Coexisting Cloud and Snow Detection Based on a Hybrid Features Network Applied to Remote Sensing Images
- 28 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-15
Abstract
Owing to the characteristics of cloud and snow, it is difficult to detect them when they coexist. Thus, we propose an end-to-end semantic segmentation network for cloud and snow detection based on hybrid feature (CSD-HFnet) to be applied to remote sensing images (RSIs) in which cloud and snow coexist. First, the local binary pattern (LBP), gray-level co-occurrence matrix (GLCM), and superpixel segmentation are combined as basic features to preserve the textural, spatial and shape information of the cloud and snow objects. We also propose deep learning feature extraction network to obtain the multi-scale deep learning features, which is utilized to better distinguish cloud from snow. The original spectral bands, the basic features, and the multi-scale deep learning features are input into the feature integration module simultaneously to form the primary multi-scale hybrid features (PMHF). Then, the PMHF are filtered, sorted and weighted by the feature filtering & sorting block and attention mechanism block to obtain the advanced multi-scale hybrid features (AMHF). Finally, the AMHF are input into the cloud and snow segmentation network, which consists of several memory-capable gate circuits for training and validation of cloud and snow detection. The results indicate that CSD-HFnet with AMHF can provide reliable detection under the condition of cloud and snow coexistence. CSD-HFnet can detect cloud and snow in multi-spectral RSIs of various spatial resolutions with an OA of 95.37%. Moreover, CSD-HFnet exhibits excellent cloud detection ability for red-green-blue (RGB) images with an OA of 95.88%, higher than other state-of-the-art cloud detection methods.Keywords
Funding Information
- Technological Research and Development Projects of Jilin (20220201017GX)
- National Natural Science Foundation of China (41871225)
This publication has 55 references indexed in Scilit:
- CLOUD DETECTION METHOD BASED ON FEATURE EXTRACTION IN REMOTE SENSING IMAGESThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013
- A novel protein structural classes prediction method based on predicted secondary structureBiochimie, 2012
- Object-based cloud and cloud shadow detection in Landsat imageryRemote Sensing of Environment, 2012
- SEEDS: Superpixels Extracted via Energy-Driven Sampling2012
- Fractional snow cover mapping through artificial neural network analysis of MODIS surface reflectanceRemote Sensing of Environment, 2011
- An optimal image transform for threshold-based cloud detection using heteroscedastic discriminant analysisInternational Journal of Remote Sensing, 2011
- Development and evaluation of a cloud-gap-filled MODIS daily snow-cover productRemote Sensing of Environment, 2010
- A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation2005
- GENETIC ALGORITHM OPTIMIZATION OF ADAPTIVE MULTI-SCALE GLCM FEATURESInternational Journal of Pattern Recognition and Artificial Intelligence, 2003
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002