Feature Matching Improvement through Merging Features for Remote Sensing Imagery

Shahid Karim*, Ye Zhang, Ali Anwar Brohi, Muhammad Rizwan Asif

*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

3 Citations (Scopus)


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.

Original languageEnglish
Article number52
Journal3D Research
Publication statusPublished - 1 Dec 2018
Externally publishedYes


  • FAST
  • Feature matching
  • SURF


Dive into the research topics of 'Feature Matching Improvement through Merging Features for Remote Sensing Imagery'. Together they form a unique fingerprint.

Cite this