In object based classification method , first Image is segmented in no of objects and then this objects are used as training , validation and testing data. Do I need data sets of Images of Same scene ? or Can I performed supervised classification with OBIA using 1 image?
The role of thumbs in supervised ML: bigger the data, better the results.
Given that over-fitting is still away.
Alpesh:
You can do only one image if that covers your area of interest. The more training data you feed to your OBIA, the better the expectations for validation and testing. In that regards you may want to mosaic adjacent areas if training data is also available and the images are compatible (temporally, spectrally, spatially, etc).
Thanks Mr. Pavon and Mr. Alaa
If I use QGIS for training shapefile generation,
Q1. Which Images I should use in QGIS for drawing training polygons ? (A) My own segmented images (B) Google Earth images
Q2. Is it necessary to draw polygons of individual class manualy for shpefile creation in QGIS ? or Is there any other way for creation of shpefiles of individual class ?
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training