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

	Real-time haze removal by GPU acceleration based on dark channel prior algorithm
	Huan Xu[1,2,3], Wending Xiang[1,2,3], Wenjin Liu[1,2], Zhenghua Guo[1,2,3], Junlong Wu[1,2,3], Ping Yang[1,2], Bing Xu[1,2]
	2017
会议名称	Proceedings of SPIE: AOPC 2017: Optical Sensing and Imaging Technology and Applications
会议录名称	0277-786X
卷号	10462
页码	104622I
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.
关键词	haze removal, dark channel prior, GPU, real-time
语种	英语
EI分类号	2017-2154
文献类型	会议论文
条目标识符	http://ir.ioe.ac.cn/handle/181551/9022
专题	自适应光学技术研究室（八室）
作者单位	1.Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu , Sichuan, China,610209 2.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, Sichuan, China,610209 3.University of Chinese Academy of Sciences, Beijing, China , 100049
推荐引用方式 GB/T 7714	Huan Xu[1,2,3], Wending Xiang[1,2,3], Wenjin Liu[1,2], Zhenghua Guo[1,2,3], Junlong Wu[1,2,3], Ping Yang[1,2], Bing Xu[1,2]. Real-time haze removal by GPU acceleration based on dark channel prior algorithm[C],2017:104622I.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2017-2154.pdf（401KB）	会议论文		开放获取	CC BY-NC-SA	请求全文