高分辨率卫星遥感影像失真探测方法研究  

On Distortion Detect Method of High-resolution Satellite Remote Sensing Images

作　　者：辛佩康 程效军[1,2] 贾东峰[1] 

机构地区：[1]同济大学测绘与地理信息学院,上海200092 [2]现代工程测量国家测绘地理信息局重点实验室,上海200092

出　　处：《昆明冶金高等专科学校学报》2017年第3期36-42,共7页Journal of Kunming Metallurgy College

摘　　要：高分辨率卫星遥感影像在成像、传输、处理等阶段会不可避免地形成模糊失真与噪声失真。目前对于这些失真的探测主要采用传统的客观探测指标,效果优劣不一,限制了影像失真探测在影像筛选与影像数据质量控制方面的应用。借助实验数据探究了不同的影像单一失真探测指标对常见的模糊失真与噪声失真的探测效果,根据初步结果选取最佳指标,再通过实验比较不同探测指标对不同影像失真的探测效果。同时,在已有研究基础上探究了一种基于灰度预测误差的失真探测方法,实验结果表明该方法对影像的模糊失真和噪声失真具有较高的探测灵敏度。The distortion formed in the course of imaging, transmission and processing of high - resolu-tion satellite remote sensing images mainly includes fuzzy one and noise one. The present traditional ob-jective indicators in use for the distortion detection have advantages and disadvantages, which has greatly limited its application in image filtering and data quality control. With the help of experimental data, this paper explores the effect of different image single distortion detection index for fuzzy and noise distortions, selects the best indicators according to preliminary results and compares the effects of different detection index to different image distortion through experiment. Meanwhile, on the basis of present researches, it further explores a new kind of distortion detection method based on gray prediction error, whose result shows that the method has higher detection sensitivity for the fuzzy and noise image distortions.

关 键 词：高分辨率卫星影像 影像失真 探测方法 灰度预测误差 

分 类 号：P237[天文地球—摄影测量与遥感]