Mapping urban form and land use with deep learning techniques: a case study of Dongguan City, China

Chen, Feihao; Tsou, Jin Yeu

doi:10.1504/ijogct.2022.121050

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods cannot resolve the heterogeneity within land uses and are hard to produce accurate results for complex land uses, because they rely heavily on the qualities of hand-crafted features which can be highly heterogeneous and are easily mis-classified by the traditional classifiers. To resolve this issue, state-of-the-art deep learning methods have been widely applied to land-use classifications in recent several years [32], as deep learning methods can automatically extract robust, representative, and abstract features of land uses, reducing the heterogeneity and improving the classification accuracy [33], [34], [35]. However, deep-learning semantic segmentation methods, such as RefineNet, PSPNet, and DeepLabv3+ [36], [37], may exacerbate the ambiguity of land-use boundaries due to the deconvolution and upsampling processes [38], leading to inaccurate boundaries of land uses.…”

Section: A Land-use Classificationmentioning

confidence: 99%

Synergistic Classification of Multilevel Land Patches (SC-MLPs): Reducing Conflicts and Improving Mapping Results for Land Uses and Functional Spaces With Very-High-Resolution Satellite Imagery

Zhang,

Xiong,

Dong

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Land uses (e.g., commercial, residential, and industrial lands) and functional spaces (e.g., living, productive, and ecological spaces) are two-level landscape patches and totally work as basic units for urban planning. The two-level patches are interrelated and mutually binding, but existing mapping methods extracted them separately, leading to substantial conflicts and errors in their mapping results. Accordingly, this study proposes a synergistic classification of multilevel land patches (SC-MLPs). It considers a multitask learning strategy and proposes a novel correlation loss function to measure the correlations between land uses and functional spaces, which is expected to resolve conflicts and improve the accuracy of the two-level land patch mapping results. Consequently, land-use and functional-space maps of three major Chinese cities are generated, which generally have a high resolution of 2 m and high overall accuracies of 90.1% for land uses and 93.8% for functional spaces. Compared to state-of-the-art land-use and functional-space mapping methods, our results have not only higher accuracies but also a better consistency which is improved by 36%. Accordingly, the proposed SC-MLP can generate not only accurate but also consistent maps of land uses and functional spaces, which plays a fundamental role in land system research and urban planning.

show abstract