Cloud Masking Technique for High-Resolution Satellite Data: An Artificial Neural Network Classifier Using Spectral & Textural Context
- 90 Downloads
Cloud masking is a very important application in remote sensing and an essential pre-processing step for any information derivation applications. It helps in estimation of usable portion of the images. Many popular spectral classification techniques rely upon the presence of a short-wave infrared band or bands of even higher wavelength to differentiate between clouds and other land covers. However, these methods are limited to sensors equipped with higher wavelength bands. In this paper, a generic and efficient technique is attempted using the Cartosat-2 series (C2S) satellite which is having high-resolution multispectral sensor in the visible and near-infrared bands. The methodology is based on textural features from the available spectral context, and using a feedforward neural network for the classification is proposed. The method was shown to have an overall accuracy of 97.98% for a large manually pre-classified validation dataset with more than 2 million data points. Experimental results and cloud masks generated for various scenes show that the method may be viable as a reasonable cloud masking algorithm for C2S data.
KeywordsCloud masking High-resolution satellite data Artificial neural network Feed forward network GLCM texture Image classification
An open-source library written in C, FANN, was used for the neural network calculations. The images of scenes shown in the paper were taken as screenshots of another open-source display utility, OpenEV. We would like to express our sincere thanks to Director, NRSC, ISRO for giving this opportunity and the Software Group team for their continuous support.
- Ahmad, A., & Quegan, S. (2012). Cloud masking for remotely sensed data using spectral and principal components analysis. ETASR—Engineering, Technology & Applied Science Research, 2, 221–225.Google Scholar
- Candra, D. S., Phinn, S., Scarth, P. (2016). Cloud and cloud shadow masking using multi-temporal cloud masking algorithm in tropical environmental. ISPRS International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B2, 95–100. https://doi.org/10.5194/isprs-archives-XLI-B2-95-2016.CrossRefGoogle Scholar
- Igel, C., Hüsken, M., 2000. Improving the Rprop learning algorithm. In Proceedings of the second international symposium on Neura, 115–121.Google Scholar
- Irish, R. R. (2000). Landsat 7 automatic cloud cover assessment in algorithms for multispectral hyperspectral and ultraspectral imagery. In Proceedings of the SPIE 4049.Google Scholar
- Khazenie, N., & Richardson, K. (1991). Classification of cloud types based on spatial textural measures using NOAA-AVHRR data. International Geoscience and Remote Sensing Symposium on Remote Sensing: Global Monitoring for Earth Management, 3, 1701–1705.Google Scholar
- Khazenie, N., Richardson, K., 1992. Comparison of texture analysis techniques in both frequency and spatial domains for cloud feature extraction. ISPRS Archives XXIX, 1009–1014.Google Scholar
- Li, A., Jiang, J., Bian, J., & Deng, W. (2012). Combining the matter element model with the associated function of probability transformation for multi-source remote sensing data classification in mountainous regions. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 80–92.CrossRefGoogle Scholar
- Martens, J., Sutskever, I., 2011. Learning recurrent neural networks with hessian-free optimization. In ICML’11 proceedings of the 28th international conference on international conference on machine learning 1033–1040.Google Scholar
- Riedmiller, M., Braun, H., 1993. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In IEEE international conference on neural networks, 586–591.Google Scholar