High-speed hardware accelerator based on brightness improved by Light-DehazeNet

Due to the increasing demand for artificial intelligence technology in today’s society, the entire industrial production system is undergoing a transformative process related to automation, reliability, and robustness, seeking higher productivity and product competitiveness. Additionally, many hardw...

Full description

Saved in:
Bibliographic Details
Published in:Journal of real-time image processing 2024-05, Vol.21 (3), p.87, Article 87
Main Authors: Teng, Peiyi, Du, Gaoming, Li, Zhenmin, Wang, Xiaolei, Yin, Yongsheng
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Artificial neural networks
Brightness
Computer Graphics
Computer Science
Deep learning
Frames per second
Hardware
Image Processing and Computer Vision
Image reconstruction
Light
Machine learning
Methods
Multimedia Information Systems
Neural networks
Pattern Recognition
Platforms
Product design
Signal,Image and Speech Processing
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the increasing demand for artificial intelligence technology in today’s society, the entire industrial production system is undergoing a transformative process related to automation, reliability, and robustness, seeking higher productivity and product competitiveness. Additionally, many hardware platforms are unable to deploy complex algorithms due to limited resources. To address these challenges, this paper proposes a computationally efficient lightweight convolutional neural network called Brightness Improved by Light-DehazeNet, which removes the impact of fog and haze to reconstruct clear images. Additionally, we introduce an efficient hardware accelerator architecture based on this network for deployment on low-resource platforms. Furthermore, we present a brightness visibility restoration method to prevent brightness loss in dehazed images. To evaluate the performance of our method, extensive experiments were conducted, comparing it with various traditional and deep learning-based methods, including images with artificial synthesis and natural blur. The experimental results demonstrate that our proposed method excels in dehazing ability, outperforming other methods in comprehensive comparisons. Moreover, it achieves rapid processing speeds, with a maximum frame rate of 105 frames per second, meeting the requirements of real-time processing.
ISSN:1861-8200
1861-8219
DOI:10.1007/s11554-024-01464-2