Research on matching algorithm of UAV infrared sensor data
LI Qian1,2, GAN Zheng3, ZHI Xiaodong2, LIU Yue4, WANG Jianchao2, JIN Dingjian2
1. China University of Geosciences(Beijing), Beijing 100083, China;
2. China Aero Geophysical Survey and Remote Sensing Center for Land and Resources, Beijing 100083, China;
3. Changjiang Spatial Information Technology Engineering Co., Ltd, Wuhan 410010, China;
4. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
Low-altitude UAV remote sensing technology has become an important means of remote sensing technology. With the continuous development of the technology, its sensors have also changed from the visible ones to the multi/hyperspectral ones. However, due to the limitations of a small UAV payload on the sensors, the data quality of these new types of sensors is poor and hence it is difficult to deal with existing methods directly. Therefore, the authors studied the data obtained by UAV infrared sensors and then optimized parameters and removed gross errors based on the SIFT matching algorithm. This method has made robust matching results and can solve the key technology of the late mapping application of multi/hyperspectral data. The authors used a set of UAV infrared data to test and verify this method. The experimental results show that this method is capable of obtaining robust matching results and has a great value in improving applications of UAV multi/hyperspectral sensors.
李迁, 甘拯, 支晓栋, 刘玥, 王建超, 金鼎坚. 无人机近红外传感器数据匹配方法[J]. 国土资源遥感, 2017, 29(1): 86-91.
LI Qian, GAN Zheng, ZHI Xiaodong, LIU Yue, WANG Jianchao, JIN Dingjian. Research on matching algorithm of UAV infrared sensor data. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 86-91.
[1] Harris C,Stephens M.A combined corner and edge detector[C]//Proceedings of the 1988 Alvey Vision Conference.Manchester,UK:AVC,1988:147-152.
[2] Rosten E,Drummond T.Machine learning for high-speed corner detection[M]//Leonardis A,Bischof H,Pinz A,eds.Computer Vision-ECCV 2006.Berlin Heidelberg:Springer,2006:430-443.
[3] Calonder M,Lepetit V,Strecha C,et al.Brief:Binary robust independent elementary features[M]//Daniilidis K,Maragos P,Paragios N,eds.Computer Vision-ECCV 2010.Berlin Heidelberg:Springer,2010:778-792.
[4] Matas J,Chum O,Urban M,et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image and Vision Computing,2004,22(10):761-767.
[5] Alahi A,Ortiz R,Vandergheynst P.FREAK:Fast retina keypoint[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Providence:IEEE,2012:510-517.
[6] Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]//Proceedings of 2011 IEEE International Conference on Computer Vision(ICCV).Barcelona:IEEE,2011:2564-2571.
[7] Morel J M,Yu G S.ASIFT:A new framework for fully affine invariant image comparison[J].SIAM Journal on Imaging Sciences,2009,2(2):438-469.
[8] Lowe D G.Object recognition from local scale-invariant features[C]//The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999.Kerkyra:IEEE,1999,2:1150-1157.
[9] Zheng Y,Cao Z G,Xiao Y.Multi-spectral remote image registration based on SIFT[J].Electronics Letters,2008,44(2):107-108.
[10] Aguilera C,Barrera F,Lumbreras F,et al.Multispectral image feature points[J].Sensors,2012,12(9):12661-12672.
[11] Meierhold N,Spehr M,Schilling A,et al.Automatic feature matching between digital images and 2D representations of a 3D laser scanner point cloud[C]//Proceedings of the ISPRS Commission V Mid-Term Symposium on Close Range Image Measurement Techniques.Newcastle:ISPRS,2010,38:446-451.
[12] Sima A,Buckley S J,Kurz T H,et al.Semi-automatic integration of panoramic hyperspectral imagery with photorealistic Lidar models[J].Photogrammetrie-Fernerkundung-Geoinformation,2012(4):443-454.
[13] May M,Turner M J.Scale invariant feature transform:A graphical parameter analysis[C].//Proceedings of the BMVC 2010 UK.Aberystwyth,UK:BMVC,2010:1-11.
2017, Vol. 29 
