Cloud detection of remote sensing images is an important preprocessing step for remote sensing image applications. While machine learning (deep learning) methods improve the accuracy of cloud detection in remote sensing images, they put forward higher requirements for the quantity and quality of data sets. However, if you want to reconstruct the dataset by yourself, you generally need to select the training samples by manual visual interpretation, which will consume a lot of manpower and material resources. Previous research mainly focused on the optimization of cloud detection algorithms, and few studied the extraction of training samples. In order to construct a cloud detection dataset, this paper proposes an Erosion and Diversion-based semi-Supervised Learning (EDSL) model. Fmask algorithm is used to automatically obtain cloud masks from Landset-8 remote sensing images to construct a cloud detection dataset. The results show that the dataset constructed by EDSL model is better than Fmask algorithm. The precision of the dataset constructed by EDSL model reaches 0.93, which exceeds Fmask. At the same time, we use SVM algorithm to conduct experiments on this data set, and the results are equivalent to the data set constructed by human vision, which proves the scientific nature of this method.
Remote sensing images are widely used in earth observation. However, the existence of clouds seriously affects the interpretation of remote sensing images. In order to improve the accuracy of cloud detection, it’s usually necessary to complete the segmentation of the cloud boundary before cloud detection. Based on the Simple Linear Iterative Clustering (SLIC) algorithm, an improved SLIC superpixels segmentation method based on density feature is proposed to realize the segmentation of cloud remote sensing images. First, to generate the initial clustering center , the density peak clustering method is used instead of the uniform setting method. Then, in the calculation of distance measurement, we added the local density distance term. Finally, we get the superpixels segmented image by iteration. Four remote sensing images with different underlying surfaces were selected as the test data. The comparison experiments with other two algorithms show that the algorithm promoted in this paper shows superior performance in boundary recall (BR) rate and the error rate is lower than other algorithms in cloud detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.