Remote sensing image cloud detection method based on adaptive shape dark channel

基于自适应形状暗通道的遥感图像云检测方法

Abstract

The invention discloses a remote sensing image cloud detection method based on an adaptive shape dark channel, which is used for solving the current problems in the prior art that the calculation amount is big, the complexity is high and the detection result is not accurate. The remote sensing image cloud detection method comprises steps of segmenting an RGB remote sensing cloud image to be detected into a plurality of irregular superpixel blocks, performing marking on the segmentation result, performing adaptive shape dark channel processing on the remote sensing image to be detected by combining with the mark to obtain a grey-scale map, performing binary processing and morphological processing on the grey-scale map, performing guiding filtering processing on the binary image after morphological processing to obtain a filtered grey-scale map, performing secondary binary processing and secondary morphological processing on the filtered grey scale image to obtain a final cloud detection result. The remote sensing image cloud detection method is simple in process, and substantial in detection effect, can be used for the pre-processing process of the remote sensing image, and can realize the rejection, classification and follow-up target identification on the remote sensing image.
本发明提出了一种基于自适应形状暗通道的遥感图像云检测方法,用于解决现有遥感图像云检测方法中存在的运算量大、复杂度高和检测结果不准确的技术问题。包括如下步骤:将待检测的RGB遥感云图分割为多个不规则的超像素块,对分割结果进行标记;结合标记对待检测的RGB遥感云图进行自适应形状暗通道处理,得到灰度图;对灰度图进行二值化处理和形态学处理;对形态学处理后的二值图进行导向滤波处理,得到滤波后的灰度图;对滤波后的灰度图进行二次二值化处理和二次形态学处理,得到最终云检测结果。本发明具有过程简单、云检测效果显著的特点,用于遥感图像的预处理过程,可以实现对遥感图像的剔除、分类和后续的目标识别。

Claims

Description

Topics

Download Full PDF Version (Non-Commercial Use)

Patent Citations (0)

    Publication numberPublication dateAssigneeTitle

NO-Patent Citations (0)

    Title

Cited By (0)

    Publication numberPublication dateAssigneeTitle