Hardware Implementation for Haze Removal With Adaptive Filtering

Bin Zhang,Jing Wei

doi:10.1109/access.2019.2944186

Bin Zhang, Jing Wei

Open Access

https://doi.org/10.1109/access.2019.2944186

Copy DOI

Abstract

Haze removal is useful in computational photography and computer vision applications. Single image haze removal is still a challenge for real-time embedded systems. In general, dark channel prior approach can effectively remove haze from a single image. However, the halo effect is the major problem of dehazing. In this study, adaptive filtering, which is easy for VLSI design, is introduced to refine the transmission map and improve the result of haze removal. A hardware architecture for our haze removal method is proposed to achieve the real-time requirement. A specific hardware component is designed to compute lengths of the paths and adaptive structuring element (ASE). The hardware architecture for haze removal is implemented in 180 nm CMOS technology and occupies 5.46 mm 2 with 143 K bit on-chip memory. The design can operate at 177MHz and support for HD (1280×720) 192 frame/s. Experiment results show that the hardware implementation is suitable in embedded system for real-time HD applications.

Highlights

The demand for embedded intelligence systems in outdoor surveillance systems, advanced driver assistance systems, and unmanned aerial vehicles is currently increasing
Guided image filter (GIF) [23], globally guided image filtering [26], The associate editor coordinating the review of this manuscript and approving it for publication was Nitin Nitin
Given that A and t cannot be estimated from the hazy image I, J cannot be computed by Equation (2) from the single image

Summary

Introduction

The demand for embedded intelligence systems in outdoor surveillance systems, advanced driver assistance systems, and unmanned aerial vehicles is currently increasing. Image processing-based methods [2]–[4] do not consider the reasons of the image degradation. They enhance contrast and saturability, but degrade visibility and lose depth information. Single image dehazing methods [10]–[15], which use assumptions and priors, have been used as well. These methods model the process of hazing and invert the process. The hazy images can be compensated by using the model They are the most widely used methods.

Objectives

Methods

Results

Conclusion