Extracting Citrus-Growing Regions by Multiscale UNet Using Sentinel-2 Satellite Imagery

Abstract

Citrus is an important commercial crop in many areas. The management and planning of citrus growing can be supported by timely and efficient monitoring of citrus-growing regions. Their complex planting structure and the weather are likely to cause problems for extracting citrus-growing regions from remote sensing images. To accurately extract citrus-growing regions, deep learning is employed, because it has a strong feature representation ability and can obtain rich semantic information. A novel model for extracting citrus-growing regions by UNet that incorporates an image pyramid structure is proposed on the basis of the Sentinel-2 satellite imagery. A pyramid-structured encoder, a decoder, and multiscale skip connections are the three main components of the model. Additionally, atrous spatial pyramid pooling is used to prevent information loss and improve the ability to learn spatial features. The experimental results show that the proposed model has the best performance, with the precision, the intersection over union, the recall, and the F1-score reaching 88.96%, 73.22%, 80.55%, and 84.54%, respectively. The extracted citrus-growing regions have regular boundaries and complete parcels. Furthermore, the proposed model has greater overall accuracy, kappa, producer accuracy, and user accuracy than the object-oriented random forest algorithm that is widely applied in various fields. Overall, the proposed method shows a better generalization ability, higher robustness, greater accuracy, and less fragmented extraction results. This research can support the rapid and accurate mapping of large-scale citrus-growing regions.

RCEAU-Net: Cascade Multi-Scale Convolution and Attention-Mechanism-Based Network for Laser Beam Target Image Segmentation with Complex Background in Coal Mine

“…At the same time, combined with the skipping connection part in the structure of U-Net++, the feature extraction part of each layer is stacked, which makes up for the problem of semantic feature loss caused by the traditional skipping connection; compared with U-Net, AS-Unet++ has a significant increase in the segmentation accuracy of remote sensing images. Li, Y. et al [ 25 ] proposed a U-Net citrus plantation extraction model based on an image pyramid structure to accurately extract citrus plantation areas based on Sentinel-2 satellite images, using the pyramid structure encoder to capture contextual information at multiple scales, and using spatial pyramid pooling to prevent information loss and improve the ability to learn spatial features, which achieves high-precision large-scale citrus plantation segmentation. Khan, M.A.-M. et al [ 26 ] proposed a Dense U-Net network to segment cracks on railway sleepers based on the U-Net network model in response to the time-consuming and inefficient traditional methods of detecting cracks on railway sleepers.…”