[1]张婷婷,陈启兴,郑国玲.基于FPGA的暗通道先验图像去雾算法研究[J].成都信息工程大学学报,2026,41(02):180-184.[doi:10.16836/j.cnki.jcuit.2026.02.007]
　ZHANG Tingting,CHEN Qixing,ZHENG Guoling.Research on FPGA-based Dark Channel Prior Image Dehazing Algorithm[J].Journal of Chengdu University of Information Technology,2026,41(02):180-184.[doi:10.16836/j.cnki.jcuit.2026.02.007]

点击复制

基于FPGA的暗通道先验图像去雾算法研究

成都信息工程大学学报[ISSN:1006-6977/CN:61-1281/TN] 卷: 41 期数: 2026年02期页码: 180-184 栏目: 电子信息科学与技术出版日期: 2026-03-30

Title:: Research on FPGA-based Dark Channel Prior Image Dehazing Algorithm

文章编号:: 2096-1618(2026)02-0180-05

作者:: 张婷婷¹; 陈启兴¹; 郑国玲²; (1.成都信息工程大学通信工程学院,四川成都 610225; 2.成都菁蓉联创科技有限公司开发部,四川成都 610095)

Author(s):: ZHANG Tingting¹; CHEN Qixing¹; ZHENG Guoling²; (1.College of Communication Engineering, Chengdu University of Information Technology, Chengdu 610225, China; 2.Development Department, Chengdu Jingrong Lianchuang Technology Co., Ltd., Chengdu 610095, China)

关键词:: 图像去雾; 大气散射模型; 暗通道; 透射率; FPGA; 实时

Keywords:: image defogging; atmospheric scattering model; dark channel; transmittance; FPGA; real-time

分类号:: TP391.4

DOI:: 10.16836/j.cnki.jcuit.2026.02.007

文献标志码:: A

摘要:: 近年来,随着数字图像处理技术的迅猛发展,图像去雾技术成为科学研究和实际应用中的重要领域。提出一种基于FPGA的改进暗通道先验图像去雾算法,针对图像偏色现象,在估计大气光照强度时采用候选大气光位置选择的方法,以减少偏色影响。同时,在透射率计算中引入引导滤波,以平滑图像并提升亮度。在FPGA实现过程中,优化大气光候选位置的选择,降低大气光照强度的计算复杂度,并用低通滤波器替代引导滤波,进一步简化算法。实验结果表明,该算法能够以160帧/秒的速度对640×480分辨率的有雾图像进行快速去雾,显著提高图像质量和处理实时性,对各类应用系统性能的提升具有积极作用。

Abstract:: In recent years, with the rapid development of digital image processing technology, image dehazing technology has become one of the highly concerned fields in scientific research and practical applications. This article proposes a research on a dark channel prior image dehazing algorithm based on FPGA. The algorithm is optimized based on dark channel images, atmospheric light intensity, and transmittance, and improves image processing efficiency through hardware acceleration to meet the real-time dehazing requirements of high-definition images. The experiment shows that the algorithm can quickly remove fog from foggy images with a resolution of 640×480 at a frame rate of 160 frames per second, which has a positive driving effect on improving image quality, real-time performance, and various application system performance.

参考文献/References:

[1] 庞宇,吴天次,王元发,等.快速视频去雾改进算法的FPGA实现[J/OL].计算机应用研究,1-6[2024-07-05].
[2] 潘雅汶,陈敏聪.实时去雾算法及其FPGA实现研究[J].长江信息通信,2023,36(4):169-171.
[3] 郝振中.基于FPGA的图像去雾算法优化研究[D].南京:南京信息工程大学,2023.
[4] 李俊.基于FPGA的实时图像去雾系统研究与设计[D].昆明:云南大学,2022.
[5] 崔冰琪,解振东,李红.基于暗通道先验图像去雾的方法改进[J].信息通信,2013,26(6):60-61.
[6] 刘杰平,黄炳坤,韦岗.一种快速的单幅图像去雾算法[J].电子学报,2017,45(8):6.
[7] 谢晓辉.基于FPGA的暗通道先验图像去雾算法研究[D].成都:电子科技大学,2022.
[8] 何召兰.基于FPGA的实时去雾系统设计[D].哈尔滨:哈尔滨理工大学,2022.
[9] Golts A,Freedman D,Elad M.Unsupervised single image dehazing using dark channel prior loss[J].IEEE transactions on Image Processing,2019,29:2692-2701.
[10] Tang Q,Yang J,He X,et al.Nighttime image dehazing based on Retinex and dark channel prior using Taylor series expansion[J].Computer Vision and Image Understanding,2021,202:103086.
[11] 王锋,李培灵,梁义涛,等.基于暗通道先验的图像去雾改进算法[J].科学技术与工程,2019,19(33):308-313.
[12] 卫林霄.图像去雾的算法研究与FPGA实现[D].西安:西安电子科技大学,2019.
[13] 张赛赛,田益民,王飞,等.基于对比度和饱和度新的先验图像去雾算法[J].包装工程,2024,45(11):191-197.
[14] 任伟.图像去雾算法研究及在FPGA上实现与优化[D].成都:电子科技大学,2021.
[15] 张韫皓,黎震海,谢泽鸿,等.基于FPGA的实时图像去雾算法改进[J].长江信息通信,2022,35(10):66-68.
[16] 张春雷,徐润,王郁杰,等.基于FPGA的视频实时去雾算法及其硬件实现[J].半导体光电,2021,42(2):264-268+274.

相似文献/References:

[1]叶开,丁妍.一种结合物理模型和景深估算的图像去雾算法[J].成都信息工程大学学报,2021,36(04):390.[doi:10.16836/j.cnki.jcuit.2021.04.007]
　YE Kai,DING Yan.A Dehazing Method Combining Physical Model and Depth Map Estimation[J].Journal of Chengdu University of Information Technology,2021,36(02):390.[doi:10.16836/j.cnki.jcuit.2021.04.007]

备注/Memo

收稿日期:2024-07-08
通信作者:陈启兴.E-mail:953060290@qq.com

更新日期/Last Update: 2026-03-30