Remote sensing image change detection is extensively utilized in various applications in the field of remote sensing, particularly in the realm of cropland conservation, where it plays a critical role in protecting the agro-ecosystem and ensuring global food security. However, the progressive improvement in resolution and size of remote sensing imagery has led to a ’scale gap’ challenge in the detection of small building changes in cropland areas. To address this challenge, an innovative multi-scale feature fusion change detection network (M-Swin) based on transformer using hierarchical windows is proposed. In order to obtain clearer edges and better separation of the change results, a novel saimese transformer encoder (MSW encoder) is proposed, which can better capture the change information in small building through hierarchical windows and fuse the multi-scale feature obtained from different windows. To effectively reduce missed and misdetected small-area of changing buildings, a novel bi-temporal image feature fusion module (BFFM) is proposed, which can enhance the features based on a priori guidance, thus improving the saliency of change regions. Additionally, a new remote sensing image change detection dataset for cropland, called LuojiaSET-CLCD, has been proposed. Experimentally demonstrates that M-Swin has good potential for highly accurate change detection of small buildings within cropland areas and outperforms several newly existing methods in three datasets (LEVIR, WHU-CD and LuojiaSET-CLCD). Our dataset will be publicly available at https://github.com/RSIIPAC/LuojiaSET-CLCD.

In this article, we introduce the method we used in the 2023 IEEE GRSS Data Fusion Contest Track 1. The task demands a fine-grained classification method for semantic urban reconstruction. Our experiments are based on Swin transformer, combined with Double-Head module and RFLA (Gaussian Receptive Field based Lable Assignment) strategy, which can effectively improve model's performance on small objects. Experimental results show that our method can bring significant improvement. We achieved the 4thplace in the final leader board.

In this article, we introduce the solution we used in the 2023 IEEE GRSS Data Fusion Contest Track 2. The task demands a roof type classification method and a building height estimation method. For roof type classification, our experiments are based on Swin transformer, combined with DoubleHead module and RFLA strategy, which can effectively improve model’s performance on small objects. For building height estimation, our experiments are based on SegFormer. Our experiments use a part of train set as validation set.

Scene classification of aerial images is the basis of automatic recognition of complex scenes, and it is also a challenging computer vision task. In recent years, with the rapid development of deep learning, the semantic feature extraction method based on a convolutional neural network (CNN) has made great progress. Moreover, a recent study indicates that combining the semantic information of deep-layer features with the detailed texture information of shallow-layer features in CNN can further improve the performance of classification. In this letter, an end-to-end multilevel feature-based network named multilevel inheritance network (MINet) is proposed for aerial scene classification. First, the feature extraction module based on the feature pyramid network (FPN) is used to get multilevel feature maps. In the process of merging shallow features, high-level semantics of deep-layer are inherited. Then, an attention mechanism is added after the multilevel features to reduce the interference of redundant information and noise. Finally, we use a feature fusion module to automatically learn the weight of each feature layer and make a comprehensive decision. The effectiveness of the proposed method is verified in AID, WHU-RS19 and NWPU-RESISC45 datasets. Results show that the proposed method achieves competitive classification accuracy.

In the field of remote sensing image processing, clouds heavily affect the quality of the remote sensing images and their application potential. Thus, in recent years, with the prevalence of deep learning techniques used in the field of image processing, many methods have been proposed for cloud removal using single remote sensing images. The existing single-image cloud removal methods suffer from poor generalization capabilities that prevent them from being applied to diverse remote sensing images. Thus, a novel method using a multimodal architecture is proposed which provides multiple most likely outputs for the image and selects the best one through perception-based image quality evaluator (PIQE). In addition, adversarial consistency loss is used to replace cycle consistency loss, which encourages the model to retain more texture information of the original image, and thus the quality of the generated image increases. Experiments demonstrate that the presented method can easily achieve a considerable increase in the peak signal-to-noise ratio and the structural similarity index compared with other methods.