FSD-BRIEF: A Distorted BRIEF Descriptor for Fisheye Image Based on Spherical Perspective Model

Abstract

Fisheye images with a far larger Field of View (FOV) have severe radial distortion, with the result that the associated image feature matching process cannot achieve the best performance if the traditional feature descriptors are used. To address this challenge, this paper reports a novel distorted Binary Robust Independent Elementary Feature (BRIEF) descriptor for fisheye images based on a spherical perspective model. Firstly, the 3D gray centroid of feature points is designed, and the position and direction of the feature points on the spherical image are described by a constructed feature point attitude matrix. Then, based on the attitude matrix of feature points, the coordinate mapping relationship between the BRIEF descriptor template and the fisheye image is established to realize the computation associated with the distorted BRIEF descriptor. Four experiments are provided to test and verify the invariance and matching performance of the proposed descriptor for a fisheye image. The experimental results show that the proposed descriptor works well for distortion invariance and can significantly improve the matching performance in fisheye images.

PSiamRML: Target Recognition and Matching Integrated Localization Algorithm Based on Pseudo-Siamese Network

“…In this way, we can ensure that the same features can be extracted from different images of the same scene. Traditional feature extraction methods include scale-invariant feature transform (SIFT) [29], speeded up robust features (SURF) [30], oriented fast and rotated brief (ORB) [31], affine SIFT (ASIFT) [32], binary robust invariant scalable keypoints (BRISK) [33], and binary fisheye spherical distorted robust independent elementary features (FSD-BRIEF) [34]. These algorithms rely on handdesigned feature descriptors; thus, their real-time performance and robustness need to be further improved.…”

Multi-Modal Scene Matching Location Algorithm Based on M2Det

“…In feature-based image-matching methods, feature extraction is a very important component. Traditional feature extraction methods mainly include scale-invariant feature transform (SIFT) [18], oriented fast and rotated brief (ORB) [19], features from accelerated segment test (FAST) [20], histogram of orientated gradient (HOG) [21], affine-SIFT (ASIFT) [22], binary robust invariant scalable keypoints (BRISK), binary fisheye spherical distorted robust independent elemental features (FSD-BRIEF) [23], etc. Because traditional feature extraction methods do not fully utilize data, they can only extract certain aspects of image features.…”