Agricultural greenhouses (AGs) are an important component of modern facility agriculture, and accurately mapping and dynamically monitoring their distribution are necessary for agricultural scientific management and planning. Semantic segmentation can be adopted for AG extraction from remote sensing images. However, the feature maps obtained by traditional deep convolutional neural network (DCNN)-based segmentation algorithms blur spatial details and insufficient attention is usually paid to contextual representation. Meanwhile, the maintenance of the original morphological characteristics, especially the boundaries, is still a challenge for precise identification of AGs. To alleviate these problems, this paper proposes a novel network called high-resolution boundary refined network (HBRNet). In this method, we design a new backbone with multiple paths based on HRNetV2 aiming to preserve high spatial resolution and improve feature extraction capability, in which the Pyramid Cross Channel Attention (PCCA) module is embedded to residual blocks to strengthen the interaction of multiscale information. Moreover, the Spatial Enhancement (SE) module is employed to integrate the contextual information of different scales. In addition, we introduce the Spatial Gradient Variation (SGV) unit in the Boundary Refined (BR) module to couple the segmentation task and boundary learning task, so that they can share latent high-level semantics and interact with each other, and combine this with the joint loss to refine the boundary. In our study, GaoFen-2 remote sensing images in Shouguang City, Shandong Province, China are selected to make the AG dataset. The experimental results show that HBRNet demonstrates a significant improvement in segmentation performance up to an IoU score of 94.89%, implying that this approach has advantages and potential for precise identification of AGs.

High-resolution thermal infrared (TIR) remote sensing images can more accurately retrieve land surface temperature and describe the spatial pattern of urban thermal environment. The Thermal Infrared Spectrometer (TIS), which has high spatial resolution among spaceborne thermal infrared sensors at present, and global data acquisition capability, is one of the sensors equipped in the SDGSAT-1. It is an important complement to the existing international mainstream satellites. In order to produce standard data products, rapidly and accurately, the automatic registration and geometric correction method needs to be developed. Unlike visible–visible image registration, thermal infrared images are blurred in edge details and have obvious non-linear radiometric differences from visible images, which make it challenging for the TIR-visible image registration task. To address these problems, homomorphic filtering is employed to enhance TIR image details and the modified RIFT algorithm is proposed to achieve TIR-visible image registration. Different from using MIM for feature description in RIFT, the proposed modified RIFT uses the novel binary pattern string to descriptor construction. With sufficient and uniformly distributed ground control points, the two-step orthorectification framework, from SDGSAT-1 TIS L1A image to L4 orthoimage, are proposed in this study. The first experiment, with six TIR-visible image pairs, captured in different landforms, is performed to verify the registration performance, and the result indicates that the homomorphic filtering and modified RIFT greatly increase the number of corresponding points. The second experiment, with one scene of an SDGSAT-1 TIS image, is executed to test the proposed orthorectification framework. Subsequently, 52 GCPs are selected manually to evaluate the orthorectification accuracy. The result indicates that the proposed orthorectification framework is helpful to improve the geometric accuracy and guarantee for the subsequent thermal infrared applications.

Plastic greenhouses (PGs), as an important part of modernized facility-based agriculture, are widely used worldwide to improve crop yield. To facilitate precision agricultural management and environment assessment, there has been widespread research attention that focuses on accurately mapping the spatial distribution and exploring coverage of PGs via remote sensing and deep learning techniques. However, limited by PGs’ poor intra-class similarity and inter-class separability in high-resolution remote sensing images (HRRSI), existing methods for PGs extraction are hard to achieve promising performance. Besides, their visualization results also suffer from adhesion problems in densely distributed areas, due to the lack of attention to geometric and boundary information. Therefore, this paper proposes a novel edge-guided dual stream network (EDSNet), which consists of an edge detection branch, a body extraction branch, and an adaptive fusion module. In the body extraction branch, a new feature extractor, termed geometric-refined attention module (GRAM), is embedded to enhance the geometric information of PGs. Moreover, edge-guided module (EGM) is introduced to guide the edge detection branch to gradually recover precise boundary details. Finally, the adaptive semantic fusion module (ASFM) adaptively fuses enhanced edge features and body features to maximally facilitate the information interaction between dual branches, thus improving inter-class separability on both sides of edges while suppressing meaningless information outside bodies. The proposed EDSNet is validated on self-labeled and publicly available datasets, and the results demonstrate that this method performs well and is suitable for accurate extraction of PGs. Code will be available at https://github.com/xchouzhang/EDSNet.

Thermal Power Plants (TPPs), as widely used industrial facilities for electricity generation, represent a key task in remote sensing image interpretation. However, detecting TPPs remains a challenging task due to their complex and irregular composition. Many traditional approaches focus on detecting compact, small-scale objects, while existing composite object detection methods are mostly part-based, limiting their ability to capture the structural and textural characteristics of composite targets like TPPs. Moreover, most of them rely on single-modality data, failing to fully exploit the rich information available in remote sensing imagery. To address these limitations, we propose a novel Cross-Modal Frequency-Responsive Attention Network (CFRANet). Specifically, the Modality-Aware Fusion Block (MAFB) facilitates the integration of multi-modal features, enhancing inter-modal interactions. Additionally, the Frequency-Responsive Attention (FRA) module leverages both spatial and localized dual-channel information and utilizes Fourier-based frequency decomposition to separately capture high- and low-frequency components, thereby improving the recognition of TPPs by learning both detailed textures and structural layouts. Experiments conducted on our newly proposed AIR-MTPP dataset demonstrate that CFRANet achieves state-of-the-art performance, with a ${\mathrm{mAP}}_{50}$ of 82.41%.

In this paper we present a new conditional random field (CRF) model based on Gaussian mixture potentials for indoor image labeling, which is useful in interactive room decoration system. Indoor images which posses many spatial regularities can be efficiently modeled by probabilistic graphical models such as CRF. The potential functions in CRF are usually set empirically and differently for different features depending on applications. We propose a new CRF model based on a general Gaussian mixture potential for different group of features, which has the advantage of labeling accuracy and training simplicity. The new model with belief propagation inference and stochastic gradient descent training is applied to floor region labeling of indoor images in Labelme database. Simulation results and visual effects prove our analysis. Comparing to other CRF models the new approach is more efficient for indoor image labeling tasks.

Accurate segmentation of coastal aquaculture ponds from high-resolution remote sensing images is critical for applications such as coastal environmental monitoring, land use mapping, and infrastructure management. Semi-supervised learning (SSL) has emerged as a promising paradigm by leveraging labeled and unlabeled data to reduce annotation costs. However, existing SSL methods often suffer from pseudo-label quality degradation, manifested as boundary adhesion and intra-class inconsistencies, which significantly affect segmentation accuracy. To address these challenges, we propose Semi-BSU, a boundary-aware semi-supervised semantic segmentation framework based on the mean teacher architecture. Semi-BSU integrates two novel components: (1) a Boundary Consistency Constraint (BCC), which employs an auxiliary boundary classifier to enhance contour accuracy in pseudo labels, and (2) a Superpixel Refinement Module (SRM), which refines pseudo labels at the superpixel level to improve intra-class consistency. Comprehensive experiments conducted on GF6 and ZY1E high-resolution remote sensing imagery, covering diverse coastal environments with complex geomorphological features, demonstrate the effectiveness of our approach. With half of the training set labeled, Semi-BSU achieves an MIOU of 0.8606, F1 score of 0.8896, and Kappa coefficient of 0.8080, outperforming state-of-the-art methods including CPS, GCT, and UniMatch by 0.3–4.9% in MIOU. The method maintains a compact computational footprint with only 1.81 M parameters and 55.71 GFLOPs. Even with only 1/8 labeled data, it yields a 3.57% MIOU improvement over the supervised baseline. The results demonstrate that combining boundary-aware learning with superpixel-based refinement offers an effective and efficient strategy for high-quality pseudo-label generation and accurate mapping of coastal aquaculture ponds in remote sensing imagery.