Earthquake-Damaged Buildings Detection in Very High-Resolution Remote Sensing Images Based on Object Context and Boundary Enhanced Loss

Fully convolutional networks (FCN) such as UNet and DeepLabv3+ are highly competitive when being applied in the detection of earthquake-damaged buildings in very high-resolution (VHR) remote sensing images. However, existing methods show some drawbacks, including incomplete extraction of different s...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Chao Wang, Xing Qiu, Hai Huan, Shuai Wang, Yan Zhang, Xiaohui Chen, Wei He
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	MDPI AG 2021-08-01
Σειρά:	Remote Sensing
Θέματα:	VHR remote sensing images earthquake-damaged buildings convolutional neural network object context boundary
Διαθέσιμο Online:	https://www.mdpi.com/2072-4292/13/16/3119
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!