MP-Net: An efficient and precise multi-layer pyramid crop classification network for remote sensing images

Accurate crop classification map is of great significance in various fields such as the survey of agricultural resource, the analysis of existing circumstance on land application, the yield estimation of crop and the disaster warning. The methods based on machine learning and deep learning are popularly used in crop classification and recognition of remote sensing images. However, the crop classification task based on neural networks still faces significant challenges due to the spatial and temporal distribution of crops and the inherent characteristics of remote sensing images. Therefore, this study proposes the multi-layer pyramid crop classification network (MPNet) to solve the above problems. To reduce the feature loss during the crop extraction, the proposed model uses the pyramid pooling module to improve the ability of global information acquisition, and the information concatenation module to retain the upper features. Using the GF-6 and Sentinel-2 satellite data, the proposed model was tested in Erhai Lake Basin and Beian City. Compared with other five deep learning models, such as FCN, SegNet, U-Net, PSPNet and DeepLabv3+, the experimental results indicate that the proposed model achieves the highest accuracy in both study areas. Meanwhile, the proposed model has the advantages of short training time and high efficiency under the same running conditions. Overall, this study is beneficial to improve the efficiency and accuracy of crop classification task in the unbalanced temporal and spatial distribution. It also brings a feasible scheme for crop classification tasks in complex growing areas. The code has been publicly available at https://github.com/Xu-Chang-Hong/MP-Net.

Automated summary

This study proposes a multi-layer pyramid crop classification network (MPNet) to solve the challenges faced in crop classification tasks based on neural networks. By using a pyramid pooling module to improve global information acquisition and an information concatenation module to retain upper features, feature loss during crop extraction is reduced. Experimental results show that the proposed model achieves the highest accuracy compared to five other deep learning models, and it also has a shorter training time and higher efficiency under the same running conditions. Overall, this study improves the efficiency and accuracy of crop classification tasks in unbalanced temporal and spatial distribution, providing a feasible solution for crop classification tasks in complex growing areas.