An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements
Multi-scale electronic map tiles are important basic geographic information data, and an approach based on deep learning is being used to generate multi-scale map tiles. Although generative adversarial networks (GANs) have demonstrated great potential in single-scale electronic map tile generation,...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/13/11/398 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846153381868994560 |
|---|---|
| author | Wei Zhu Qingsheng Guo Nai Yang Ying Tong Chuanbang Zheng |
| author_facet | Wei Zhu Qingsheng Guo Nai Yang Ying Tong Chuanbang Zheng |
| author_sort | Wei Zhu |
| collection | DOAJ |
| description | Multi-scale electronic map tiles are important basic geographic information data, and an approach based on deep learning is being used to generate multi-scale map tiles. Although generative adversarial networks (GANs) have demonstrated great potential in single-scale electronic map tile generation, further research concerning multi-scale electronic map tile generation is needed to meet cartographic requirements. We designed a multi-scale electronic map tile generative adversarial network (MsM-GAN), which consisted of several GANs and could generate map tiles at different map scales sequentially. Road network data and building footprint data from OSM (Open Street Map) were used as auxiliary information to provide the MsM-GAN with cartographic knowledge about spatial shapes and spatial relationships when generating electronic map tiles from remote sensing images. The map objects which should be deleted or retained at the next map scale according to cartographic standards are encoded as auxiliary information in the MsM-GAN when generating electronic map tiles at smaller map scales. In addition, in order to ensure the consistency of the features learned by several GANs, the density maps constructed from specific map objects are used as global conditions in the MsM-GAN. A multi-scale map tile dataset was collected from MapWorld, and experiments on this dataset were conducted using the MsM-GAN. The results showed that compared to other image-to-image translation models (Pix2Pix and CycleGAN), the MsM-GAN shows average increases of 10.47% in PSNR and 9.92% in SSIM and has the minimum MSE values at all four map scales. The MsM-GAN also performs better in visual evaluation. In addition, several comparative experiments were completed to verify the effect of the proposed improvements. |
| format | Article |
| id | doaj-art-9b06e1ca92f84c148bb853b3382bf127 |
| institution | Kabale University |
| issn | 2220-9964 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj-art-9b06e1ca92f84c148bb853b3382bf1272024-11-26T18:06:25ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-11-01131139810.3390/ijgi13110398An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic RequirementsWei Zhu0Qingsheng Guo1Nai Yang2Ying Tong3Chuanbang Zheng4School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, ChinaMulti-scale electronic map tiles are important basic geographic information data, and an approach based on deep learning is being used to generate multi-scale map tiles. Although generative adversarial networks (GANs) have demonstrated great potential in single-scale electronic map tile generation, further research concerning multi-scale electronic map tile generation is needed to meet cartographic requirements. We designed a multi-scale electronic map tile generative adversarial network (MsM-GAN), which consisted of several GANs and could generate map tiles at different map scales sequentially. Road network data and building footprint data from OSM (Open Street Map) were used as auxiliary information to provide the MsM-GAN with cartographic knowledge about spatial shapes and spatial relationships when generating electronic map tiles from remote sensing images. The map objects which should be deleted or retained at the next map scale according to cartographic standards are encoded as auxiliary information in the MsM-GAN when generating electronic map tiles at smaller map scales. In addition, in order to ensure the consistency of the features learned by several GANs, the density maps constructed from specific map objects are used as global conditions in the MsM-GAN. A multi-scale map tile dataset was collected from MapWorld, and experiments on this dataset were conducted using the MsM-GAN. The results showed that compared to other image-to-image translation models (Pix2Pix and CycleGAN), the MsM-GAN shows average increases of 10.47% in PSNR and 9.92% in SSIM and has the minimum MSE values at all four map scales. The MsM-GAN also performs better in visual evaluation. In addition, several comparative experiments were completed to verify the effect of the proposed improvements.https://www.mdpi.com/2220-9964/13/11/398generating adversarial networksserial generative adversarial networkcartographic generalizationmulti-scale electronic map tilesauxiliary information |
| spellingShingle | Wei Zhu Qingsheng Guo Nai Yang Ying Tong Chuanbang Zheng An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements ISPRS International Journal of Geo-Information generating adversarial networks serial generative adversarial network cartographic generalization multi-scale electronic map tiles auxiliary information |
| title | An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements |
| title_full | An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements |
| title_fullStr | An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements |
| title_full_unstemmed | An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements |
| title_short | An Improved Generative Adversarial Network for Generating Multi-Scale Electronic Map Tiles Considering Cartographic Requirements |
| title_sort | improved generative adversarial network for generating multi scale electronic map tiles considering cartographic requirements |
| topic | generating adversarial networks serial generative adversarial network cartographic generalization multi-scale electronic map tiles auxiliary information |
| url | https://www.mdpi.com/2220-9964/13/11/398 |
| work_keys_str_mv | AT weizhu animprovedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT qingshengguo animprovedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT naiyang animprovedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT yingtong animprovedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT chuanbangzheng animprovedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT weizhu improvedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT qingshengguo improvedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT naiyang improvedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT yingtong improvedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements AT chuanbangzheng improvedgenerativeadversarialnetworkforgeneratingmultiscaleelectronicmaptilesconsideringcartographicrequirements |