基于非参数边缘积分估计的局部特征描述子

郑明国; 吴成东; 陈东岳; 贾同; 金勇虎

doi:10.13700/j.bh.1001-5965.2015.0156

基于非参数边缘积分估计的局部特征描述子

doi: 10.13700/j.bh.1001-5965.2015.0156

东北大学信息科学与工程学院, 沈阳 110819

基金项目: 国家自然科学基金(61273078)

详细信息

作者简介:
郑明国男,博士研究生。主要研究方向:视觉导航、模式识别、数字信号处理。Tel.:024-83687415 E-mail:15840514543@163.com;吴成东男,博士,教授,博士生导师。主要研究方向:图像智能处理、机器人智能导航。Tel.:024-83687146 E-mail:wuchengdong@ise.neu.edu.cn

通讯作者:
吴成东,Tel.:024-83687146 E-mail:wuchengdong@ise.neu.edu.cn

中图分类号: V249.32⁺5;TP391.4
计量
- 文章访问数: 989
- HTML全文浏览量: 184
- PDF下载量: 540
- 被引次数: 0
出版历程
- 收稿日期: 2015-03-19
- 网络出版日期: 2016-03-20

Local feature descriptor based on nonparametric marginal integration estimation

College of Information Science and Engineering, Northeastern University, Shenyang 110819, China

Funds: National Natural Science Foundation of China (61273078)

摘要

摘要: 为提高图像匹配性能提出了关于局部区域特征描述子的统计模型。该模型是一种基于梯度模值及方向分布的边缘积分函数模型。在离散梯度方向的边缘积分函数与梯度矢量场的模值累积方向直方图相同。采用基于核函数的非参数估计,估计了该函数,应用于尺度不变特征变换(SIFT)描述子。为了提高描述子的旋转不变性、独特性,降低运算复杂度,将特征点周围的局部区域作为圆形,由径向采样网格划分为8个子区域。在每个子区域估计边缘积分函数,特征向量由每个小块8个方向的函数值组成。实验表明,该描述子能够提高旋转变换的检测率(查全率),降低运算复杂度。
- 梯度分布 /
- 非参数估计 /
- 边缘积分 /
- 尺度不变特征变换 (SIFT) /
- 图像匹配
Abstract: A statistical model for the feature descriptor of local region was suggested to improve the image matching performance. This model is a marginal integration function model based on the gradient magnitude and orientation distribution. The marginal integration function on the discrete gradient orientations is the same as the magnitude accumulation orientation histogram of gradient vector field. Using the nonparametric estimator based on kernel function, we estimated this function and applied it to scale invariant feature transform (SIFT) descriptor. To enhance rotation invariance and distinctiveness and to reduce computational complexity for descriptor, local region around the feature point was selected as circle and partitioned to the 8 sub-regions by radial sampling grid. The marginal expectation functions are estimated in each sub-region and the feature vector consists of the function values on the 8 orientations for 8 sub-regions. Experiments show that this descriptor can improve detective rate (recall) for rotation and reduce computational complexity.
- gradient distribution /
- nonparametric estimation /
- marginal integration /
- scale invariant feature transform (SIFT) /
- image matching

HTML全文

参考文献(15)

[1]	WU H Y, CAI Z H,WANG Y X.Vision-based auxiliary navigation method using augmented reality for unmanned aerial vehicles[C]//IEEE International Conference on Digital Object Identifier. Piscataway,NJ:IEEE Press,2012:520-525.
[2]	KOUSKOURICLAS R, BADEKAS E,GASTERATOS A.Simultaneous visual object recognition and position estimation using SIFT[C]//Proceedings Second International Conference on Intelligent Robotics and Applications.Berlin:Springer-Verlag,2009:866-875.
[3]	ZHENG M G, WU C D,CHEN D Y,et al.Rotation and affine-invariant SIFT descriptor for matching UAV images with satellite images[C]//Proceedings of IEEE Chinese Guidance Navigation and Control Conference.Piscataway,NJ:IEEE Press,2014:2624-2628.
[4]	LOWE D G. Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[5]	DALAL N, TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2005:886-893.
[6]	MIKOLAJCZYK K, SCHMID C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[7]	VEDALDI A. An open implementation of the SIFT detector and descriptor:UCLA-CSD-070012[R].Los Angeles:UCLA, 2007.
[8]	ZHAO J,XIN F T. Improved SIFT features in image retrieval using[C]//International Conference on Computer Research and Development.Piscataway,NJ:IEEE Press,2011:393-397.
[9]	MOREL J M, YU G.ASIFT:A new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469.
[10]	TANG H, TANG F.AH-SIFT:Augmented histogram based SIFT descriptor[C]//IEEE International Conference on Image Processing.Piscataway,NJ:IEEE Press,2012:2357-2360.
[11]	WU J,CUI Z,SHENG V S,et al. A comparative study of SIFT and its variants[J].Measurement Science Review,2013,13(3):122-131.
[12]	LOWE D G. Method and apparatus for identifying scale invariant features in an image and use of same for locating an object in an image:US 6711293[P].2004-03-24.
[13]	BROWN M, GANG H,WINDER S.Discriminative learning of local image descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(1):43-57.
[14]	GIL A,MOZOS O M, BALLESTA M,et al.A comparative evaluation of interest point detectors and local descriptors for visual SLAM[J].Machine Vision and Applications,2010,21(6):905-920.
[15]	TAKEZAWA K. Introduction to nonparametric regression[M].Hoboken,NJ:John Wiley & Sons,2006:103-230.