Built-Up Area Mapping for the Greater Bay Area in China from Spaceborne SAR Data Based on the PSDNet and Spatial Statistical Features
Abstract
:1. Introduction
2. Study Area and Dataset
2.1. Study Area
2.2. Spaceborne SAR Datasets
3. Methodology
3.1. Spaceborne SAR Data Pre-Processing
3.2. Calculation of the SAR Image Features
3.3. PSDNet Deep Leaning Model
3.3.1. Network Architecture and Inputs
3.3.2. Backbone Network of the Encoder
3.3.3. Multi-Scale Decoder
3.3.4. Focal Loss
3.4. Post-Processing of the Final BA Mapping
4. Experimental Results Analysis and Comparisons
4.1. Accuracy Evaluation and Comparison
4.2. Information of the BAs Training Samples in SAR Images
4.3. Experimental Results of Our Proposed Method within Different Regions
4.4. Comparisons with the WSF Product
5. Discussions
5.1. Comparison with Other Deep Learing Models
5.2. Ablation Study for the Proposed Method
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Conflicts of Interest
References
- Ban, Y.; Jacob, A.; Gamba, P. Spaceborne SAR data for global urban mapping at 30m resolution using a robust urban extractor. ISPRS J. Photogramm. Remote Sens. 2015, 103, 28–37. [Google Scholar] [CrossRef]
- Yang, C.; Li, Q.; Zhao, T.; Liu, H.; Gao, W.; Shi, T.; Guan, M.; Wu, G. Detecting Spatiotemporal Features and Rationalities of Urban Expansions within the Guangdong–Hong Kong–Macau Greater Bay Area of China from 1987 to 2017 Using Time-Series Landsat Images and Socioeconomic Data. Remote Sens. 2019, 11, 2215. [Google Scholar] [CrossRef] [Green Version]
- Ma, P.; Wang, W.; Zhang, B.; Wang, J.; Shi, G.; Huang, G.; Chen, F.; Jiang, L.; Lin, H. Remotely sensing large- and small-scale ground subsidence: A case study of the Guangdong–Hong Kong–Macao Greater Bay Area of China. Remote Sens. Environ. 2019, 232, 111282. [Google Scholar] [CrossRef]
- Xiang, D.; Tang, T.; Hu, C.; Fan, Q.; Su, Y. Built-up Area Extraction from PolSAR Imagery with Model-Based Decomposition and Polarimetric Coherence. Remote Sens. 2016, 8, 685. [Google Scholar] [CrossRef] [Green Version]
- Zhang, W.; Xiang, D.; Su, Y. Fast Multiscale Superpixel Segmentation for SAR Imagery. IEEE Geosci. Remote Sens. Lett. 2020, 19, 4001805. [Google Scholar] [CrossRef]
- Xiang, D.; Tang, T.; Ban, Y.; Su, Y.; Kuang, G. Unsupervised polarimetric SAR urban area classification based on model-based decomposition with cross scattering. ISPRS J. Photogramm. Remote Sens. 2016, 116, 86–100. [Google Scholar] [CrossRef]
- Cheng, J.; Zhang, F.; Xiang, D.; Yin, Q.; Zhou, Y. PolSAR Image Classification With Multiscale Superpixel-Based Graph Convolutional Network. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5209314. [Google Scholar] [CrossRef]
- Wang, R.; Chen, J.-W.; Wang, Y.; Jiao, L.; Wang, M. SAR Image Change Detection via Spatial Metric Learning With an Improved Mahalanobis Distance. IEEE Geosci. Remote Sens. Lett. 2019, 17, 77–81. [Google Scholar] [CrossRef] [Green Version]
- Liu, C.; Huang, X.; Zhu, Z.; Chen, H.; Tang, X.; Gong, J. Automatic extraction of built-up area from ZY3 multi-view satellite imagery: Analysis of 45 global cities. Remote Sens. Environ. 2019, 226, 51–73. [Google Scholar] [CrossRef]
- Chen, J.; Chen, J.; Liao, A.; Cao, X.; Chen, L.; Chen, X.; He, C.; Han, G.; Peng, S.; Lu, M.; et al. Global land cover mapping at 30 m resolution: A POK-based operational approach. ISPRS J. Photogramm. Remote Sens. 2015, 103, 7–27. [Google Scholar] [CrossRef] [Green Version]
- Zhang, X.; Liu, L.Y.; Wu, C.S.; Chen, X.D.; Gao, Y.; Xie, S.; Zhang, B. Development of a global 30 m impervious surface map using multisource and multitemporal remote sensing datasets with the Google Earth Engine platform. Earth Syst. Sci. Data 2020, 12, 1625–1648. [Google Scholar] [CrossRef]
- Pesaresi, M.; Ehrilch, D.; Florczyk, A.J.; Freire, S.; Julea, A.; Kemper, T.; Soille, P.; Syrris, V. Operating procedure for the production of the Global Human Settlement Layer from Landsat data of the epochs 1975, 1990, 2000, and 2014. Publ. Off. Eur. Union 2016, 1–62. [Google Scholar]
- Dell’Acqua, F.; Gamba, P. Texture-based characterization of urban environments on satellite SAR images. IEEE Trans. Geosci. Remote Sens. 2003, 41, 153–159. [Google Scholar] [CrossRef]
- Esch, T.; Marconcini, M.; Felbier, A.; Roth, A.; Heldens, W.; Huber, M.; Schwinger, M.; Taubenböck, H.; Müller, A.; Dech, S. Urban footprint processor—Fully automated processing chain generating settlement masks from global data of the TanDEM-X mission. IEEE Geosci. Remote Sens. Lett. 2013, 10, 1617–1621. [Google Scholar] [CrossRef] [Green Version]
- Marconcini, M.; Marconcini, A.M.; Esch, T.; Gorelick, N. Understanding Current Trends in Global Urbanisation—The World Settlement Footprint Suite. GI_Forum 2021, 1, 33–38. [Google Scholar] [CrossRef]
- Dekker, R. Texture analysis and classification of ERS SAR images for map updating of urban areas in the netherlands. IEEE Trans. Geosci. Remote Sens. 2003, 41, 1950–1958. [Google Scholar] [CrossRef]
- Stasolla, M.; Gamba, P. Spatial Indexes for the Extraction of Formal and Informal Human Settlements From High-Resolution SAR Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2008, 1, 98–106. [Google Scholar] [CrossRef]
- Esch, T.; Thiel, M.; Schenk, A.; Roth, A.; Muller, A.; Dech, S. Delineation of urban footprints from TerraSAR-X data by analyzing speckle characteristics and intensity information. IEEE Trans. Geosci. Remote Sens. 2009, 48, 905–916. [Google Scholar] [CrossRef]
- Gamba, P.; Aldrighi, M.; Stasolla, M. Robust extraction of urban area extents in HR and VHR SAR images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2010, 4, 27–34. [Google Scholar] [CrossRef]
- Esch, T.; Taubenböck, H.; Roth, A.; Heldens, W.; Felbier, A.; Schmidt, M.; Mueller, A.A.; Thiel, M.; Dech, S.W. TanDEM-X mission-new perspectives for the inventory and monitoring of global settlement patterns. J. Appl. Remote Sens. 2012, 6, 061702. [Google Scholar] [CrossRef]
- Gamba, P.; Lisini, G. Fast and efficient urban extent extraction using ASAR wide swath mode data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2013, 6, 2184–2195. [Google Scholar] [CrossRef]
- Cao, H.; Zhang, H.; Wang, C.; Zhang, B. Operational Built-Up Areas Extraction for Cities in China Using Sentinel-1 SAR Data. Remote Sens. 2018, 10, 874. [Google Scholar] [CrossRef] [Green Version]
- Tang, J.; Cheng, J.; Xiang, D.; Hu, C. Large-Difference-Scale Target Detection Using a Revised Bhattacharyya Distance in SAR Images. IEEE Geosci. Remote Sens. Lett. 2022, 19, 4506205. [Google Scholar] [CrossRef]
- Zhang, F.; Tianying, M.; Xiang, D.; Ma, F.; Sun, X.; Zhou, Y. Adversarial deception against SAR target recognition network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 4507–4520. [Google Scholar] [CrossRef]
- Jing, W.; Jin, T.; Xiang, D. Edge-Aware Superpixel Generation for SAR Imagery With One Iteration Merging. IEEE Geosci. Remote Sens. Lett. 2020, 18, 1600–1604. [Google Scholar] [CrossRef]
- Liu, J.; Wang, Q.; Cheng, J.; Xiang, D.; Jing, W. Multitask Learning-Based for SAR Image Superpixel Generation. Remote Sens. 2022, 14, 899. [Google Scholar] [CrossRef]
- Ban, Y.; Yousif, O.A. Multitemporal spaceborne SAR data for urban change detection in China. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2012, 5, 1087–1094. [Google Scholar] [CrossRef]
- Hu, H.; Ban, Y. Unsupervised Change Detection in Multitemporal SAR Images Over Large Urban Areas. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2014, 7, 3248–3261. [Google Scholar] [CrossRef]
- Gao, D.-L.; Zhang, R.; Xue, D.-X. Improved fully convolutional network for the detection of built-up areas in high resolution SAR images. In Proceedings of the International Conference on Image and Graphics, Shanghai, China, 13–15 September 2017; pp. 611–620. [Google Scholar]
- Li, J.; Zhang, H.; Wang, C.; Wu, F.; Li, L. Spaceborne SAR Data for Regional Urban Mapping Using a Robust Building Extractor. Remote Sens. 2020, 12, 2791. [Google Scholar] [CrossRef]
- Wu, F.; Wang, C.; Zhang, H.; Li, J.; Li, L.; Chen, W.; Zhang, B. Built-up area mapping in China from GF-3 SAR imagery based on the framework of deep learning. Remote Sens. Environ. 2021, 262, 112515. [Google Scholar] [CrossRef]
- Li, M.; Li, M.; Zhang, P.; Wu, Y.; Song, W.; An, L. SAR Image Change Detection Using PCANet Guided by Saliency Detection. IEEE Geosci. Remote Sens. Lett. 2018, 16, 402–406. [Google Scholar] [CrossRef]
- Kang, M.; Baek, J. SAR Image Change Detection via Multiple-Window Processing with Structural Similarity. Sensors 2021, 21, 6645. [Google Scholar] [CrossRef] [PubMed]
- Ulaby, F.T.; Kouyate, F.; Brisco, B.; Williams, T.H.L. Textural Infornation in SAR Images. IEEE Trans. Geosci. Remote Sens. 1986, 2, 235–245. [Google Scholar] [CrossRef]
- Xu, Q.; Chen, K.; Sun, X.; Zhang, Y.; Li, H.; Xu, G. Pseudo-Siamese Capsule Network for Aerial Remote Sensing Images Change Detection. IEEE Geosci. Remote Sens. Lett. 2020, 19, 6000405. [Google Scholar] [CrossRef]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Lin, T.-Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2980–2988. [Google Scholar]
Region | Image Number | Included Cities | Acquisition Date | Beam Mode | Flight Direction | Resolution (m) | Polarization |
---|---|---|---|---|---|---|---|
Guangdong-Hong Kong-Macao Greater Bay Area | 1 | Hong Kong Macao Shenzhen Zhuhai Zhongshan Jiangmen | January 2022 | IW | ASCENDING | 10 | VV |
2 | Guangzhou | January 2022 | IW | ASCENDING | 10 | VV |
Type | Category | Positive Samples | Negative Samples | Total |
---|---|---|---|---|
Training set | Downtown BAs | 23 | 0 | 23 |
Mountain BAs | 8 | 9 | 17 | |
Village BAs | 16 | 6 | 22 | |
Port BAs | 7 | 0 | 7 | |
Seaside BAs | 14 | 17 | 31 | |
Total | 100 |
Region | OA (%) | PA (%) | UA (%) | F |
---|---|---|---|---|
Futian District | 93.27 | 88.17 | 90.17 | 0.89 |
Shenzhen Bay | 94.88 | 86.54 | 89.52 | 0.88 |
Hong Kong Island | 92.56 | 85.34 | 86.54 | 0.86 |
Qianshan Waterway | 95.48 | 88.69 | 91.27 | 0.90 |
Kaiping City | 93.22 | 87.26 | 88.78 | 0.88 |
Taishan City | 95.84 | 89.12 | 93.21 | 0.91 |
Region | OA (%) | PA (%) | UA (%) | F |
---|---|---|---|---|
Foshan City | 91.27 | 87.62 | 91.33 | 0.89 |
Jiangmen City | 89.88 | 87.11 | 90.66 | 0.88 |
Guangzhou City | 94.32 | 88.24 | 89.22 | 0.88 |
Dongguan City | 93.56 | 89.78 | 92.12 | 0.91 |
OA (%) | PA (%) | UA (%) | F | ||
---|---|---|---|---|---|
Shenzhen and Hong Kong regions | Our method | 93.22 | 86.62 | 88.65 | 0.87 |
WSF product | 93.67 | 87.15 | 89.88 | 0.88 | |
Jiangmen City regions | Our method | 90.12 | 85.05 | 88.72 | 0.87 |
WSF product | 91.33 | 86.21 | 89.08 | 0.87 |
Region | Method | OA (%) |
---|---|---|
Futian District | Our method | 93.27 |
BA-Unet | 84.18 | |
PSPNet | 82.15 | |
Shenzhen Bay | Our method | 94.88 |
BA-Unet | 83.21 | |
PSPNet | 80.38 | |
Hong Kong Island | Our method | 92.56 |
BA-Unet | 84.54 | |
PSPNet | 83.54 | |
Qianshan Waterway | Our method | 95.48 |
BA-Unet | 83.45 | |
PSPNet | 82.67 | |
Kaiping City | Our method | 93.22 |
BA-Unet | 82.87 | |
PSPNet | 80.56 | |
Taishan City | Our method | 95.84 |
BA-Unet | 80.28 | |
PSPNet | 77.51 |
Images | Image Size | Method | Time (s) |
---|---|---|---|
Image number 1 | 25,088 × 7680 | Our method | 72.84 |
BA-Unet | 112.47 | ||
PSPNet | 173.54 | ||
Image number 2 | 19,968 × 14,336 | Our method | 76.32 |
BA-Unet | 108.52 | ||
PSPNet | 186.21 |
Regions | Our Original Method | Our Method without the Speckle DiverGence Feature | Our Method without the Spatial Statistical Features | |
---|---|---|---|---|
Foshan | OA (%) | 93.21 | 84.21 | 71.98 |
Jiangmen | OA (%) | 91.03 | 82.09 | 69.56 |
Guangzhou | OA (%) | 92.34 | 83.01 | 68.32 |
Dongguan | OA (%) | 90.88 | 79.32 | 64.43 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, W.; Lu, S.; Xiang, D.; Su, Y. Built-Up Area Mapping for the Greater Bay Area in China from Spaceborne SAR Data Based on the PSDNet and Spatial Statistical Features. Remote Sens. 2022, 14, 3428. https://doi.org/10.3390/rs14143428
Zhang W, Lu S, Xiang D, Su Y. Built-Up Area Mapping for the Greater Bay Area in China from Spaceborne SAR Data Based on the PSDNet and Spatial Statistical Features. Remote Sensing. 2022; 14(14):3428. https://doi.org/10.3390/rs14143428
Chicago/Turabian StyleZhang, Wei, Shengtao Lu, Deliang Xiang, and Yi Su. 2022. "Built-Up Area Mapping for the Greater Bay Area in China from Spaceborne SAR Data Based on the PSDNet and Spatial Statistical Features" Remote Sensing 14, no. 14: 3428. https://doi.org/10.3390/rs14143428