Abstract
Cloud/snow recognition is one application of satellite remote sensing imagery in natural disaster monitoring. Deep learning technology has contributed to the improvement of the performance of cloud/snow recognition. However, deep learning-based methods cannot well balance the performance and efficiency of cloud/snow recognition. In this paper, an augmented multi-dimensional and multi-grained Cascade Forest is proposed for cloud/snow recognition. The multi-dimensional deep forest structure with the representation learning ability allows it to capture the spatial and spectral information of cloud/snow satellite imagery accordingly equipped with good recognition efficiency. Besides, a simple augmentation Random Erasing method is introduced for enhancing the robustness of cloud/snow recognition. The experimental results on the HJ-1A/1B dataset show that the proposed method improves the performance of cloud/snow recognition by extracting spectral information from multi-spectral satellite imagery. In addition, based on the tree-based structure, the proposed method well balances the performance and efficiency of cloud/snow recognition, which can be considered as an alternative to the Neural Network for cloud/snow recognition.
Highlights
T HE plateau areas are covered with snow all year round, and snow disasters happen irregularly
The application of the pretraining model greatly improved the accuracy and speed of cloud/snow recognition in remote sensing imagery
The results show that the training speed of RES-gcForest is faster than Convolutional Neural Network (CNN), gcForest, and Cascade Forest
Summary
T HE plateau areas are covered with snow all year round, and snow disasters happen irregularly. Le Goff’s [13] and Zhu [14] researches utilized the texture and spatial features of satellite remote sensing imagery to analyze clouds and snow, made full use of the advantages of Neural Networks in feature extraction, and combined the texture features of clouds and snow with spectral features, which had seen an increase both in recognition accuracy and recognition speed. The existing cloud/snow recognition algorithms based on deep learning [16] can make good use of the spectral and texture features of remote sensing images [17], [22], almost all models need to have a pre-set structure. Based on the problems of traditional algorithms, deep learning algorithms, and existing ensemble algorithms in cloud/snow recognition, this paper develops a multi-grained sampling Cascade Forest (RES-gcForest) algorithm based on the Random Erasing image enhancement method, which can achieve high accuracy and fast cloud/snow recognition.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
