Semantic segmentation with overlapping patches

5 views (last 30 days)
I am using Deeplabv3+ to perform semantic segmentation in an image but the result shows strong discontinuities due to patch-wise predictions. Is there a way of using overlapping patches that are aggregated (or averaged) to produce the output? I tried to use a code showed in this example. However the output has still the patchy pattern. Any sollutions?
Mahesh Taparia
Mahesh Taparia on 12 Oct 2021
Can you specify the input which you are passing? I think the network give the pixel wise output, how it became discontinuous?
Matheus Ferreira
Matheus Ferreira on 13 Oct 2021
Because I am working with remote sensing images I should pass image tiles that are merged together after prediction. I could solve the problem using 'blockproc' and defining the 'BorderSize' parameter according to the amount of overlap desired.

Sign in to comment.

Accepted Answer

Mahesh Taparia
Mahesh Taparia on 13 Oct 2021
In this case, you can use 'blockproc' function. Create the image block and pass it to network. For more information, you can refer this documentation.

More Answers (0)




Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!