Dense High-definition Image Matching Strategy Based on Scale Distribution of Feature and Geometric Constraint

doi:10.11947/j.AGCS.2018.20170630

Abstract

Abstract: This paper mainly expounds the basic issue three about the intelligent photogrammetry based on machine vision:the intelligent and fast matching process among high-definition images.Image feature matching,as a fundamental data processing procedure,plays an important role in the computational efficiency of computing the digital photogrammetry coordinate space.There are challenges for image feature match including high computational expense due to high-resolution data and similar feature interference.Concerning these problems,the mathematical nature of the invariant feature of image scale was studied,and the geometric model of multi-view camera was used to derive and verify the scale distribution of image feature points.The information interaction process of the scale component in the feature extraction and the matching process was determined.Through the equal-scale feature matching,the calculation amount in the image matching process was reduced and the effective information was retained,which greatly reduced the time of the initial distance matching progress among 10⁵ points in 1 second.On this basis,combining the feature scale distribution and the geometric constraint,the improved feature matching algorithm was used to reduce the matching search range under the limited time and the computational scale.Fast and dense matching achieves through the feature index and the partition parallel processing.Using intel i7-4720HQ and NVIDIA GTX970M,the experiment shows that the feature matching method based on the scale distribution feature has a great advantage in improving the speed and accuracy of automatic image matching and matches thousands of points in less than one second.It provides a new idea for the fast and high precision processing of digital images,which can not only meet the accuracy of digital photogrammetry but greatly improve the efficiency of production.

Key words: scale invariant feature, scale constraint, epipolar geometry, dense matching

CLC Number:

P236

ZHAO Hongrui, LU Shenghan. Dense High-definition Image Matching Strategy Based on Scale Distribution of Feature and Geometric Constraint[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 790-798.

References

[1] 王伟, 黄雯雯, 镇姣. Pictometry倾斜摄影技术及其在3维城市建模中的应用[J]. 测绘与空间地理信息, 2011, 34(3):181-183. WANG Wei, HUANG Wenwen, ZHEN Jiao. Pictometry Oblique Photography Technique and Its Application in 3D City Modeling[J]. Geomatics & Spatial Information Technology, 2011, 34(3):181-183.
[2] WEINMANN M. Visual Features-from Early Concepts to Modern Computer Vision[M]//FARINELLA E M. Advanced Topics in Computer Vision. London UK:Springer, 2013:1-34.
[3] 杨化超, 张书毕, 张秋昭. 基于SIFT的宽基线立体影像最小二乘匹配方法[J]. 测绘学报, 2010, 39(2):187-194. YANG Huachao, ZHANG Shubi, ZHANG Qiuzhao. Least Square Matching Methods for Wide Base-line Stereo Images Based on SIFT Features[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(2):187-194.
[4] 赵璐璐, 耿国华, 李康, 等. 基于SURF和快速近似最近邻搜索的图像匹配算法[J]. 计算机应用研究, 2013, 30(3):921-923. ZHAO Lulu, GENG Guohua, LI Kang, et al. Images Matching Algorithm Based on SURF and Fast Approximate Nearest Neighbor Search[J]. Application Research of Computers, 2013, 30(3):921-923.
[5] 张东兴, 祝明波, 邹建武, 等. 基于相似三角形的SIFT错误匹配点剔除算法研究[J]. 计算机工程与科学, 2012, 34(4):66-70. ZHANG Dongxing, ZHU Mingbo, ZOU Jianwu, et al. Research on Wrong Match Pairs Elimination Based on Similar Triangles in the SIFT Algorithm[J]. Computer Engineering and Science, 2012, 34(4):66-70.
[6] BIAN Jiawang, LIN Wenyan, MATSUSHITA Y, et al. GMS:Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI:IEEE, 2017:2828-2837.
[7] YU Guoshen, MOREL J M. ASIFT:An Algorithm for Fully Affine Invariant Comparison[J]. Image Processing on Line, 2011, 1:11-38.
[8] KE Yan, SUKTHANKAR R. PCA-SIFT:A More Distinctive Representation for Local Image Descriptors[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE, 2004:506-513.
[9] LENC K, VEDALDI A. Learning Covariant Feature Detectors[M]//HUA G, JÉGOU H. Computer Vision-ECCV 2016 Workshops. Cham:Springer, 2016.
[10] BROWN M, HUA G, WINDER S. Discriminative Learning of Local Image Descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(1):43-57.
[11] TRZCINSKI T, CHRISTOUDIAS M, LEPETIT V. Learning Image Descriptors with Boosting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):597-610.
[12] 张永, 武玉建. 一种改进的SIFT图像特征匹配算法[J]. 计算机工程与应用, 2014, 50(9):167-169. ZHANG Yong, WU Yujian. Improved SIFT Image Feature Matching Algorithm[J]. Computer Engineering and Application, 2014, 50(9):167-169.
[13] 程德志, 李言俊, 余瑞星. 基于改进SIFT算法的图像匹配方法[J]. 计算机仿真, 2011, 28(7):285-289. CHENG Dezhi, LI Yanjun, YU Ruixing. Image Matching Method Based on Improved SIFT Algorithm[J]. Computer Simulation, 2011, 28(7):285-289.
[14] 杜振鹏, 李德华. 基于KD-Tree搜索和SURF特征的图像匹配算法研究[J]. 计算机与数字工程, 2012, 40(2):96-98, 126. DU Zhenpeng, LI Dehua. Image Matching Algorithm Research Based on KD-tree Search and SURF Feature[J]. Computer and Digital Engineering, 2012, 40(2):96-98, 126.
[15] 杨松, 邵龙潭, 宋维波, 等. 一种基于SIFT特征的快速图像匹配算法[J]. 计算机应用与软件, 2016, 33(7):186-189, 256. YANG Song, SHAO Longtan, SONG Weibo, et al. A Quick Image Matching Algorithm Based on Sift Feature[J]. Computer Applications and Software, 2016, 33(7):186-189, 256.
[16] ACHARYA K A, BABU V R. Speeding Up SIFT Using GPU[C]//Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics. Jodhpur, India:IEEE, 2013.
[17] MOHAMMADI M S, REZAEIAN M. SiftCU:An Accelerated CUDA Based Implementation of SIFT[C]//Symposium on Computer Science and Software Engineering. Tehran:[s.n.], 2013.
[18] WU C. SiftGPU:A GPU Implementation of Scale Invariant Feature Transform (SIFT)[J]. 2007.
[19] HUANG Yang, LIU Jinshou, TU Meisheng, et al. Research on CUDA-based SIFT Registration of SAR Image[C]//Fourth International Symposium on Parallel Architectures, Algorithms and Programming. Tianjin, China:IEEE, 2011:100-104.
[20] 袁修国, 彭国华, 王琳. 基于GPU的变型SIFT算子实时图像配准[J]. 计算机科学, 2011, 38(3):300-303. YUAN Xiuguo, PENG Guohua, WANG Lin. GPU-based Real Time Image Registration with Variant SIFT[J]. Computer Science, 2011, 38(3):300-303.
[21] FASSOLD H, ROSNER J. A Real-time GPU Implementation of the SIFT Algorithm for Large-scale Video Analysis Tasks[C]//Proc. SPIE 9400, Real-time Image and Video Processing. San Francisco, California:SPIE, 2015:940007.
[22] BRAUX-ZIN J, DUPONT R, BARTOLI A. A General Dense Image Matching Framework Combining Direct and Feature-based Costs[C]//IEEE International Conference on Computer Vision. Sydney, NSW, Australia:IEEE, 2013:185-192.
[23] 何孝莹, 岳建伟, 张栩然. 基于SIFT算法的无人机影像快速匹配[J]. 计算机工程, 2011, 37(7):216-218, 230. HE Xiaoying, YUE Jianwei, ZHANG Xuran. Quick Match of Unmanned Aerial Vehicles Image Based on SIFT Algorithm[J]. Computer Engineering, 2011, 37(7):216-218, 230.
[24] SUN Yanbiao, ZHAO Liang, HUANG S, et al. L2-SIFT:SIFT Feature Extraction and Matching for Large Images in Large-scale Aerial Photogrammetry[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 91:1-16.
[25] LUO Juan, OUBONG G. A Comparison of SIFT, PCA-SIFT and SURF[J]. International Journal of Image Processing, 2009, 3(4):143-152.