Road segmentation in aerial images

Road Segmentation in Aerial Images by Exploiting Road Vector Data for USA

Road segmentation in aerial Images by exploiting road vector data

The proposed method achieves on average 90% recall and 79% precision on large aerial images covering various types of roads.

Which means of course that 21% of the time a human agent needs to fix up the data. That’s a big improvement over previous methods, but it still leaves a lot of work for Telegenisys to do.

You may also like


Submit a Comment

Your email address will not be published. Required fields are marked *

Pin It on Pinterest