AD-RoadNet: An Auxiliary-Decoding Road Extraction Network Improving Connectivity While Preserving Multiscale Road Details

Obtaining Road information from high-resolution remote sensing images is gaining attention in intelligent transportation systems. Existing road extraction methods tend to improve road connectivity with graph convolution or global attention, however, ignore the damage of introduced excessive effectiv...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Ziqing Luo, Kailei Zhou, Yumin Tan, Xiaolu Wang, Rui Zhu, Liqiang Zhang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2023-01-01
Schriftenreihe:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Schlagworte:	Hybrid receptive field (RF) multiscale road extraction road connectivity semantic segmentation topological feature
Online-Zugang:	https://ieeexplore.ieee.org/document/10163787/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!