Figure 14
An illustration showing two rows of images labeled a through f, where image a is an aerial photograph labeled Origin R G B one and images b through f are segmentation maps labeled No D F E B, No F M B, No P M S S, Proposed method, and Ground Truth, all displaying four bounding boxes and a legend.

Visual Segmentation Results on the Vaihingen dataset. (a) optical images; (b) No DFEB; (c) No FMB; (d) No PMSS; (e) AMBNet; (f) Ground Truth.

This Feature Is Available To Subscribers Only

or Create an Account

Close subscription notice
Close access options