Open AccessMethod of optimization of the fundamental matrix by technique speeded up robust features application of different stress images
Author(s) -
Ahmed Chater,
Hicham Benradi,
Abdelali Lasfar
Publication year - 2022
Publication title -
international journal of power electronics and drive systems/international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
eISSN - 2722-2578
pISSN - 2722-256X
DOI - 10.11591/ijece.v12i2.pp1429-1436
Subject(s) - scale invariant feature transform , outlier , fundamental matrix (linear differential equation) , computer science , epipolar geometry , artificial intelligence , pixel , computation , pattern recognition (psychology) , matrix (chemical analysis) , feature (linguistics) , projection (relational algebra) , computer vision , algorithm , mathematics , feature extraction , image (mathematics) , mathematical analysis , linguistics , philosophy , materials science , composite material
The purpose of determining the fundamental matrix (F) is to define the epipolar geometry and to relate two 2D images of the same scene or video series to find the 3D scenes. The problem we address in this work is the estimation of the localization error and the processing time. We start by comparing the following feature extraction techniques: Harris, features from accelerated segment test (FAST), scale invariant feature transform (SIFT) and speed-up robust features (SURF) with respect to the number of detected points and correct matches by different changes in images. Then, we merged the best chosen by the objective function, which groups the descriptors by different regions in order to calculate ‘F’. Then, we applied the standardized eight-point algorithm which also automatically eliminates the outliers to find the optimal solution ‘F’. The test of our optimization approach is applied on the real images with different scene variations. Our simulation results provided good results in terms of accuracy and the computation time of ‘F’ does not exceed 900 ms, as well as the projection error of maximum 1 pixel, regardless of the modification.