A SegNet-Based Approach for Road Label Placement Integrating Geometric and Textual Information
Yu, Huafei ; Ai, Tingua ; Yang, Min ; Oucheikh, Rachid LU ; Kong, Bo ; Wu, Hao ; Zhang, Zhenyu and Harrie, Lars LU
(2025)
In Transactions in GIS
29(4).
- Abstract
- As a crucial tool for enhancing the readability and comprehensibility of geoinformation, automated label placement in mapping applications remains a significant challenge, particularly when generalizing the label placement process for high-density maps, despite the availability of tools such as QGIS-PAL and ArcGIS-Maplex label engine. This study focuses on utilizing deep learning (DL) for road labeling tasks and addresses two key questions: Can DL models predict the quantity and shape of road labels? Can they determine the label positions? Our proposed SegNet-based model employed “where” and “what” modules, integrating geometric contextual information with textual data as inputs. We validated the model using London, UK wayfinding map data,... (More)
- As a crucial tool for enhancing the readability and comprehensibility of geoinformation, automated label placement in mapping applications remains a significant challenge, particularly when generalizing the label placement process for high-density maps, despite the availability of tools such as QGIS-PAL and ArcGIS-Maplex label engine. This study focuses on utilizing deep learning (DL) for road labeling tasks and addresses two key questions: Can DL models predict the quantity and shape of road labels? Can they determine the label positions? Our proposed SegNet-based model employed “where” and “what” modules, integrating geometric contextual information with textual data as inputs. We validated the model using London, UK wayfinding map data, demonstrating improved readability and achieving comparable machine learning evaluation metrics to mainstream labeling tools. Notably, our method accurately predicted label placements for roads and ensured consistent label sizes. This study provides valuable insights and recommendations for leveraging DL techniques to alleviate labor-intensive challenges of map labeling. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/bca2a6b0-3bef-4cc7-bca8-2e9bd0cdf375
- author
- Yu, Huafei
; Ai, Tingua
; Yang, Min
; Oucheikh, Rachid
LU
; Kong, Bo
; Wu, Hao
; Zhang, Zhenyu
and Harrie, Lars
LU
- organization
- publishing date
- 2025-06-18
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Transactions in GIS
- volume
- 29
- issue
- 4
- article number
- e70080
- publisher
- Wiley-Blackwell
- external identifiers
-
- scopus:105008867690
- ISSN
- 1467-9671
- DOI
- 10.1111/tgis.70080
- language
- English
- LU publication?
- yes
- id
- bca2a6b0-3bef-4cc7-bca8-2e9bd0cdf375
- date added to LUP
- 2025-12-02 09:53:59
- date last changed
- 2025-12-03 04:01:46
@article{bca2a6b0-3bef-4cc7-bca8-2e9bd0cdf375,
abstract = {{As a crucial tool for enhancing the readability and comprehensibility of geoinformation, automated label placement in mapping applications remains a significant challenge, particularly when generalizing the label placement process for high-density maps, despite the availability of tools such as QGIS-PAL and ArcGIS-Maplex label engine. This study focuses on utilizing deep learning (DL) for road labeling tasks and addresses two key questions: Can DL models predict the quantity and shape of road labels? Can they determine the label positions? Our proposed SegNet-based model employed “where” and “what” modules, integrating geometric contextual information with textual data as inputs. We validated the model using London, UK wayfinding map data, demonstrating improved readability and achieving comparable machine learning evaluation metrics to mainstream labeling tools. Notably, our method accurately predicted label placements for roads and ensured consistent label sizes. This study provides valuable insights and recommendations for leveraging DL techniques to alleviate labor-intensive challenges of map labeling.}},
author = {{Yu, Huafei and Ai, Tingua and Yang, Min and Oucheikh, Rachid and Kong, Bo and Wu, Hao and Zhang, Zhenyu and Harrie, Lars}},
issn = {{1467-9671}},
language = {{eng}},
month = {{06}},
number = {{4}},
publisher = {{Wiley-Blackwell}},
series = {{Transactions in GIS}},
title = {{A SegNet-Based Approach for Road Label Placement Integrating Geometric and Textual Information}},
url = {{http://dx.doi.org/10.1111/tgis.70080}},
doi = {{10.1111/tgis.70080}},
volume = {{29}},
year = {{2025}},
}