201. Land Use and Land Cover Mapping in China Using Multimodal Fine-Grained Dual Network
- Author
-
Liu, Shang, Wang, Huadong, Hu, Yuan, Zhang, Mengting, Zhu, Yixuan, Wang, Zhibin, Li, Dongyang, Yang, Mingyang, and Wang, Fan
- Abstract
With the advancement of geo-systems and the increased availability of satellite data, a plethora of land-use and land-cover (LULC) products have been developed. The existing LULC products primarily relied on time-series imagery to classify land by pixel-based classifiers, allowing for local analysis and accurate boundary detection. However, the advent of deep learning has shifted toward the use of patch-based CNN models for generating land cover maps. In this article: 1) we create a training dataset for China using a voting strategy based on three off-the-shelf available LULC products, avoiding the labor-intensive manual annotation. 2) We design a novel CNN-based model for the LULC task, called multimodal fine-grained dual network (dubbed as Dual-Net), which takes dual-date images to generate final maps and reduces the need for gap-free temporal sequences or separate cloud detection. To leverage the correlation between location, date, and category, we embed modal information (dates and geo-locations) into the model. Furthermore, by incorporating low-level constraints and using pseudolabel refinement, we continually improve the performance and achieve more refined segmentation. 3) Due to the lack of a suitable validation dataset for China, we create a new validation dataset called the China Sentinel2 Validation Dataset (CSVD) by manually annotating 733 finely labeled images of
$1024 \times 1024$ - Published
- 2023
- Full Text
- View/download PDF