A comparative analysis of feature detection and matching algorithms for aerial image stitching

Jolhip, Mohd Ismail and Minoi, Jacey Lynn and Lim, Terrin (2017) A comparative analysis of feature detection and matching algorithms for aerial image stitching. Journal of Telecommunication, Electronic and Computer Engineering, 9 (2-10). pp. 85-90. ISSN 2180-1843

[img] PDF

Download (1kB)
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....


Features detection and matching are the essential processes in image mosaicing and computer vision applications. Our work intend to find descriptors that are obtained by considering all interest/feature points and its locations on images, and then form a set of corresponding spatial relations based on the interest points between images. Hence in this paper, we will evaluate and present the performance of a few detector-descriptor-matcher approaches on raw aerial images for stitching image purposes. We have experimented on Canny Edge Detector, SIFT and SURF approaches to extract feature points. The extracted descriptors are then matched using FLANN based matcher. Finally, the RANSAC Homography is used to estimate the transformation model so stitching procedure could be applied in order to produce a mosaic aerial image. The results have shown that SURF approach outperforms the others in terms of its robustness of the method and higher speed in execution time.

Item Type: Article
Uncontrolled Keywords: Feature Detection, Feature Matching, Image Stitching, Interest Points, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak.
Subjects: T Technology > T Technology (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Academic Faculties, Institutes and Centres > Institute of Social Informatics and Technological Innovations
Depositing User: Ibrahim
Date Deposited: 01 Mar 2018 07:25
Last Modified: 01 Mar 2018 07:25
URI: http://ir.unimas.my/id/eprint/19715

Actions (For repository members only: login required)

View Item View Item