Segmentation Is Not the End of Road Extraction: An All-Visible Denoising Auto-Encoder for Connected and Smooth Road Reconstruction

With a plethora of remote sensing (RS) images, deep neural network-based semantic segmentation models (SegModels) achieve commendable road extraction performance. However, the occlusions caused by vehicles, roadside objects and shadows cannot be directly identified as road pixels, especially on high...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2023-05, p.1-1
Hauptverfasser:	Han, Lingyi, Hou, Lu, Zheng, Xiangxiang, Ding, Ziyue, Yang, Haojun, Zheng, Kan
Format:	Artikel
Sprache:	eng
Schlagworte:	connectivity Data mining deep learning denoising auto-encoder Feature extraction Image reconstruction Road extraction Roads Semantic segmentation smoothness Task analysis Topology
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!