Adopted Image Matching Techniques for Aiding Indoor Navigation
Mohamed Ramadan1, Mohamed El-Tokhey2, Ayman Ragab3, Tamer Fathy4, Ahmed Ragheb5
1Mohamed Ramadn, Assistant Lecturer, Public Works Department, Ain Shams University/ Faculty of Engineering/ Cairo, Egypt.
2Mohamed El-Tokhey, Professors, Public Works Department, Ain Shams University/ Faculty of Engineering/ Cairo, Egypt.
3Ayman Ragab, Professors, Public Works Department, Ain Shams University/ Faculty of Engineering/ Cairo, Egypt.
4Tamer Fathy, Professors, Public Works Department, Ain Shams University/ Faculty of Engineering/ Cairo, Egypt.
5Ahmed Ragheb, Associate Professor, Public Works Department, Ain Shams University/ Faculty of Engineering/ Cairo, Egypt.
Manuscript received on 27 November 2020 | Revised Manuscript received on 03 December 2020 | Manuscript Accepted on 15 December 2020 | Manuscript published on 30 December 2020 | PP: 1-11 | Volume-1 Issue-1, December 2020 | Retrieval Number: A1001121120/2020©LSP
Open Access | Ethics and Policies | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fast and accurate image matching is a very important task with various applications in computer vision and robotics. In this research, we compare the performance of all available feature detection techniques (HARRIS, GFTT, SIFT, SURF, STAR, FAST, ORB, MSER, Dense, and Simple Blob), feature description techniques (SIFT, SURF, BRIEF, and ORB), and image matching techniques (Brute Force, BruteForce-L1, Brute Force-Hamming, Brute Force-Hamming LUT, and Flann Based) against different kinds of geometric distortions and deformations such as scaling, rotation, fish-eye distortion, and shearing. To perform this task, we manually apply different types of transformations on original images and compute the matching evaluation parameters such as the number of key points in images, the processing time, and the matching accuracies for each algorithm and we will show that which algorithm is the best more robust against these distortions.
Keywords: Feature Detector, Feature Descriptor, Image Matching, Indoor Navigation, Open CV.