Satellite Images provides a detailed aspect of the earth surface, through many wavelengths (spectral) and spatial data. High-resolution (HR) image contains more pixels than a low-resolution image for the same area, which mean there is a difference between low and high-resolution features. The traditional image classification techniques consist of two categories: unsupervised and supervised classification. The most known unsupervised method is k-means classifier.
Papers:
1) Y. T. Hsieh, C. T. Chen, and J. C. Chen, 2017 “Applying object based image analysis and knowledge-based classification to ADS-40 digital aerial photographs to facilitate complex forest land cover classification,” Journal of Applied Remote Sensing, vol. 11, no. 1, article 015001.
2) Rathore, M.M.U.; Paul, A.; Ahmad, A.; Chen, B.-W.; Huang, B.; Ji, W., 2016 “Real-Time Big Data Analytical Architecture for Remote Sensing Application”. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. Vol. 8, 4610 - 4621.
Dear Professor,
I have read this paper before which may help you (if you have not taken a look at it yet).
"Hamida, A. Ben, Alexandre Benoit, Patrick Lambert, Louis Klein, C. Ben Amar, Nicolas Audebert, and Sébastien Lefèvre. "Deep learning for semantic segmentation of remote sensing images with rich spectral content." In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 2569-2572. IEEE, 2017."
It presents recent Deep Learning approaches for fine or coarse land cover semantic segmentation estimation. it's a bit different than what you want but it may help you.
Best Regards.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Analysis
- Data Analysis
- Dataset
- Big Data