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...

压缩感知跟踪中的特征选择与目标模型更新

DOI: 10.11834/jig.20140614

Keywords: 压缩感知,目标跟踪,特征选择,目标模型更新

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的为了增强压缩感知跟踪算法在复杂场景下的性能,提出一种特征选择与目标模型更新的改进跟踪算法。方法本文算法包含两方面的改进,一是根据特征的正负类条件概率分布的距离选择能有效区分目标与背景的特征;二是根据当前目标与原始目标的差异自适应更新目标外观模型,使得目标遇到较大遮挡或者姿态频繁改变时目标外观模型不会被错误更新。结果对于10个复杂环境下的经典视频序列,基于压缩感知的改进跟踪算法获得平均85.19%的正确跟踪率和平均13.74个像素的跟踪误差效果,在中心误差、成功率和精确度3个指标上均优于最近提出的3个代表性跟踪算法。结论实验结果表明,本文新的特征选择和目标模型更新算法,既增强了压缩感知跟踪算法的鲁棒性,又加快了跟踪速度。

References

[1]  Yilmaz A, Javed O, Shah M. Object tracking: a survey[J]. ACM Computing Surveys, 2006, 38(4): 13.
[2]  Black M J, Jepson A D. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation[J]. International Journal of computer vision, 1998, 26(1): 63-84.
[3]  Black M J, Fleet D J, Yacoob Y. A framework for modeling appearance change in image sequences[C]//Proceedings of Sixth International Conference on Computer Vision. Washington DC: IEEE, 1998: 660-667.
[4]  Shen H, Li S, Bo F, et al. On road vehicles real-time detection and tracking using vision based approach[J]. Acta Optica Sinica, 2010,30(1):1076-1083.[沈?,李舜酩,柏方超,等.路面车辆实时检测与跟踪的视觉方法[J].光学学报,2010,30(1):1076-1083.]
[5]  Cheng Y L, Li B, Zhang W C, et al. An adaptive pedestrian tracking algorithm with prior knowledge[J]. Pattern Recognition and Artificial Intelligence, 2009, 22(5): 704-708. [程有龙,李斌,张文聪,等. 融合先验知识的自适应行人跟踪算法[J]. 模式识别与人工智能,2009,22(5):704-708.]
[6]  Mei X, Ling H. Robust visual tracking using ? 1 minimization[C]//Proceedings of IEEE the 12th International Conference on Computer Vision. Washington DC:IEEE, 2009: 1436-1443.
[7]  Learned-Miller E G, Lara LS. Distribution fields for tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE, 2012: 1910-1917.
[8]  Donoho D. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.
[9]  Dai Q H, Fu C J, Ji X Y. Research on compressed sensing[J]. Chinese Journal of Computers, 2011,34(3):425-434.[戴琼海,付长军,季向阳. 压缩感知研究[J].计算机学报,2011,34(3):425-434.]
[10]  Ji S, Xue Y, Carin L. Bayesian compressive sensing[J]. IEEE Transactions on Signal Processing, 2008, 56(6): 2346-2356.
[11]  Do T T, Chen Y, Nguyen D T, et al. Distributed compressed video sensing[C]//Proceedings of the 16th IEEE International Conference on Image processing. Washington DC:IEEE, 2009: 1393-1396.
[12]  Jung H, Sung K, Nayak K S, et al. k-t FOCUSS: a general compressed sensing framework for high resolution dynamic MRI[J]. Magnetic Resonance in Medicine, 2009, 61(1): 103-116.
[13]  Lu Y, Wu S J, Zhang H G, et al. Low complexity compressed sensing based Doppler high resolution algorithm[J]. Journal of Xidian University, 2011,38(2):82-87. [刘寅,吴顺君,张怀根,等. 一种快速的基于压缩感知的多普勒高分辨方法[J].西安电子科技大学学报, 2011,38(2):82-87.]
[14]  Yu H M, Fang G Y. Research on compressive sensing based 3D imaging method applied to ground penetrating radar[J]. Journal of Electronics & Information Technology, 2010,32(1):12-16. [余慧敏, 方广有. 压缩感知理论在探地雷达三维成像中的应用[J].电子与信息学报,2010,32(1):12-16.]
[15]  Li H, Shen C, Shi Q. Real-time visual tracking using compressive sensing[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE, 2011: 1305-1312.
[16]  Zhang K, Zhang L, Yang M H. Real-time compressive tracking[C]//Computer Vision-ECCV 2012. Berlin Heidelberg: Springer, 2012, 7574: 864-877.
[17]  Levi K, Weiss Y. Learning object detection from a small number of examples: the importance of good features[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE, 2004, 2: 53-60.
[18]  Jebara T, Jaakkola T. Feature selection and dualities in maximum entropy discrimination[C]//Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 2000: 291-300.
[19]  Zhu Y, Yu J X, Cheng H, et al. Graph classification: a diversified discriminative feature selection approach[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management. New York: ACM, 2012: 205-214.
[20]  Yang Y, Shen H T, Ma Z, et al. L2,1-norm regularized discriminative feature selection for unsupervised learning[C]//Proceedings of the 22nd International Joint Conference on Artificial Intelligence-Volume. Menlo Park, Calif.: AAAI Press, 2011,2: 1589-1594.
[21]  更多...
[22]  Babenko B, Yang M H, Belongie S. Visual tracking with online multiple instance learning[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE, 2009: 983-990.
[23]  Grabner H, Leistner C, Bischof H. Semi-supervised on-line boosting for robust tracking[C]//Computer Vision-ECCV, 2008. Berlin Heidelberg: Springer, 2008,5302: 234-247.
[24]  Zhang K, Song H. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013, 46(1):397-411.
[25]  Lu H, Zhou Q, Wang D, et al. A co-training framework for visual tracking with multiple instance learning[C]//Proceedings of IEEE International Conference on Automatic Face & Gesture Recognition and Workshops. Washington DC:IEEE, 2011: 539-544.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133