Real-time haze removal by GPU acceleration based on dark channel prior algorithm

被引：0

作者：

Xu, Huan ^{[1
,2
,3
]}

Xiang, Wending ^{[1
,2
,3
]}

Liu, Wenjin ^{[1
,2
]}

Guo, Zhenghua ^{[1
,2
,3
]}

Wu, Junlong ^{[1
,2
,3
]}

Yang, Ping ^{[1
,2
]}

Xu, Bing ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, Key Lab Adapt Opt, Chengdu 610209, Sichuan, Peoples R China

[2] Chinese Acad Sci, Inst Opt & Elect, Chengdu 610209, Sichuan, Peoples R China

[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China

来源：

AOPC 2017: OPTICAL SENSING AND IMAGING TECHNOLOGY AND APPLICATIONS | 2017年 / 10462卷

关键词：

haze removal; dark channel prior; GPU; real-time;

D O I：

10.1117/12.2284753

中图分类号：

TP7 [遥感技术];

学科分类号：

081102 ; 0816 ; 081602 ; 083002 ; 1404 ;

摘要：

Dark channel prior haze removal algorithm is very simple and effective for single image haze removal, but it's somehow limited by color distortion in gray areas and expenditure of time. Firstly, aiming at solving color distortions, we propose a modified dark channel prior haze removal algorithm. We correct the transmission of the gray areas by introducing the correction parameter, and the transmission is unchanged when the areas meet the law of dark channel prior. Secondly, to realize real-time haze removal for video surveillance, we use GPU to parallel accelerate and optimize the new algorithm on Compute Unified Device Architecture platform released by NVIDIA. Experiments show that the modified algorithm works effectively in gray areas. At the same time, the processing speed of images with a resolution of 640x480 can reach 37 frames per second after GPU acceleration and can also obtain the real-time haze removal result.

引用

页数：7

共 50 条

[1] Modified Image Haze Removal Algorithm Based on Dark Channel Prior
Hu, Junpeng
Li, Zuoyong
Chen, Xinwei
2019 IEEE INTL CONF ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, BIG DATA & CLOUD COMPUTING, SUSTAINABLE COMPUTING & COMMUNICATIONS, SOCIAL COMPUTING & NETWORKING (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2019), 2019, : 1600 - 1605
[2] A Modified Haze Removal Algorithm Using Dark Channel Prior
Wu, Xiaotian
Ding, Xinghao
Xiao, Quan
ADVANCED MATERIALS AND ENGINEERING MATERIALS, PTS 1 AND 2, 2012, 457-458 : 1397 - 1402
[3] Real-time hardware accelerator for single image haze removal using dark channel prior and guided filter
Liang, Zhengfa
Liu, Hengzhu
Zhang, Botao
Wang, Benzhang
IEICE ELECTRONICS EXPRESS, 2014, 11 (24):
[4] An Improved Single Image Haze Removal Algorithm Based on Dark Channel Prior and Histogram Specification
Yang, Shuai
Zhu, Qingsong
Wang, Jianjun
Wu, Di
Xie, Yaoqin
PROCEEDINGS OF 3RD INTERNATIONAL CONFERENCE ON MULTIMEDIA TECHNOLOGY (ICMT-13), 2013, 84 : 279 - 292
[5] A haze removal algorithm combining fractional differential, dark channel prior and Retinex
Ma R.-G.
Wang W.-X.
Liu W.
Zhang Y.
Xu L.
Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science), 2016, 44 (09): : 16 - 23
[6] Fast Haze Removal of UAV Images Based on Dark Channel Prior
Zhang, Siyu
Li, Congli
Xue, Song
IMAGE AND VIDEO TECHNOLOGY (PSIVT 2017), 2018, 10799 : 254 - 267
[7] Image Haze Removal of Wiener Filtering Based on Dark Channel Prior
Shuai, Yanjuan
Liu, Rui
He, Wenzhang
PROCEEDINGS OF THE 2012 EIGHTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2012), 2012, : 318 - 322
[8] FPGA Implementation of Haze Removal Technique Based on Dark Channel Prior
Varalakshmi, J.
Jose, Deepa
Kumar, P. Nirmal
COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING, 2020, 1108 : 624 - 630
[9] Image Haze Removal Using Dark Channel Prior
Liu, ShaSha
Shen, Xianghui
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER, NETWORKS AND COMMUNICATION ENGINEERING (ICCNCE 2013), 2013, 30 : 269 - 271
[10] Image-Based Automated Haze Removal Using Dark Channel Prior
Uddin, Mohammad Shorif
Gautam, Bishal
Sarker, Aditi
Akter, Morium
Haque, Mohammad Reduanul
2017 IEEE REGION 10 HUMANITARIAN TECHNOLOGY CONFERENCE (R10-HTC), 2017, : 412 - 415

← 1 2 3 4 5 →