摘要
视觉传感器暴露在雾霾、沙尘等复杂环境时,可见光图像的品质急剧下降,通过图像增强算法可以还原场景本来面貌并改善画面的质量。设计了一种基于FPGA的实时图像增强处理系统,利用FPGA硬件化并行处理的特点,通过RTL级逻辑资源综合实现了双边滤波图像增强算法,并通过分时复用及多级并行流水设计,使系统达到了全实时的处理速度,算法处理延迟小于5. 9 ms,满足了实时视频处理的性能要求。
In the hazy,and dust weather,visible light video image quality declined sharply.By the image dehazing algorithm,the original scene is recovered.Thus quality of video image can be greatly boosted.In order to cope the requirement for real time image processing on embedded systems,an image enhancement system with FPGA processor is designed in this paper.For the better computing efficiency on the embedded systems,the recursive bilateral filter based image enhancement algorithm is optimized to its pipeline paralleled form.According to the testing of the FPGA image processing hardware platform,it only has 5.9 ms output delay for input PAL standard video signal and reach the requirement for real time applications.
作者
王闯
WANG Chuang(Xi′an Aeronautics Computing Technique Research Institute,AVIC,Xi′an 710068,China)
出处
《航空计算技术》
2018年第5期255-256,260,共3页
Aeronautical Computing Technique
基金
装备预研中航工业联合基金项目资助(6141B05060402)
关键词
图像增强
并行计算
双边滤波
FPGA
image enhancement
parallel computing
bilateral filter
FPGA