摘要
针对视频图像增强处理的应用需求及视频图像场景的多样化特点,给出了一种基于光照-反射模型的低照度图像增强算法及其硬件实现。首先,基于光照-反射模型将亮度图像分解为照度分量、反射分量,并对估计的照度分量进行非线性调节,合成新的亮度图像;然后,引入调整系数对光照估计进行场景补偿以适应不同的场景;最后,在现场可编程逻辑门阵列(FPGA)硬件上进行算法实现。在Altera EP4CE40F23C8 FPGA硬件上实现结果表明,图像增强算法的主、客观处理效果得到明显提升,可满足不同场景的低照度视频图像实时增强处理应用。
In accordance to the application requirements of video image enhancement and the diversification of video scenes, a low illumination image enhancement algorithm based on illumination-reflection model and its hardware realization are proposed. Firstly, the brightness image is decomposed into illumination component and reflection component, and the estimated illumination component is adjusted nonlinearly to synthesize a new brightness image. Secondly, the adjustment coefficient is introduced to compensate the illumination estimation to adapt to different scenes. Finally, the algorithm is implemented on the field-programmable gate array (FPGA) hardware. The results of hardware implementation on Altera EP4CE40F23C8 FPGA show that the subjective and objective processing effects have been improved obviously by the proposed algorithm, and meet the real-time enhancement processing applications of low-illumination video images in different scenes.
作者
黄巧洁
邓华秋
刘建成
Huang Qiaojie;Deng Huaqiu;Liu Jiancheng(School of Intelligent Engineering, Guangdong Agriculture Industry Business Polytechnic, Guangzhou 510507;School of Physics and Optoelectronics, South China University of Technology, Guangzhou 510640)
出处
《高技术通讯》
EI
CAS
北大核心
2019年第8期758-766,共9页
Chinese High Technology Letters
基金
国家级星火计划(2015GA780030)
广东农工商职业技术学院校级重点科研(xyzd1604)资助项目
作者简介
联系人:黄巧洁,女,1981年生,硕士,讲师;研究方向:数字图像处理,计算机通信等;E-mail:qjhuang@gdaib.edu.cn.
