Semantic segmentation with overlapping patches

18 Ansichten (letzte 30 Tage)
Matheus Ferreira
Matheus Ferreira am 8 Okt. 2021
Beantwortet: Mahesh Taparia am 13 Okt. 2021
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?
  2 Kommentare
Mahesh Taparia
Mahesh Taparia am 12 Okt. 2021
Hi
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 am 13 Okt. 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.

Melden Sie sich an, um zu kommentieren.

Akzeptierte Antwort

Mahesh Taparia
Mahesh Taparia am 13 Okt. 2021
Hi
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.

Weitere Antworten (0)

Produkte


Version

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by