Local Background-aware Target Tracking
-
摘要: 经典视觉跟踪方法通常仅以目标区域内信息作为目标描述. 实际中, 目标局部背景信息也影响着跟踪性能. 本文首先在目标描述中引入局部背景信息, 并将目标表示为一带权点集. 然后通过K近邻计算目标观测概率, 并联合目标先验信息得到搜索区域内各点后验概率值. 最后, 利用均值漂移(Mean shift)算法估计目标状态. 本文算法优点如下: 1) 目标描述中联合局部背景信息, 增强了目标模型. 因此, 跟踪过程中提高了目标与背景的区分能力, 并进一步使跟踪算法更加稳定, 跟踪结果更加精准. 2)目标初始化时, 利用Mean shift对目标进行一次重定位. 由此解决了不精确初始化时跟踪算法容易失效的问题. 在不同视频上进行了定性和定量的实验验证. 结果表明本文算法具有较高的跟踪稳定性和准确性, 尤其当目标初始化比较粗糙时.Abstract: Classical visual tracking methods usually only adopt target information to describe the target. In practice, local background information around the target also influences the tracking process. In this paper, we first introduce the local background information into target description, and represent it as a set of weighted feature points. After that, the posterior probability of each point in the search-region is calculated by incorporating the target observation obtained by K nearest neighbor (KNN) algorithm and the Gaussian prior distribution of the target. Finally, the mean shift algorithm is used to estimate the target state. The proposed method has the following two advantages: 1) The local background information is integrated into the target description, which enhances the target model. Thereby, the discriminative ability is promoted in the tracking process, which further makes the tracker more robust and accurate. 2) In the initialization stage, the mean-shift is applied to relocating the target, which can solve the problem that the tracking algorithm is prone to failure in inexact initialization. Extensive experiments in different video sequences are conducted to evaluate our approach qualitatively and quantitatively. The results show that our method holds high tracking accuracy and stability, especially when the target is roughly initialized.
-
Key words:
- Target tracking /
- weighted points set /
- K nearest neighbor (KNN) /
- mean shift
-
[1] Hou Zhi-Qiang, Han Chong-Zhao. A survey of visual tracking. Acta Automatica Sinica, 2006, 32(4): 603-617(侯志强, 韩崇昭. 视觉跟踪技术综述. 自动化学报, 2006, 32(4): 603-617)[2] Yilmaz A, Javed O, Shah M. Object tracking: a survey. ACM Computing Surveys, 2006, 38(4): 1-45[3] Kim I S, Choi H S, Yi K M, Choi J Y, Kong S G. Intelligent visual surveillance——a survey. International Journal of Control, Automation, and Systems, 2010, 8(5): 926-939[4] Wang Yong, Chen Fen-Xiong, Guo Hong-Xiang. Kernel spatial histogram target tracking based on template drift correction. Acta Automatica Sinica, 2012, 38(3): 430-436(王勇, 陈分雄, 郭红想. 偏移校正的核空间直方图目标跟踪. 自动化学报, 2012, 38(3): 430-436)[5] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577[6] Li Pei-Hua. An improved mean shift algorithm for object tracking. Acta Automatica Sinica, 2007, 33(4): 347-354(李培华. 一种改进的Mean Shift 跟踪算法. 自动化学报, 2007,33(4): 347-354)[7] Arulampalam M S, Maskell S, Gordon N, Clapp T. A tutorial on particle filters for online nonlinear/non-Gaussian bayesian tracking. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188[8] Isard M, Blake A. Condensation-conditional density propagation for visual tracking. International Journal of Computer Vision, 1998, 29(1): 5-28[9] Collins R T, Liu Y X, Leordeanu M. Online selection of discriminative tracking features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643[10] Ning J, Zhang L, Zhang D, Wu C. Robust mean shift tracking with corrected background-weighted histogram. IET Computer Vision, 2012, 6(1): 62-69[11] Wang L F, Pan C H, Xiang S M. Mean-shift tracking algorithm with weight fusion strategy. In: Proceedings of the 18th International Conference on Image. Brussels, Belgium: IEEE, 2011. 473-476[12] Grabner H, Grabner M, Bischof H. Real-time tracking via on-line boosting. In: Proceedings of the 17th British Machine Vision Conference. Guildford: BMVA Press, 2006. 47-56[13] Grabner H, Leistner C, Bischof H. Semi-supervised on-line boosting for robust tracking. In: Proceedings of the 10th European Conference on Computer Vision. Berlin, Heidelberg: Springer-Verlag, 2008. 243-247[14] Babenko B, Yang M H, Belongie S. Robust object tracking with online multiple instance learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632[15] Page L, Brin S, Motwani R, Winograd T. The PageRank Citation Ranking: Bringing Order to the Web, Technical Report, Stanford Digital Library Technologies Project, USA, 1999[16] Bradski G R. Real time face and object tracking as a component of a perceptual user interface. In: Proceedings of the 4th Workshop on Applications of Computer Vision. Princeton, USA: IEEE, 1998. 214-219[17] Qian Hui-Min, Mao Yao-Bin, Wang Zhi-Quan. Mean shift tracking with self-updating tracking window. Journal of Image and Graphics, 2007, 12(2): 245-249(钱惠敏, 茅耀斌, 王执铨. 自动选择跟踪窗尺度的Mean-Shift算法. 中国图象图形学报, 2007, 12(2): 245-249)[18] Tola E, Lepetit V, Fua P. DAISY: an efficient dense descriptor applied to wide-baseline stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830[19] Lu Da-Jin. Stochastic Processes and Their Applications. Beijing: Tsinghua University Press, 1986(陆大琻. 随机过程及其应用. 北京: 清华大学出版社, 1986)
点击查看大图
计量
- 文章访问数: 1515
- HTML全文浏览量: 47
- PDF下载量: 1115
- 被引次数: 0