A 4K-Capable Hardware Accelerator of Haze Removal Algorithm using Haze-relevant Features

The performance of vision-based intelligent systems, such as self-driving cars and unmanned aerial vehicles, is subject to weather conditions, notably the frequently encountered haze or fog. As a result, studies on haze removal have garnered increasing interest from academia and industry. This paper...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of Information and Communication Convergence Engineering, 20(3) Vol. 20; no. 3; pp. 212 - 218
Main Authors:	Seungmin Lee, Bongsoon Kang
Format:	Journal Article
Language:	English
Published:	한국정보통신학회JICCE 30.09.2022 한국정보통신학회
Subjects:	전자/정보통신공학 Real-time processing Field-programmable gate array Hardware accelerator Haze removal
ISSN:	2234-8255, 2234-8883
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The performance of vision-based intelligent systems, such as self-driving cars and unmanned aerial vehicles, is subject to weather conditions, notably the frequently encountered haze or fog. As a result, studies on haze removal have garnered increasing interest from academia and industry. This paper hereby presents a 4K-capable hardware implementation of an efficient haze removal algorithm with the following two improvements. First, the depth-dependent haze distribution is predicted using a linear model of four haze-relevant features, where the model parameters are obtained through maximum likelihood estimates. Second, the approximated quad-decomposition method is adopted to estimate the atmospheric light. Extensive experimental results then follow to verify the efficacy of the proposed algorithm against well-known benchmark methods. For real-time processing, this paper also presents a pipelined architecture comprised of customized macros, such as split multipliers, parallel dividers, and serial dividers. The implementation results demonstrated that the proposed hardware design can handle DCI 4K videos at 30.8 frames per second. KCI Citation Count: 1
Bibliography:	http://www.jicce.org/
ISSN:	2234-8255 2234-8883
DOI:	10.56977/jicce.2022.20.3.212