一种高分辨率卫星影像自动云检测方法

An automatic cloud detection method for high resolution satellite images

针对多数已有的卫星影像云检测方法利用云独特的光谱特征、构造指数图像进行云识别的方法,对传感器、环境参数、云层类型等比较敏感的问题,提出了一种改进HIS模型的高分辨率卫星影像自动云检测方法,以有效弥补传统纹理分析方法计算精度低、效率低下的问题。采用两景国产高分二号遥感影像进行试验。结果表明,该方法错误率低于5%、查全率高于92%、查准率高于95%。

Cloud detection from satellite imagery is one of the classic research topics in the field of image processing.Most of the existing cloud detection methods make use of the unique spectral characteristics of the cloud to construct an index for cloud recognition from the images,but they are sensitive to sensors,environmental parameters,and types of clouds etc.An automatic cloud detection method is proposed based on improved HIS model in this paper.It effectively makes up for the shortcomings of low calculation accuracy and low efficiency of traditional texture analysis methods.Two domestic GF-2 images are tested on the proposed method.Experimental results show that the error rate of this method is less than 5%,the recall rate is higher than 92%,and the precision rate is higher than 95%,Basically realize automatic detection.