Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aerial images. The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 9 vom: 31. Sept., Seite 5401-5413
|
1. Verfasser: |
Oner, Doruk
(VerfasserIn) |
Weitere Verfasser: |
Kozinski, Mateusz,
Citraro, Leonardo,
Dadap, Nathan C,
Konings, Alexandra G,
Fua, Pascal |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2022
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |