基于视网膜中央凹视觉的生产监控图像处理方法  

Production monitoring image processing based on foveated vision

作　　者：郑勇[1] 刘大成[1] 

机构地区：[1]清华大学工业工程系,北京100084

出　　处：《清华大学学报（自然科学版）》2005年第2期258-261,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金面上项目(50205015);北京市自然科学基金重点项目(4031001-2)

摘　　要：在面向生产现场的远程视频监控系统中,视频图像的庞大数据量与系统的处理能力和网络带宽条件往往容易形成冲突,而繁杂冗余的现场视觉信息也难以符合生产监控的需求。该文提出了一种基于视网膜中央凹视觉的生产监控图像处理方法,从生产监控的特点和需求出发,模仿人眼的视觉感知特性对视频图像进行空间变分辨率转换,从而降低数据量并实现对监控效用信息(MEI)的筛选。实验结果表明,该方法能够帮助远程视频监控系统有效降低视频传输码率,在保证系统实时性的同时提高了生产监控的效率。The large amount of video data from remote video production monitoring systems usually exceeds system processing capabilities and network bandwidth limitations. The complex redundant visual information is also often not useful for production monitoring. This paper describes a foveated vision-based image processing method, which considers the requirements of production monitoring, and simulates the visual perception process of the human eye by a spatial resolution variable transform of the video image to reduce the video data and identify the monitor effective information. Experimental results show that this method effectively reduces the video rate from the remote video monitoring system to ensure real-time ability and improve production monitoring efficiency.

关 键 词：生产监控 远程视频监控系统 监控效用信息 视网膜中央凹视觉 空间变分辨率转换 

分 类 号：TH7[机械工程—仪器科学与技术]