Wind turbines are one of the important carriers of clean energy utilization. Accurately and rapidly detecting wind turbine objects in large-scale remote sensing images can effectively monitor the development activities and optimize energy utilization. Addressing the detection challenges posed by the complex distribution scenes and the slender, dispersed structural characteristics of wind turbines in remote sensing images, this paper proposes a remote sensing image wind turbine detector, RSWDet, based on neural networks. RSWDet comprises two innovative key modules. The first is a dual-branch structured point set detection head, which, through training, adapts to the unique features of wind turbines, enabling accurate detection in large-scale complex backgrounds. The second is the Low-level Feature Enhancement (LFE) module, which compensates for the loss of wind turbine feature information during sampling by leveraging rich low-level feature information. Experimental verification of RSWDet was conducted on datasets and real-world scenes. The results demonstrate that RSWDet exhibits significant advantages compared to other algorithms, achieving the highest average accuracy of 83.1%, precision of 97.8%, and recall of 99% on the validation set. In the actual multi-scene GF2 remote sensing image test, with a threshold of 0.4, the precision can reach 85.3%, and the recall can reach 89.9%.

Remote sensing visual grounding (RSVG) aims to accurately localize specific targets in remote sensing (RS) images based on natural language descriptions. However, existing RSVG datasets often contain overly simplistic textual descriptions, exhibit imbalanced object size distributions, and lack semantic connections between targets and the surrounding contexts. Moreover, current approaches rely on global visual features for region-level localization, while the interaction between visual and textual modalities remains limited. To address these challenges, we propose improvements from both the dataset and algorithm perspectives. First, we explore the semantic correlation between remote sensing objects and their scene context. Based on high-resolution Gaofen satellite imagery, we expand several typical object categories and construct richer textual descriptions that reflect object-background associations. By refining and extending the existing DIOR-RSVG dataset, we build a new dataset named DGF-RSVG. Second, to enhance the semantic alignment between global visual features and textual features, we propose a novel global vision-language multimodal feature interaction enhancement module (GME). In parallel, we design a local attention enhancement module (LAE) to facilitate fine-grained interaction between object-related textual features and regional visual proposals. These two modules form the foundation of our newly developed detection framework: the global-local attention enhanced detector (GLAED). Extensive experiments show that GLAED achieves state-of-the-art performance on the DGF-RSVG dataset, outperforming the closest competitor by 4.3% in Pr@0.5. It also achieves highly competitive results on the DIOR-RSVG dataset, demonstrating the effectiveness of both our proposed dataset and model framework.

As an important facility for effectively controlling water pollution discharge and recycling waste water resources, accurate sewage treatment plant extraction is very important for protecting quality, function, and sustainable development of the water environment. However, due to the presence of rectangular and circular treatment facilities in sewage treatment plants, the shapes are diverse and the scales are different, resulting in the poor performance of conventional object detection algorithms. This paper proposes a multi-attention network (MANet) for sewage treatment plants using remote sensing images. MANet consists of three major components: a light backbone used to obtain multi-scale features, a channel and spatial attention module that realizes the feature representation of the channel dimension and spatial dimension, and a scale attention module to obtain scale-aware features. The results from the extensive experiments performed on the sewage treatment plant dataset suggest that our proposed MANet exhibits a superior performance compared with other competing methods. Meanwhile, we used a well-trained model to predict the sewage treatment plant from the GF-2 data for the Beijing area. By comparing the results with the data of manually obtained sewage treatment plants, our method can achieve an accuracy of 80.1% while maintaining the recall rate at a high level (90.4%).

Change detection aims to identify surface changes by analyzing remote sensing imagery acquired at different time points. A wide range of deep learning methods have been developed, typically relying on carefully designed models trained on limited publicly available datasets. Moreover, some studies have explored the application of visual foundation models with a large amount of prior knowledge to change detection tasks. However, the existing change detection networks based on vision foundation models ignore the semantic constraints between multi-temporal images. To address this issue, this paper presents an advanced vision foundation model-constrained change detection network (VFCCD), which effectively integrates features from vision foundation models into the change detection task. The proposed network is designed from the perspectives of feature transfer and feature decoding to improve the extraction performance of changing regions. First, we introduce the semantic feature transfer module (SFTM), which uses a cross-attention mechanism to effectively transfer visual features to the change detection network. We subsequently develop a semantic feature-constrained decoder (SFC-Decoder) that directly incorporates visual features into the decoder to extract the semantic information of change regions. A feature-level loss constraint is then applied based on the ground truth and the predicted change results. To verify the effectiveness and robustness of our proposed method, we conduct comparative experiments on multiple datasets. The results demonstrate that our approach achieves state-of-the-art performance. Additionally, we construct an application-oriented change detection dataset (SDCD) using selected remote sensing imagery from Shandong Province. The distribution map of the change detection results in Shandong Province further proves the feasibility of our proposed model in large-scale applications. Our code is available at https://github.com/WuChaseSea/VFCCD.