Feature Matching Improvement through Merging Features for Remote Sensing Imagery

Feature matching is the core stage for object recognition, tracking and several applications of computer vision. Low resolution images have various limitations with respect to spatial, spectral, pixel and temporal information which reduces the performance of image processing approaches. We have combined SURF features with FAST and BRISK features individually in order to provide an optimal solution for feature matching. Furthermore, feature matching has exploited through combined features and compared the performance with state-of-the-art methods. Lastly, RANSAC and MSAC were utilized to eliminate the wrong matches to get optimal feature matches. The experimental results show that the combination of FAST–SURF and BRISK–SURF perform feature matching optimally according to the number of feature matches and estimated time.

[1]  Lingjia Gu.  An Automatic Target Image Mosaic Algorithm , 2007, EUROCON 2007 - The International Conference on "Computer as a Tool".

[2]  Jie Pan,et al.  A new moving objects detection method based on improved SURF algorithm , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[3]  Frédéric Jurie,et al.  Vehicle detection in aerial imagery : A small target detection benchmark , 2016, J. Vis. Commun. Image Represent..

[4]  Qiang Wang,et al.  A Fast Method for Feature Matching Based on SURF , 2011, IScIDE.

[5]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[6]  Taejung Kim,et al.  Automatic satellite image registration by combination of matching and random sample consensus , 2003, IEEE Trans. Geosci. Remote. Sens..

[7]  Tamim Asfour,et al.  Combining Harris interest points and the SIFT descriptor for fast scale-invariant object recognition , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Saptadi Nugroho,et al.  Features Deletion on Multiple Objects Recognition using Speeded-Up Robust Features, Scale Invariant Feature Transform and Randomized KD-Tree , 2016 .

[9]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[10]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[11]  Zhang Huijuan,et al.  Fast image matching based-on improved SURF algorithm , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[12]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[13]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[14]  Wang Wei,et al.  Image Matching for Geomorphic Measurement Based on SIFT and RANSAC Methods , 2008, 2008 International Conference on Computer Science and Software Engineering.

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

[16]  Xiang Ying,et al.  3D Point Cloud Initial Registration Using Surface Curvature and SURF Matching , 2018 .

[17]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[18]  Mark Hedley,et al.  Fast corner detection , 1998, Image Vis. Comput..

[19]  Ye Zhang,et al.  Comparative analysis of feature extraction methods in satellite imagery , 2017 .

[20]  Ethan Rublee,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.