GitHub - NeerajChinna123/Topographical-Feature-Extraction-Using-Machine-Learning-Techniques-from-Sentinel-2A-Imagery-: The advancement in the satellite technology has made it possible to easily and frequently obtain the satellite images of most of the regions in the Earth. The satellite data contains abundant amount of information which can be very useful for variety of societal applications. However, manual identification of the land cover in a particular area is a very challenging and time-consuming task. we propose a method for classifying the land types from Sentinel 2A imagery using various models like random forest, SVM, Naive Bayes, Decision Tree (CART) and validate which model better classifies them. QGIS software is used to generate training data for the classifier. The analysis reveals that random forest classifier outperforms the rest of the classification methods in terms of better accuracy. This automated approach can be applied to large sets of data, reducing the need for manual labeling.

NeerajChinna123 / Topographical-Feature-Extraction-Using-Machine-Learning-Techniques-from-Sentinel-2A-Imagery- Public

Notifications You must be signed in to change notification settings
Fork 2
Star 6

The advancement in the satellite technology has made it possible to easily and frequently obtain the satellite images of most of the regions in the Earth. The satellite data contains abundant amount of information which can be very useful for variety of societal applications. However, manual identification of the land cover in a particular area …

6 stars 2 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
Input fcc sample image, training data image and outputs		Input fcc sample image, training data image and outputs
dataset)		dataset)
project.ipynb		project.ipynb