An Improved Jensen-Shannon Divergence Based SpatiogramSimilarity Measure for Object Tracking
-
摘要: 空间直方图是直方图的一种推广, 它能更精确地描述图像(或目标), 被应用到目标跟踪和图像检索等多个领域, 选择一种合适的度量两个空间直方图之间相似性的方法至关重要. 本文提出一种基于改进Jensen-Shannon divergence (JSD) 距离的空间直方图相似性度量, 将空间直方图中每个区间所对应像素的颜色特征和空间特征的联合分布看作一个带权重的高斯分布, 然后计算两个空间直方图对应区间之间的相似度, 即计算两个带权重的高斯分布之间的改进的JSD距离. 本文在计算JSD距离时充分利用高斯分布的权重, 从而提高了度量方法的区分能力. 理论和实验证明了本文提出的相似性度量的区分能力优于Ulges的度量方法, 视频跟踪结果也更稳定、更精确.Abstract: Spatiogram is a generalization of histogram, which can more accurately describe the image (or the object) and has found application in object tracking and image retrieval. Suitable similarity measure is critical. In this paper, we present an improved Jensen-Shannon divergence (JSD) based spatiogram similarity measure. The spatial-color joint probability distribution of the pixels corresponding to each bin is regarded as a weighted Gaussian distribution. Then, the similarity of corresponding bin of two spatiograms is computed by improved Jensen-Shannon divergence with two weighted Gaussian distributions. We make full use of the weight of Gaussian distribution in order to improve the discrimination of the proposed measure. The proposed measure gives superior discriminative power both theoretically and experimentally than the measure proposed by Ulges, and the result of object tracking is more stable and accurate.
-
Key words:
- Spatiogram /
- Jensen-Shannon divergence (JSD) /
- particle filter /
- object tracking
-
[1] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2006. 2169-2178[2] Lampert C H, Blaschko M B, Hofmann T. Beyond sliding windows: object localization by efficient subwindow search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA: IEEE, 2008. 1-8[3] Birchfield S T, Rangarajan S. Spatiograms versus histograms for region-based tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005. 1158-1163[4] Li Y, Ai H, Huang C, Lao S. Robust head tracking with particles based on multiple cues. In: Proceedings of the 9th European Conference on Computer Vision Workshop on Human-Computer Interaction. Graz, Austria: Springer, 2006. 29-39[5] O'Conaire C, O'Connor N E, Smeaton A F. An improved spatiogram similarity measure for robust object localisation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Honolulu, USA: IEEE, 2007. 1067-1072[6] Birchfield S T, Rangarajan S. Spatial histograms for region-based tracking. ETRI Journal, 2007, 29(5): 697-699[7] Yao Zhi-Jun, Liu Jun-Tao, Zhou Yu, Liu Wen-Yu. Symmetric Kullback-Leibler divergence object tracking method. Journal of Huazhong University of Science and Technology (Natural Science), 2011, 39(11): 1-4(姚志均, 刘俊涛, 周瑜, 刘文予. 基于对称KL距离的相似性度量方法. 华中科技大学学报(自然科学版), 2011, 39(11): 1-4)[8] Yao Z J, Lai Z Y, Liu W Y. A symmetric KL divergence based spatiogram similarity measure. In: Proceedings of the 18th IEEE International Conference on Image Processing. Brussels, Belgium: IEEE, 2011. 197-200[9] Ulges A, Lampert C, Keysers D, Breuel T. Spatiogram-based shot distances for video retrieval. In: Online Proceedings of the Text Retrieval Conference on Video Retrieval Evaluation. Gaithersburg, USA: NIST, 2006. 1-10[10] O'Conaire C, O'Connor N E, Smeaton A F, Jones G. Organising a daily visual diary using multifeature clustering. In: Proceedings of the 19th SPIE Annual Symposium on Electronic Imaging —— Multimedia Content Access: Algorithms and Systems. San Jose, USA: SPIE, 2007. 1-11[11] Sundar R S, Rangan C P. Spatiogram based fast mode decision in spatial scalable video coding. In: Proceedings of the 11th Pacific Rim Conference on Multimedia. Shanghai, China: Springer, 2010. 121-135[12] Arulampalam M S, Maskell S, Gordon N, Clapp T. A tutorial on particle filters for online non-linear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188[13] Nummiaro K, Koller-Meier E, Gool L V. An adaptive color-based particle filter. Image and Vision Computing, 2003, 21(1): 99-110[14] Dunne P, Matuszewski B J. Choice of similarity measure, likelihood function and parameters for histogram based particle filter tracking in CCTV grey scale video. Image and Vision Computing, 2011, 29(2-3): 178-189[15] Zhang Gong-Yuan, Cheng Yong-Mei, Yang Feng, Pan Quan, Liang Yan. Design of an adaptive particle filter based on variance reduction technique. Acta Automatica Sinica, 2010, 36(7): 1020-1024[16] Zhu Ji-Hua, Zheng Nan-Ning, Yuan Ze-Jian, Zhang Qiang. A SLAM algorithm based on central difference particle filter. Acta Automatica Sinica, 2010, 36(2): 249-257(祝继华, 郑南宁, 袁泽剑, 张强. 基于中心差分粒子滤波的SLAM算法. 自动化学报, 2010, 36(2): 249-257)[17] Hu J S, Juan C W, Wang J J. A spatial-color mean-shift object tracking algorithm with scale and orientation estimation. Pattern Recognition Letters, 2008, 29(16): 2165-2173[18] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577[19] Gan Ming-Gang, Chen Jie, Wang Ya-Nan, Jin Dai-Zhong. A target tracking algorithm based on mean shift and normalized moment of inertia feature. Acta Automatica Sinica, 2010, 36(9): 1332-1336(甘明刚, 陈杰, 王亚楠, 金代中. 基于Mean Shift算法和NMI特征的目标跟踪算法研究. 自动化学报, 2010, 36(9): 1332-1336)[20] CAVIAR test case scenarios [Online], available: http: //groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/, March 5, 2011
点击查看大图
计量
- 文章访问数: 2489
- HTML全文浏览量: 65
- PDF下载量: 1187
- 被引次数: 0