A NOVEL DATA AUGMENTATION METHOD TO ENHANCE THE TRAINING DATASET FOR ROAD EXTRACTION FROM SWISS HISTORICAL MAPS
Long-term retrospective road data are required for various analyses (e.g., investigation of urban sprawl, analysis of road network evolution). Yet, it is challenging to extract roads from scanned historical maps due to their dissatisfying quality. Although deep learning has been exerting its superio...
Main Authors: | C. Jiao, M. Heitzler, L. Hurni |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2022-05-01
|
Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2022/423/2022/isprs-annals-V-2-2022-423-2022.pdf |
Similar Items
-
A fast and effective deep learning approach for road extraction from historical maps by automatically generating training data with symbol reconstruction
by: Chenjing Jiao, et al.
Published: (2022-09-01) -
Leveraging uncertainty estimation and spatial pyramid pooling for extracting hydrological features from scanned historical topographic maps
by: Sidi Wu, et al.
Published: (2022-12-01) -
A CLOSER LOOK AT SEGMENTATION UNCERTAINTY OF SCANNED HISTORICAL MAPS
by: S. Wu, et al.
Published: (2022-06-01) -
CNN-BASED TEMPLATE MATCHING FOR DETECTING FEATURES FROM HISTORICAL MAPS
by: X. Xia, et al.
Published: (2022-05-01) -
Creating a dataset of historic roads in Sydney from scanned maps
by: Hamish Turner, et al.
Published: (2023-10-01)