MAPD: An FPGA-Based Real-Time Video Haze Removal Accelerator Using Mixed Atmosphere Prior

计算机科学 现场可编程门阵列 库达 大气(单位) 薄雾 人工智能 计算机视觉 计算机图形学(图像) 计算机硬件 并行计算 气象学 物理
作者
Yanjie Tan,Yifu Zhu,Zhaoyang Huang,Huailiang Tan,Keqin Li
出处
期刊:IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems [Institute of Electrical and Electronics Engineers]
卷期号:42 (12): 4777-4790 被引量:7
标识
DOI:10.1109/tcad.2023.3291670
摘要

Real-time video dehazing plays a key role in helping autonomous driving detect pedestrians or obstacles in severe foggy weather to prevent potential hazards. Existing video dehazing methods achieve good restoration performance but still suffer from oversaturation and low dehazing speed, especially for high-definition (HD, high-resolution) videos. In this article, we propose a mixed atmosphere prior information video dehazing accelerator (MAPD) and implement it on field programmable gate array (FPGA) to achieve real-time haze removal for HD video. MAPD provides a mixed atmospheric light model by applying heterogeneous atmospheric light in the foreground area to balance brightness deviation, and maintaining the global atmospheric light in the background region. Considering the parallel characteristics of FPGA, MAPD leverages the redundant information between adjacent frames to accelerate the dehazing process and designs an indirect transmission estimation to decrease resource consumption. For comparison, we also implement six dehazing solutions (DCP, color ellipsoid prior (CEP), RDCP, FFVD, MHVD, and REFD) on FPGA, and deploy a graphics processing unit (GPU)-based method $(D^{4})$ on the platform with Nvidia 3080 GPU. Experiments using two widely used benchmarks show that MAPD increases the performance by up to 36.5%, 53.5%, 36.3%, 33.3%, 11.9%, and 23.3%, decreases resource consumption by up to 79.7%, 75.0%, 74.8%, 25.6%, 22.6%, and 73.9% and enhances FPS for HD videos by up to 241.6%, 145.9%, 151.7%, 68.6%, 50.6%, and 62.4%, compared with DCP, CEP, RDCP, FFVD, MHVD, and REFD. Compared to $D^{4}$ , MAPD also promotes the dehazing performance by up to 21.8%, and increases FPS by up to 487.0%.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
waive完成签到,获得积分10
刚刚
wu完成签到,获得积分10
1秒前
星辰大海应助楠楠采纳,获得10
1秒前
1秒前
Qiao应助耍酷曼雁采纳,获得30
2秒前
阳佟半仙发布了新的文献求助10
2秒前
乐观的海雪完成签到,获得积分20
2秒前
3秒前
3秒前
miao发布了新的文献求助10
3秒前
moneymoney完成签到,获得积分10
3秒前
清新的Q完成签到,获得积分10
4秒前
4秒前
高高高完成签到,获得积分10
5秒前
5秒前
5秒前
5秒前
6秒前
xiaochuan完成签到,获得积分10
6秒前
尊敬的扬发布了新的文献求助10
6秒前
文静的翠安完成签到,获得积分10
6秒前
猫猫发布了新的文献求助10
6秒前
UU完成签到,获得积分10
6秒前
善良身影发布了新的文献求助10
6秒前
7秒前
DEREK发布了新的文献求助10
7秒前
xmz完成签到,获得积分10
7秒前
李太白云游四海完成签到,获得积分10
7秒前
Zgrey完成签到,获得积分10
7秒前
烂漫的汲完成签到,获得积分10
8秒前
jingyi完成签到,获得积分10
8秒前
石石刘发布了新的文献求助10
8秒前
yang完成签到,获得积分10
8秒前
zhaofw完成签到,获得积分10
9秒前
甜酒发布了新的文献求助10
9秒前
9秒前
wyl发布了新的文献求助10
9秒前
传奇3应助ty采纳,获得10
9秒前
9秒前
willow完成签到,获得积分10
9秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968934
求助须知:如何正确求助?哪些是违规求助? 3513835
关于积分的说明 11170238
捐赠科研通 3249167
什么是DOI,文献DOI怎么找? 1794650
邀请新用户注册赠送积分活动 875278
科研通“疑难数据库(出版商)”最低求助积分说明 804755