This chapter was an insight to semantic segmentation on remote sensing images. We have introduced the semantic segmentation using a U-Net like architecture, a popular model targeting semantic segmentation of images.
We have built and used a small model to classify the buildings over one entire remote sensing image, without any limitation regarding its size, and in reasonable time.
We saw that, unlike the patch-based approach, semantic segmentation employs models that preserve the spatial resolution of the output. However, we have also understood that this kind of models must be trained from densely annotated images: the training step require patches of images that are fully annotated, i.e. each pixel of the image has a corresponding ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access