Deep learning-based semantic segmentation technology is widely applied in remote sensing and has achieved excellent performance in remote sensing image target extraction. Greenhouses play an important role in the development of agriculture in China. However, the rapid expansion of greenhouses has had a series of impacts on the environment. Therefore, the extraction of large-scale greenhouses is crucial for the sustainable development of agriculture and environmental governance. It is difficult for existing methods to acquire precise boundaries. Therefore, we propose a spatial convolutional long short-term memory structure, which can fully consider the spatial continuity of ground objects. We use multitask learning to improve the network’s ability to extract image boundaries and promote convergence through auxiliary loss. We propose a superpixel optimization module to optimize the main-branch results of network semantic segmentation using more precise boundaries obtained by advanced superpixel segmentation techniques. Compared with other mainstream methods, our proposed structure can better consider spatial information and obtain more accurate results. We chose Shandong Province, China, as the study area and used Gaofen-1 satellite remote sensing images to create a new greenhouse dataset. Our method achieved an F1 score of 77%, a significant improvement over mainstream semantic segmentation networks, and it could extract greenhouse results with more precise boundaries. We also completed large-scale greenhouse mapping for Shandong Province, and the results show that our proposed modules have great potential in greenhouse extraction.

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.

Aiming at the contradiction between accuracy and speed in industrial object detection, this paper proposes an industrial object detection method based on improved CenterNet. The improved method uses ResNet-50 as the Backbone to boost detection speed, and an upsampling layer is added to the feature processing network to improve detection accuracy. The expermient results show that the mAP of the improved method reaches 87.41 %, which is 3.44% higher than the CenterNet-Res101 method, and the detection speed reaches 31 FPS, which is 4 FPS faster than the CenterNet-Res101 method.

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.

In remote sensing semantic segmentation, imperfect labels are prevalent due to the complexities of data acquisition and annotation processes. Although recent approaches to noisy label correction in remote sensing segmentation have shown promising results, challenges remain in accuracy and generalizability, given the incomplete consideration of the complex mixing involved. Nearly all methods should address three key challenges to identify and correct noisy labels: when to select labels, which labels to select, and how to handle the selected labels. We propose a novel label correction framework, Adaptive Consistency-Guided Object-Level Label Correction with Mean Teacher (ACOC-MT), which effectively addresses all three of these challenges. The ACOC-MT framework determines when to conduct label correction through the Stable Early Learning Detection module, selects noisy labels using the Consistency Threshold Mask module, and corrects the labels through the Object Label Correction module. To validate against real-world noisy labels rather than simulated ones, we constructed three real-world noisy-labeled datasets, CPCTC-N, BBD250-N, and CFD-N, from three different remote sensing scenarios. Extensive experiments on these three datasets demonstrate the efficacy and superior performance of our approach.

Building extraction is a core task in the semantic segmentation of satellite remote sensing imagery. Conventional pixel-level segmentation methods often prioritize texture over geometric structure, resulting in suboptimal performance in complex scenes affected by illumination variations, shadows, and scale changes. In this article, an innovative object-level building extraction approach is introduced to better capture the geometric structure of buildings, which incorporates superpixel segmentation to represent images as a set of adjacent regions. The proposed model consists of a cascade multi-scale fusion module (CMSFM) that progressively integrates contextual information across different receptive fields, along with a boundary-assisted loss function designed to enhance edge delineation and improve object-level accuracy. The experimental results on the WHU building dataset and the Massachusetts Buildings Dataset show that the proposed method notably outperforms other representative semantic segmentation approaches, such as FCN, UNet, DeepLab V3, and SETR. On the WHU dataset, MRLNet achieves the largest MIoU of 90.14% and the highest F1 score of 92.47%. On the Massachusetts Buildings Dataset, MRLNet attains the best MIoU of 83.14% and the highest F1 score of 90.46%. In addition, our building extraction model achieves a substantial performance improvement after the addition of the CMSFM module and the boundary-assisted loss function, demonstrating the effectiveness of these two enhancements used in our proposed model. It is expected that this research can provide a promising tool for the accurate extraction of buildings using satellite remote sensing images, which is indispensable in urban planning, disaster assessment, and other fields.