一种透视不变的图像匹配算法

蔡国榕; 李绍滋; 吴云东; 苏松志; 陈水利

doi:10.3724/SP.J.1004.2013.01053

一种透视不变的图像匹配算法

doi: 10.3724/SP.J.1004.2013.01053

1.
集美大学理学院厦门 361021;
2.
厦门大学信息科学与技术学院厦门 361005;
3.
福建省仿脑智能系统重点实验室(厦门大学) 厦门 361005

基金项目:

国家自然科学基金(61103052, 61202143), 国家教育部博士点基金(20090121110032), 福建省产学重大科技项目(2011H6020), 福建省自然科学基金项目 (2011J01013, 2013J01245, 2013J05100) 深圳市科技计划项目(JC200903180630A, ZYB200907110169A), 厦门市科技计划项目(3502Z20123022, 3502Z20110010), 福建省教育厅基金项目 (JK2012025)资助

详细信息

通讯作者:
李绍滋

计量
- 文章访问数: 2235
- HTML全文浏览量: 79
- PDF下载量: 2840
- 被引次数: 0
出版历程
- 收稿日期: 2012-09-20
- 修回日期: 2013-03-19
- 刊出日期: 2013-07-20

A Perspective Invariant Image Matching Algorithm

1.
School of Science, Jimei University, Xiamen 361021;
2.
School of Information Science and Technology, Xiamen University, Xiamen 361005;
3.
Fujian Key Laboratory of the Brain-like Intelligent Systems (Xiamen University), Xiamen 361005

Funds:

Supported by National Natural Science Foundation of China (61103052, 61202143), the National Research Foundation for the Doctoral Program of Higher Education of China (20090121110032), the Key Project for Industry-Academia-Research of Fujian Province (2011H6020), the Natural Science Foundation of Fujian Province (2011J01013, 2013J01245, 2013J05100), Shenzhen Science and Technology Research Foundation (JC200903180630A, ZYB200907110169A), the Natural Science Foundation of Xiamen City (3502Z20123022, 3502Z20110010), and the Projects of Education Department of Fujian Province (JK2012025)

摘要

摘要: 针对ASIFT (Affine scale invariant feature transform) 算法存在的仿射采样策略、采样点离散设置等问题,提出了一种基于粒子群优化的图像透视不变特征PSIFT (Perspective scale invariant feature transform)算法. 该算法通过虚拟相机的透视采样来模拟景物在多视角图像中的变形. 在此基础上,将图像匹配问题转换为透视变换的优化问题,并以粒子群算法为工具,研究了虚拟相机旋转参数搜索空间、适应值函数的合理设定. 针对三组不同类型低空遥感图像的实验结果表明,该算法比ASIFT、SIFT (Scale invariant feature transform)、Harris affine和MSER (Maximally stable extremal regions)等算法获得更多的特征匹配对,有效地提高了算法对视角变化的鲁棒性.
- 图像匹配 /
- 透视变换 /
- SIFT特征 /
- 粒子群优化
Abstract: To solve the problem of affine transform and discrete sampling in ASIFT (Affine scale invariant feature transform), the PSIFT (Perspective scale invariant feature transform), which is based on particle swarm optimization, is proposed in this paper. The proposed algorithm uses a virtual camera and homographic transform to simulate perspective distortion among multi-view images. Therefore, particle swarm optimization is employed to determine the appropriate homography, which is decomposed into three rotation matrices. Experimental results obtained on three categories of low-altitude remote sensing images show that the proposed method outperforms significantly the state-of-the-art ASIFT, SIFT, Harris-affine and MSER, especially when images suffer severe perspective distortion.
- Image matching /
- perspective transform /
- SIFT (Scale invariant feature transform) feature /
- particle swarm optimization (PSO)

HTML全文

参考文献(33)

[1]	Bardera A, Feixas M, Boada I, Sbert M. Image registration by compression. Information Sciences, 2010, 180(7): 1121-1133
[2]	Rajwade A, Banerjee A, Rangarajan A. Probability density estimation using isocontours and isosurfaces: applications to information-theoretic image registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 475-491
[3]	Sun Yan-Yue, He Xiao-Hai, Song Hai-Ying, Chen Wei-Long. A block-matching image registration algorithm for video super-resolution reconstruction. Acta Automatica Sinica, 2011, 37(1): 37-43 (孙琰玥, 何小海, 宋海英, 陈为龙. 一种用于视频超分辨率重建的块匹配图像配准方法. 自动化学报, 2011, 37(1): 37-43)
[4]	Han Yu, Wang Wei-Wei, Feng Xiang-Chu. Iteratively reweighted method based nonrigid image registration. Acta Automatica Sinica, 2011, 37(9): 1059-1066 (韩雨, 王卫卫, 冯象初. 基于迭代重加权的非刚性图像配准. 自动化学报, 2011, 37(9): 1059-1066)
[5]	Harris C, Stephens M. A combined corner and edge detector. In: Proceedings of the 4th Alvey Vision Conference. Manchester, UK: University of Sheffield Printing Unit, 1988. 147-151
[6]	Förstner W. A feature based correspondence algorithm for image matching. International Archives of the Photogrammetry and Remote Sensing, 1986, 26(3): 150-166
[7]	Smith S M, Brady J M. SUSAN — a new approach to low level image processing. International Journal of Computer Vision, 1997, 23(1): 45-78
[8]	Rosten E, Porter R, Drummond T. Faster and better: a machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1): 105-119
[9]	Rublee E, Rabaud V, Konolige K, Bradski G. ORB: an efficient alternative to SIFT or SURF. In: Proceedings of the International Conference on Computer Vision. Barcelona, US: IEEE, 2011. 2564-2571
[10]	Lowe D. Object recognition from local scale-invariant features. In: Proceedings of the 7th IEEE International Conference on Computer vision. Corfu, US: IEEE, 1999. 1150-1157
[11]	Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110
[12]	Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D.C., US: IEEE, 2004. 506-513
[13]	Bay H, Tuytelaars T, van Gool L. Surf: speeded up robust features. In: Proceedings of the European Conference on Computer Vision. Graz, Germany: Springer, 2006. 404-417
[14]	Zeng Luan, Gu Da-Long. A SIFT feature descriptor based on sector area partitioning. Acta Automatica Sinica, 2012, 38(9): 1513-1519 (曾峦, 顾大龙. 一种基于扇形区域分割的SIFT特征描述符. 自动化学报, 2012, 38(9): 1513-1519)
[15]	Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63-86
[16]	Ozuysal M, Calonder M, Lepetit V, Fua P. Fast keypoint recognition using random ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 448-461
[17]	Taylor S, Rosten E, Drummond T. Robust feature matching in 2.3μs. In: Proceedings of the 2009 International Conference on Computer Vision and Pattern Recognition. Miami, US: IEEE, 2009. 15-22
[18]	Lobaton E, Vasudevan R, Alterovitz R, Bajcsy R. Robust topological features for deformation invariant image matching. In: Proceedings of the 2011 International Conference on Computer Vision. Washington D.C., USA: IEEE, 2011. 2516-2523
[19]	Schmidt U, Roth S. Learning rotation-aware features: from invariant priors to equivariant descriptors. In: Proceedings of the 2012 International Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE, 2012. 2050-2057
[20]	Morel J M, Yu G S. ASIFT: a new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 2009, 2(2): 438-469
[21]	Podbreznik P, Potocnik B. Estimating correspondence between arbitrarily selected points in two widely-separated views. Advanced Engineering Informatics, 2010, 24(3): 367-376
[22]	Cao B, Ma C W, Liu A T. Affine-invariant SIFT descriptor with global context. In: Proceedings of the 3rd International Congress on Image and Signal Processing. Yantai, China: IEEE, 2010. 68-71
[23]	Aguilara W, Frauela Y, Escolanob F, Martinez-Perez M E, Espinosa-Romero A, Lozano M A. A robust graph transformation matching for non-rigid registration. Image and Vision Computing, 2009, 27(7): 897-910
[24]	Le Brese C, Zou J J, Uy B. An improved ASIFT algorithm for matching repeated patterns. In: Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010. 2949-2952
[25]	Liu J, Yang J. Action recognition using spatiotemporal features and hybrid generative/discriminative models. Journal of Electronic Imaging, 2012, 21(2): 023010
[26]	Cai Guo-Rong, Li Shao-Zi, Chen Shui-Li, Wu Yun-Dong, Su Song-Zhi. Affine SIFT feature optimization algorithm based on fuzzy control. Fuzzy Systems and Mathematics, 2012, 26(5): 147-153 (蔡国榕, 李绍滋, 陈水利, 吴云东, 苏松志. 基于模糊控制的ASIFT图像特征优化算法. 模糊系统与数学, 2012, 26(5): 147-153)
[27]	Kennedy J, Eberhart R. Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks. Perth, Australia: IEEE, 1995. 1942-1948
[28]	Mikolajczyk K, Schmid C. An affine invariant interest point detector. In: Proceedings of the 7th European Conference on Computer Vision. London, UK: Springer, 2002. 128-142
[29]	Matas J, Chum O, Urban M, Pajdla T. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing, 2004, 22(10): 761-767
[30]	Hashimoto T, Takagi M, Kajiware E. Remote Sensing Note. Tokyo: Japan Association on Remote Sensing, 1999
[31]	Shi Y H, Eberhart R C. Fuzzy adaptive particle swarm optimization. In: Proceedings of the 2001 IEEE Congress on Evolutionary Computation. San Francisco, USA: IEEE, 2001. 101-106
[32]	Ratnawecra A, Halgamuge S, Watson H C. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients. IEEE Transactions on Evolutionary Computation, 2004, 8(3): 240-255
[33]	Cai Guo-Rong, Chen Shui-Li, Li Shao-Zi, Wu Yun-Dong. Cooperative particle swarm optimization algorithm based on adaptive migratory operator. Journal of Xiamen University (Natural Science), 2010, 49(6): 772-778 (蔡国榕, 陈水利, 李绍滋, 吴云东. 一种具有自适应迁移能力的多粒子群协同优化算法. 厦门大学学报 (自然科学版), 2010, 49(6): 772-778)