A Comprehensive Overview of Fish-Eye Camera Distortion Correction Methods

TL;DR

This paper reviews various techniques for correcting distortion in fish-eye camera images, including polynomial models, mapping methods, and deep learning, highlighting their advantages and limitations.

Contribution

It provides a comprehensive overview of existing fish-eye distortion correction methods, including recent deep learning approaches, aiding informed method selection.

Findings

Polynomial distortion models effectively correct radial distortions.

Deep learning methods show promising results but have limitations.

Different methods vary in accuracy, computational complexity, and applicability.

Abstract

The fisheye camera, with its unique wide field of view and other characteristics, has found extensive applications in various fields. However, the fisheye camera suffers from significant distortion compared to pinhole cameras, resulting in distorted images of captured objects. Fish-eye camera distortion is a common issue in digital image processing, requiring effective correction techniques to enhance image quality. This review provides a comprehensive overview of various methods used for fish-eye camera distortion correction. The article explores the polynomial distortion model, which utilizes polynomial functions to model and correct radial distortions. Additionally, alternative approaches such as panorama mapping, grid mapping, direct methods, and deep learning-based methods are discussed. The review highlights the advantages, limitations, and recent advancements of each method, enabling readers to make informed decisions based on their specific needs.