Rotation and affine-invariant SIFT descriptor for matching UAV images with satellite images

Image matching is a key issue in Vision-Based UAV navigation problems. This paper presents an affine and rotation-invariant SIFT features descriptor for matching UAV image with satellite images. The SIFT and ASIFT algorithm are nowadays widely applied for robust image matching, but it also has a high computational complexity. SURF is used for real-time UAV position estimation but is not satisfied for affine invariant. We introduce the new SIFT feature descriptor based on pie chart region. This descriptor is invariant for rotation, affine, scale and the dimension of the feature vector is relatively reduced. Therefore, this method satisfies robustness and low computational complexity. Experiments show that this method can improve the matching accuracy and robustness.

[1]  Patrick Doherty,et al.  Vision-based pose estimation for autonomous indoor navigation of micro-scale Unmanned Aircraft Systems , 2010, 2010 IEEE International Conference on Robotics and Automation.

[2]  Aly A. Farag,et al.  CSIFT: A SIFT Descriptor with Color Invariant Characteristics , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Farhad Samadzadegan,et al.  Vision-Aided Inertial Navigation for Pose Estimation of Aerial Vehicles , 2009 .

[4]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[5]  Xueyuan Guan,et al.  A GPU accelerated real-time self-contained visual navigation system for UAVs , 2012, 2012 IEEE International Conference on Information and Automation.

[6]  Wen Gao,et al.  PQ-WGLOH: A bit-rate scalable local feature descriptor , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Guozun Men,et al.  Improved SIFT features in image retrieval using , 2011, 2011 3rd International Conference on Computer Research and Development.

[8]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[9]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[10]  G. Conte,et al.  An Integrated UAV Navigation System Based on Aerial Image Matching , 2008, 2008 IEEE Aerospace Conference.

[11]  Pengpeng Zhao,et al.  A Comparative Study of SIFT and its Variants , 2013 .

[12]  Zhihao Cai,et al.  Vison-based auxiliary navigation method using augmented reality for unmanned aerial vehicles , 2012, IEEE 10th International Conference on Industrial Informatics.

[13]  Hamid R. Rabiee,et al.  RASIM: A Novel Rotation and Scale Invariant Matching of Local Image Interest Points , 2011, IEEE Transactions on Image Processing.

[14]  Jean-Michel Morel,et al.  ASIFT: A New Framework for Fully Affine Invariant Image Comparison , 2009, SIAM J. Imaging Sci..

[15]  F. Samadzadegan,et al.  Vision-based pose estimation for autonomous outdoor navigation of aerial vehicles , 2011, The 2nd International Conference on Control, Instrumentation and Automation.

[16]  Linda G. Shapiro,et al.  A SIFT descriptor with global context , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).