摘要
针对串行架构的处理器如ARM和DSP等实现双边滤波算法消耗资源过多的情况,提出了一种基于FPGA加速的双边滤波去噪的实现方法。根据双边滤波算法的原理以及FPGA的硬件资源,充分发挥FPGA在并行计算上的优势,在滤波器的系数生成和除法操作上进行了优化。在减少了FPGA所消耗的资源的同时,保证了图像去除噪声的实时性,从而为后期的视频采集与传输系统奠定了一个良好的开端。
Considering that general serial processors, such as ARM and DSP, consume too many resources, we propose a method for a bilateral filter based on FPGA acceleration. According to the theory of a bilateral filter and the hardware resources that an FPGA can provide, we optimize the coefficient generation and division operation of the filter in the FPGA, which takes full advantage of the parallel computing capabilities in the FPGA. This ensures that the image is filtered in real-time, while reducing the resources consumed by the FPGA, and provides a good foundation for the later design of the video capture and transmission systems.
引文
[1]王萍,白光远,唐晓燕.基于FPGA的图像中值滤波算法的优化及实现[J].电子与电脑,2009(10):94-96.WANG Ping,BAI Guangyuan,TANG Xiaoyang.Median filter algorithm optimize and executebased on FPGA[J].Compotech China,2009(10):94-96.
[2]梁广顺,汪日伟,温显斌.基于双边滤波与非局部均值的图像去噪研究[J].光电子·激光,2015,26(11):2231-2235.LIANG Guangshun,WANG Riwei,WEN Xianbin.Image denoising based on bilateral filtering and non-local means[J].Journal of Optoelectronics·Laser,2015,26(11):2231-2235.
[3]白书华.基于FPGA的实时图像采集和去噪系统设计[J].航天器环境工程,2016,33(2):163-166.BAI Shuhua.Design of real-time image acquisition and denoising based on FPGA[J].Spacecraft Environment Engineering,2016,33(2):163-166.
[4]李红平,陈祥望,徐丹.基于双边滤波的HDR图像色调映射算法[J].云南大学学报:自然科学版,2014,36(3):341-346.LI Hongping,CHEN Xiangwang,XU Dan.HDR image tone mapping algorithms based on bilateral filtering[J].Journal of Yunnan University:Natural science,2014,36(3):341-346.
[5]田小平,姜薇,吴成茂.基于双边滤波的低亮度图像增强算法[J].西安邮电大学学报,2016,21(4):43-47.TIAN Xiaoping,JIANG Wei,WU Chengmao.Low luminance image enhancement based on bilateral filtering[J].Journal of Xi’an university of Posts and Telecommunications,2016,21(4):43-47.
[6]梁超,马天翔.基于黑体标定的红外图像非均匀性校正系统设计[J].中国光学,2016,9(3):385-393.LIANG Chao,MA Tianxiang.Design of infrared imaging nonuniformity correction system based on black body calibration[J].Chinese Optics,2016,9(3):385-393.