Scripts and commands for augmenting machine learning data sets for the remote sensing domain.
Other utility script exist, such as creating 5-fold or 10-fold cross validation data sets.
Scripts originally developed for the UC Merced data.
Get UC Merced Land Use Dataset
Don't forget to acknowledge data set creators:
Yi Yang and Shawn Newsam, "Bag-Of-Visual-Words and Spatial Extensions for Land-Use Classification," ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM GIS), 2010.
This data set can be obtained from the authors of the following paper.
Acknowledge the data set creators:
Dai, D., Yang, W.: Satellite image classification via two-layer sparse coding with biased image representation. IEEE Geosci. Remote Sens. Lett. 8(1), 173176 (2011)
-
These scripts require caffe to use. The guide for installing caffe can be found here
-
See the readme files in the appropriate directories for directions on how to use those scripts.
-
General workflow for using these scripts:
- Augmentation Scripts
- Fivefold Scripts
- Classification Scripts