Hrlinknet: Linknet with High-Resolution Representation for High-Resolution Satellite Imagery

Automatic extraction of buildings from high-resolution remote sensing imagery is very useful in many applications such as city management, mapping, urban planning and geographic information updating. However, due to the general texture of the building and the complexity of the image background, high...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Geoscience and Remote Sensing Symposium proceedings s. 2504 - 2507
Hlavní autoři: Wu, Muyu, Shu, Zhen, Zhang, Jinming, Hu, Xiangyun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 11.07.2021
Témata:
building extraction
Buildings
Deep learning
encoder-decoder
fully convolutional networks
high-resolution remote sensing imagery
Image edge detection
Image segmentation
Satellites
semantic segmentation
Semantics
Sensors
Urban planning
ISSN:2153-7003
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Automatic extraction of buildings from high-resolution remote sensing imagery is very useful in many applications such as city management, mapping, urban planning and geographic information updating. However, due to the general texture of the building and the complexity of the image background, high-precision building segmentation from high-resolution sensing image is still a challenging task. Existing state-of-the-art frameworks use repeated pooling and step operations leading to the loss of detailed information. Thus, high-resolution representations are essential for building extraction. On this basis, our proposed network, named as HRLinkNet, maintains high-resolution representations through the whole process based on the LinkNet. We tested it on WHU Building dataset. Experimental results show that the proposed HRLinkNet is superior to the LinkNet, UNet, DLinkNet, segnet and so on.
ISSN:2153-7003
DOI:10.1109/IGARSS47720.2021.9554601