基于FPGA+ARM的实时图像去雾系统设计  

Design of real-time image defogging system based on FPGA+ARM

作　　者：陈曦[1] 钱国明[1] 史艳高 CHEN Xi;QIAN Guoming;SHI Yangao(College of Electronic and Optic Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China)

机构地区：[1]南京邮电大学电子与光学工程学院,江苏南京210023

出　　处：《电子设计工程》2023年第13期192-195,共4页Electronic Design Engineering

摘　　要：针对使用无人机对油料农作物成熟期进行远程巡航勘察的应用场景,为解决雾霾天气下图像质量较差、色彩失真的问题,该文提出一种基于FPGA+ARM的实时图像去雾系统。借助FPGA的并行运算优势,对图像的去雾处理进行加速,通过ARM处理器实现摄像头工作模式、视频数据存储等控制,从整体上提高了有雾图像的数据采集与去雾处理的实时性。系统采用改进的Retinex去雾算法完成滤波函数、色彩空间转换等处理,同时引入Sigmod函数对去雾后图像色彩进行校正。测试结果表明,该系统能够有效恢复出图像原始色彩,具有运算速度快、可移植性高、功耗低等优点,可以满足无人机远程视频勘察的实际需求。In order to solve the problems of poor image quality and color distortion in haze weather,a realtime image defogging system based on FPGA+ARM is proposed.With the parallel operation advantage of FPGA,the image defogging processing is accelerated,and the camera working mode and video data storage are controlled by ARM processor,which improves the real-time performance of data acquisition and defogging processing of foggy images as a whole.The system uses the improved Retinex defogging algorithm to complete the processing of filter function and color space conversion,and introduces Sigmod function to correct the image color after defogging.The test results show that the system can effectively restore the original color of the image,has the advantages of fast operation speed,high portability and low power consumption,and can meet the practical needs of UAV remote video survey.

关 键 词：图像去雾 农作物勘察 FPGA Retinex去雾算法 

分 类 号：TN791[电子电信—电路与系统]