改进的二次型直方图距离度量

doi:10.3969/j.issn.1001-2400.2015.03.027

J4 ›› 2015, Vol. 42 ›› Issue (3): 161-167+172.doi: 10.3969/j.issn.1001-2400.2015.03.027

改进的二次型直方图距离度量

余旺盛;田孝华;侯志强;刘彬

(空军工程大学信息与导航学院，陕西西安 710077)

收稿日期:2014-03-02 出版日期:2015-06-20 发布日期:2015-07-27
通讯作者: 余旺盛
作者简介:余旺盛(1985-)，男，讲师，E-mail: xing_fu_yu@sina.com．
基金资助:
国家自然科学基金资助项目(61175029，61473309)

Improved quadratic-form metric for histogram distance measurement

YU Wangsheng;TIAN Xiaohua;HOU Zhiqiang;LIU Bin

(Information and Navigation College, Air Force Engineering Univ., Xi'an 710077, China)

Received:2014-03-02 Online:2015-06-20 Published:2015-07-27
Contact: YU Wangsheng

摘要/Abstract

摘要：

为增强直方图距离度量的辨别力，对二次型的直方图距离度量问题进行了研究．首先，对传统的二次型距离及其存在的问题进行了简要评述; 然后，通过对传统二次型距离度量函数进行改进和构建新的相关矩阵，提出了改进的二次型直方图距离度量准则; 最后对所提距离度量的快速计算以及高维直方图的距离度量问题进行了讨论．改进的距离度量准则充分考虑了直方图子区间之间的相关性．通过形状匹配、图像检索以及视觉跟踪等一系列实验测试，验证了所提距离度量准则的有效性和优越性．

关键词: 形状匹配, 图像检索, 视觉跟踪, 直方图距离

Abstract:

In order to improve the discrimination of histogram distance measurement, the problem of histogram distance measurement based on the quadratic-form metric is researched. Firstly, the traditional quadratic-form metric and its disadvantage are briefly reviewed. Then, an improved quadratic-form metric for histogram distance measurement is proposed by modifying the traditional quadratic-form distance function and the correlation matrix. Finally, the fast computation of the proposed metric and the measurement of high dimension histograms are discussed. The proposed metric takes a full consideration of the correlation between histogram bins, which increases its discrimination. Experiments based on shape matching, image retrieval and visual tracking validate the effectiveness of the proposed metric and its superiority over the traditional ones.

Key words: shape matching, image retrieval, visual tracking, histogram distance

余旺盛;田孝华;侯志强;刘彬. 改进的二次型直方图距离度量[J]. J4, 2015, 42(3): 161-167+172.

YU Wangsheng;TIAN Xiaohua;HOU Zhiqiang;LIU Bin. Improved quadratic-form metric for histogram distance measurement[J]. J4, 2015, 42(3): 161-167+172.

参考文献

［1］周瑜, 刘俊涛, 白翔. 形状匹配方法研究与展望［J］. 自动化学报, 2012, 38(6): 889-910.
Zhou Yu, Liu Juntao, Bai Xiang. Research and Perspective on Shape Matching ［J］. Acta Automatica Sinica, 2012, 38(6): 889-910.
［2］杨红菊, 菅小艳, 曹付元, 等. 基于组合欧拉向量与边缘方向直方图的图像检索方法［J］. 模式识别与人工智能, 2012, 25(3): 450-455.
Yang Hongju, Jian Xiaoyan, Cao Fuyuan, et al. Image Retrieval Method Based on Combined Euler Vector and Edges Direction Histogram ［J］. Pattern Recognition and Artificial Intelligence, 2012, 25(3): 450-455.
［3］余旺盛, 侯志强, 田孝华, 等. 利用局部特征联合匹配的非刚体目标跟踪［J］. 西安电子科技大学学报, 2014, 41(6): 183-189.
Yu Wangsheng, Hou Zhiqiang, Tian Xiaohua, et al. Non-rigid Object Tracking Using Joint Matching of Local Features ［J］. Journal of Xidian University, 2014, 41(6): 183-189.
［4］王勇, 陈分雄, 郭红想. 偏移校正的核空间直方图目标跟踪［J］. 自动化学报, 2012, 38(3): 430-436.
Wang Yong, Chen Fenxiong, Guo Hongxiang. Kernel Spatial Histogram Target Tracking Based on Template Drift Correction ［J］. Acta Automatica Sinica, 2012, 38(3): 430-436.
［5］ Karavasilis V, Nikou C, Likas A. Visual Tracking Using the Earth Mover's Distance Between Gaussian Mixtures and Kalman Filtering ［J］. Image and Vision Computing, 2011, 29(5): 295-305.
［6］ Leichter I. Mean Shift Trackers with Cross-Bin Metrics ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 695-706.
［7］ Wu J, Rehg J M. Beyond the Euclidean Distance: Creating Effective Visual Codebooks Using the Histogram Intersection Kernel ［C］//Proceedings of 12th International Conference on Computer Vision. Piscataway: IEEE, 2009: 630-637.
［8］ Sarra S, Amel B. Fast Scalable Retrieval of Multispectral Images with Kullback-Leibler Divergence ［C］//Proceedings of 17th IEEE International Conference on Image Processing. Piscataway: IEEE, 2010: 2333-2336.
［9］姚志均, 刘俊涛, 赖重远, 等. 一种改进的JSD 距离的空间直方图相似度度量及目标跟踪［J］. 自动化学报, 2011, 37(12): 1464-1473.
Yao Zhijun, Liu Juntao, Lai Zhongyuan, et al. An Improved Jensen-Shannon Divergence Based Spatiogram Similarity Measure for Object Tracking ［J］. Acta Automatica Sinica, 2011, 37(12): 1464-1473.
［10］贾世杰, 孔祥维. 一种新的直方图核函数及在图像分类中的应用［J］. 电子与信息学报, 2011, 33(7): 1738-1742.
Jia Shiji, Kong Xiangwei. A New Histogram-based Kernel Function Designed for Image Classification ［J］. Journal of Electronics ＆ Information Technology, 2011, 33(7): 1738-1742.
［11］ Rubner Y, Tomasi C, and Guibas L. The Earth Mover's Distance as a Metric for Image Retrieval ［J］. International Journal of Computer Vision, 2000, 40(2): 99-121.
［12］ Ling H, Okada K. EMD-L1: An Efficient and Robust Algorithm for Comparing Histogram-Based Descriptors ［C］//Lecture Notes in Computer Science: 3953. Berlin: Springer, 2006: 330-343.

[1]	张飞,马时平,张立朝,何林远,仇祝令,韩永赛. 空间可靠性和相关滤波器联合学习的跟踪算法[J]. 西安电子科技大学学报, 2021, 48(5): 167-177.
[2]	闫佳,曹玉东,任佳兴,陈冬昊,李晓会. 深度非对称压缩型哈希算法[J]. 西安电子科技大学学报, 2021, 48(5): 212-221.
[3]	王洪雁,邱贺磊,裴腾达. 利用判别字典学习的视觉跟踪方法[J]. 西安电子科技大学学报, 2019, 46(4): 150-158.
[4]	刘道华,崔玉爽,赵岩松,宋玉婷,王景慧. 一种改进卷积神经网络的教学图像检索方法[J]. 西安电子科技大学学报, 2019, 46(3): 52-58.
[5]	杨源;查宇飞;覃兵;梁兵兵;杨丽薇;李运. 利用核技巧和迭代量化的图像检索算法[J]. 西安电子科技大学学报, 2017, 44(1): 165-170.
[6]	张浪;侯志强;余旺盛;许婉君. 利用快速傅里叶变换的双层搜索目标跟踪算法[J]. 西安电子科技大学学报, 2016, 43(5): 153-159.
[7]	张立朝;毕笃彦;杨源;余旺盛;覃兵. 一种AGMM配准的尺度自适应目标跟踪方法[J]. J4, 2015, 42(5): 175-182.
[8]	余旺盛;侯志强;田孝华;查宇飞. 利用局部特征联合匹配的非刚体目标跟踪[J]. J4, 2014, 41(6): 160-166.
[9]	闫允一;姜帅;郭宝龙. 结合稳定兴趣点和Gabor小波的图像检索[J]. J4, 2014, 41(5): 118-123.
[10]	朱旭东;李晖;郭祯. 云计算环境下加密图像检索[J]. J4, 2014, 41(2): 151-158.
[11]	孟繁杰;郭宝龙. 使用兴趣点局部分布特征及多示例学习的图像检索方法[J]. J4, 2011, 38(2): 47-53.
[12]	何周灿;王庆;杨恒. 图像特征匹配中一种快速关键维过滤搜索算法[J]. J4, 2010, 37(3): 534-540.
[13]	张志安;骆斌. 一种新的颜色空间特征图像检索 [J]. J4, 2008, 35(3): 577-580.
[14]	赵珊;周利华. DCT压缩域中基于纹理和形状的图像检索算法 [J]. J4, 2007, 34(3): 402-408.
[15]	安志勇;王晓华;赵珊;周利华. 一种图像纹理特征检索算法 [J]. J4, 2007, 34(3): 409-413.

改进的二次型直方图距离度量

Improved quadratic-form metric for histogram distance measurement

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10