MCC-Net: a multi-channel complementation net for remote sensing monitoring of the non-agriculturalization within arable land

This article proposes a multi-channel complementary change detection network (MCC-Net) integrating Convolutional Neural Network (CNN) and Transformer architectures. Firstly, a three-channel feature extraction module is designed for fully extracting the spatio-temporal features of the two-phase images. Then, a pyramid spatio-temporal cross-attention module is constructed to enhance the spatio-temporal features extracted with the CNN and Transformer by leveraging the interpolated features of the two-phase images to highlight the information of the changes. Finally, a multi-layered feature fusion module is proposed to further enhance the augmented features from the perspectives of both layers and channels. On the Henan Cultivated Land Change Dataset (HCLCD) and control change detection datasets (PX-CLCD, LuojiaSET-CLCD), the F1-score/Intersection over Union (IoU) values of MCC-Net reached 80.15%/65.02%, 95.50%/90.95%, and 72.50%/56.83%, respectively, which were significantly better than those of six state-of-the-art comparison methods. These results demonstrate that MCC-Net possesses a superior ability to identify within-class difference scenarios of cropland non-agriculturalization.