Classify each pixel of the image

DynaSlum / SatelliteImaging

The software for WP1: SatelliteImaging

Apache License 2.0

3 stars 1 forks source link

Classify each pixel of the image #39

Closed elboyran closed 7 years ago

elboyran commented 7 years ago

[x] Decide on how to do it- via datastore or not. Check of the method predict can work on single image tile or on datastore.
[x] Create function and script for predicting the label of each pixel based on tile (100x100px = 80x80m) around it using a learned classifier.
[x] Segment the whole image using codes: 1- Slum, 2- NonBuiltUp and 3 BuiltUp

elboyran commented 7 years ago

The predict method of the ImageCategoryClassifier can be used to predict the labels of an image datastore: [labelIdx,score] = predict(categoryClassifier,imds) but geenrating tiles for ALL pixels makes more than 30 million images- too much storage!

elboyran commented 7 years ago

Classifying one pixel using s tile around it (100x100px = 80x80m.) takes about 350 ms. But segmenting the whole image of more than 30 million (6223 x 4872 = 30 318 456) pixels would take in current implementation 12 days. Therefore, I've processed every 5th pixel in both dimensions , that took about 11 hours. Interpolation to the missing pixels should be a separate issue.