ZHAO Zheng1,2, LING Xiao3, SUN Changkui1, LI Yongzhi1
1. China Aero Geophysical Survey and Remote Sensing Center for Land and Resources, Beijing 100083, China;
2. Key Laboratory of Airborne Geophysics and Remote Sensing Geology, Ministry of Land and Resources, Beijing 100083, China;
3. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
In full consideration of the characteristics of the UAV tilted images, this paper presents an UAV tilt image matching method based on POS. Compared with existing matching method, this paper firstly introduces the global SRTM data as auxiliary to forecast the images overlap area, and secondly set up an approximate relationship of epipolar line between images to exclude the gross error. As known to all, the SIFT matching algorithm has large computation and spends a lot of time, so this paper replaces it with SIFT GPU to improve operating efficiency. Specially, this paper refines the accuracy of POS step by step, because the initial accuracy of POS is not high. The experimental results of UAV tilt images from different tilt cameras shows that this method can provide a sufficient number of corresponding points which are evenly distributed and correct.
赵政, 凌霄, 孙长奎, 李勇志. 基于POS的无人机倾斜影像匹配方法[J]. 国土资源遥感, 2016, 28(1): 87-92.
ZHAO Zheng, LING Xiao, SUN Changkui, LI Yongzhi. UAV tilted images matching research based on POS. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(1): 87-92.
[1] 李德仁,李明.无人机遥感系统的研究进展与应用前景[J].武汉大学学报:信息科学版,2014,39(5):505-513. Li D R,Li M.Research advance and application prospect of unmanned aerial vehicle remote sensing system[J].Geomatics and Information Science of Wuhan University,2014,39(5):505-513.[2] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.[3] Lowe D G.Local feature view clustering for 3D object recognition[C]//The Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Kauai,HI,USA:IEEE,2001:I-682-I-688.[4] Lowe D G.Object recognition from local scale-invariant features[C]//The Proceedings of the 7th IEEE International Conference on Computer Vision.Kerkyra:IEEE,1999:1150-1157.[5] Lowe D G.Fitting parameterized three-dimensional models to images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(5):441-450.[6] 李芳芳,肖本林,贾永红,等.SIFT算法优化及其用于遥感影像自动配准[J].武汉大学学报:信息科学版,2009,34(10):1245-1249. Li F F,Xiao B L,Jia Y H,et al.Improved SIFT algorithm and its application in automatic registration of remotely-sensed imagery[J].Geomatics and Information Science of Wuhan University,2009,34(10):1245-1249.[7] Fischler M A,Bolles R C.Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395.[8] 刘立,彭复员,赵坤,等.采用简化SIFT算法实现快速图像匹配[J].红外与激光工程,2008,37(1):181-184. Liu L,Peng F Y,Zhao K,et al.Simplified SIFT algorithm for fast image matching[J].Infrared and Laser Engineering,2008,37(1):181-184.[9] 陈信华.SIFT特征匹配在无人机低空遥感影像处理中的应用[J].现代测绘,2007,30(6):10-12. Chen X H.The application of SIFT feature matching in the process of unmanned air vehicle remotely-sensed imagery on the low altitude[J].Modern Surveying and Mapping,2007,30(6):10-12.[10] 张祖勋,张剑清.数字摄影测量学[M].武汉:武汉大学出版社,1997. Zhang Z X,Zhang J Q.Digital Photogram-Metry[M].Wuhan:Wuhan University Press,1997.[11] 王瑞,梁华,蔡宣平.基于GPU的SIFT特征提取算法研究[J].现代电子技术,2010,33(15):41-43. Wang R,Liang H,Cai X P.Study of SIFT feature extraction algorithm based on GPU[J].Modern Electronics Technique,2010,33(15):41-43.
2016, Vol. 28 
