ROAD EXTRACTION BASED ON IMPROVED DEEPLABV3 PLUS IN REMOTE SENSING IMAGE

Abstract. Urban roads in remote sensing images will be disturbed by surrounding ground features such as building shadows and tree shadows, and the extraction results are prone to problems such as incomplete road structure, poor topological connectivity, and poor accuracy. For mountain roads, there will also be problems such as hill shadow or vegetation occlusion. We propose an improved Deeplabv3+ semantic segmentation network method. This method uses ResNeSt, which introduces channel attention, as the backbone network, and combines the ASPP module to obtain multi-scale information, thereby improving the accuracy of road extraction. Analysis of the experimental results on the Deeplglobe dataset shows that the intersection ratio and accuracy of the method in this paper are 63.15% and 73.16%, respectively, which are better than other methods.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
ROAD EXTRACTION BASED ON IMPROVED DEEPLABV3 PLUS IN REMOTE SENSING IMAGE ; volume:XLVIII-3/W2-2022 ; year:2022 ; pages:67-72 ; extent:6
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLVIII-3/W2-2022 (2022), 67-72 (gesamt 6)

Urheber
Wang, H.
Yu, F.
Xie, J.
Zheng, H.

DOI
10.5194/isprs-archives-XLVIII-3-W2-2022-67-2022
URN
urn:nbn:de:101:1-2022110304342216397331
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
15.08.2025, 07:29 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Beteiligte

  • Wang, H.
  • Yu, F.
  • Xie, J.
  • Zheng, H.

Ähnliche Objekte (12)