the 12th International Conference on Computer Vision.Kyoto: IEEE, 2009: 670-677.
[3]  Ren X, Malik J.Tracking as repeated figure/ground segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Chicago: IEEE, 2007: 17-22.
[4]  Wang S, Lu H, Yang F, et al.Superpixel tracking[C]//Proceeding of the 13th International Conference on Computer Vision.Barcelona, Spain: IEEE, 2011: 1323-1330.
[5]  Sigari M H, Fathy M.Real-time background modeling/subtraction using two-layer codebook model[C]//Proceedings of the International Multi Conference of Engineers and Computer Scientists.Hong Kong, China: IMECS 2008, 1: 10-21.
[6]  Qi M B, Yang A L, Jiang J G, et al.A vehicles detection and tracking algorithm based on improved codebook[J].Journal of Image and Graphics, 2011,16(3): 406-412.[齐美彬, 杨爱丽, 蒋建国, 等.一种基于改进码本的车辆检测与追踪方法.中国图象图形学报, 2011,16(3): 406-412.]
[7]  Avidan S.Ensemble tracking[J].IEEE Transactions on Pattern Analysis And Machine Intelligence,2007,29(2):261-271.
[8]  Grabner H, Leistner C, Bischof H.Semi-supervised on-line boosting for robust tracking.[C]//Proceedings of the 10th European Conference on Computer Vision.Marsille, France: Springer 2008, 234-247.
[9]  Kalal Z, Mikolajczyk K, Matas J.Tracking-learning-detection[J].IEEE Transactions on Pattern Analysis And Machine Intelligence, 2012, 34(7): 1409-1422.
[10]  Steven J S, Ramanan D.Self-paced learning for long-term tracking[C]//Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon: IEEE, 2013.
[11]  Kalal Z, Mikolajczyk K, Matas J.Forward-Backward Error: automatic detection of tracking failures[C]//Proceedings of the 20th International Conference on Computer Vision and Pattern Recognition.Istanbul: IEEE Computer Society, 2010: 2756-2759.
[12]  Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision.2004, 60(2): 91-110.
[13]  Bruce D L, Takeo K. An iterative image registration technique with an application to stereo vision[C]//Proceedings of the 7th International Joint Conference on Artificial Intelligence. British:[s.n.], 1981: 674-649.
[14]  Jiang J W, Ylimaz A.Good features to track: a view geometric approach[C]//Proceeding of IEEE Conference on Conputer Vision and Pattern Recognition.Barcelona: IEEE, 2011: 72-79.
[15]  Nickels K, Hutchinson S.Estimating uncertainty in SSD-based feature tracking[J].Image and Vision Computing, 2002, 20(1): 47-58.
[16]  Cehovin L, Kristan M, Leonardis A.An adaptive coupled-layer visual model for robust visual tracking[C]//Proceedings of IEEE International Conference on Computer Vision.Barcelona, Spain: IEEE, 2011: 1363-1370.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133