Important Notice: Our web hosting provider recently started charging us for additional visits, which was unexpected. In response, we're seeking donations. Depending on the situation, we may explore different monetization options for our Community and Expert Contributors. It's crucial to provide more returns for their expertise and offer more Expert Validated Answers or AI Validated Answers. Learn more about our hosting issue here.

I have decided to use cross-classification for change detection by using two Riverstone NDVI images from 1991 and 2000. Is this reasonable?

April 26, 2017decided detection from 1991 images NDVI reasonable riverstone

0

Posted

I have decided to use cross-classification for change detection by using two Riverstone NDVI images from 1991 and 2000. Is this reasonable?

1 Answer

0

Posted

It is reasonable to to use cross-classification for the project but I do not recommend that you classify just the NDVI images. The reason is that water, industrial buiildings with large roof areas and fallow land (i.e. fields without crops) all have very low NDVI values. It is impossible to spearate them into different classes with an NDVI image. I recommned that you use a multiband image for classification; the original georeferenced image is the easiest to use.