Open AccessStudy and Performance Evaluation Binary Robust Invariant Scalable Keypoints (BRISK) for Underwater Image Stitching
Author(s) -
Didit Andri Jatmiko,
Salita Ulitia Prini
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/879/1/012111
Subject(s) - image stitching , ransac , computer vision , artificial intelligence , underwater , computer science , image warping , homography , binary number , binary image , scale invariant feature transform , scalability , feature extraction , image (mathematics) , image processing , mathematics , oceanography , statistics , projective test , arithmetic , database , projective space , geology
In this paper, performance evaluation of Binary Robust Invariant Scalable Key points (BRISK) for underwater image stitching is presented. Underwater image stitching is quite challenging because usually images produced by underwater cameras have few features and noise such as motion blur and underexposure. In this paper, we proposed a robust algorithm for the underwater image stitching which consists of several stages: taking an image frame, getting a key point using BRISK, feature matching using Random Sample Consensus (RANSAC), homography estimation, and perspective warping. The experimental result shows that the proposed algorithm can be implemented for underwater image and achieve better matching results even the less detected keypoints.