hi i want to compare the two images using CNN and identify the building changes.The result comes like a its new building,old building etc..i really confused about that.Is there anybodies know that?
Hi chitra M,
Did you have a look at this webinar already? Integrating Deep Learning with ArcGIS using Python
In this webinar several scenarios of applying the latest machine learning and deep learning techniques to geospatial data are covered, including semantic segmentation (such as land-cover classification and identifying roads and building footprints) using satellite imagery and models such as U-Net and Mask R-CNN.
So this might be a starting point to design your workflow to compare two images using CNN (Convolutional Neural Networks).
Thanks Egge -Jan..
I watched that video that video only shows the detect the building foot
prints using mask R-CNN and gives one polygon features and but i already
have polygon(building) shape file and images, i want to identifying
building changes by analyzing difference between old and new imagery..do u
have knowledge about it?if u have means pleas share your ideas.thanks in