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 intraclass similarity and interclass separability in high-resolution remote sensing images (HRRSIs), 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 article 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, an 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 interclass 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. The code will be available athttps://github.com/xchouzhang/EDSNet.

Raw Night-Time-Light (NTL) images captured by the Glimmer Image for Urbanization (GIU) sensor of the SDGSAT-1 satellite face the problem of stripe noise and vignetting. This paper proposed a universal method for relative radiometric correction of NTL images captured by push-broom system. Firstly, NTL ground object pixels from stripe noise were masked by setting thresholds of digital number (DN) value, allowing for the calculation of stripe noise thresholds. Secondly, a new vignetting correction was proposed by using a novel "Night-Day" orbital images as calibration data. The calculated stripe noise thresholds and vignetting correction parameters can be applied to other raw orbital images. The results were found to be superior to existing methods. In addition, using the calculated correction parameters can solve the residual stripes existing in the official products. Finally, the results of relative radiometric correction on raw images from different places further demonstrate the credibility of the proposed method.

There is a large amount of out-of-distribution data (OOD) in remote sensing, which hinders high-accuracy segmentation models under the assumption of independent identical distribution (i.i.d.) from stable and reliable performance in real-world remote sensing applications. And Domain Adaptation (DA) is presented to seamlessly extend classifiers to the label-scarce target domain in the presence of the label-sufficient source domain with different data distributions. However, given that the domain shift, i.e. the distribution difference between the two domains, is more serious in remote sensing images, the current DA methods for image segmentation in Computer Vision (CV) typically perform unsatisfactorily in remote sensing, even suffering from the negative domain alignment. To this end, this paper proposes the Self-Training Adversarial Domain Adaptation (STADA) method for remote sensing image segmentation, which not only performs adversarial learning to extract domain-invariant features, but also implements Self-Training using pseudo-labels in the target domain denoised by the conditional adversarial loss for classifier adaptation. The ISPRS and WHU datasets are employed to conduct extensive experiments to investigate the effectiveness of STADA and the specific effect of its each DA component. And the experimental results demonstrate that STADA outperforms other state-of-the-art DA methods in the remote sensing image segmentation task.

Due to more abundant data sources, more various objects of interest, and more time-consuming annotations, there is a large amount of out-of-distribution (OOD) data in the remote sensing field, on which the performance of high-accuracy image segmentation models trained under ideal experimental conditions generally degrades dramatically. Domain adaptation (DA) consequently comes into being, which aims to learn the predictor for the label-scarce target domain of interest with the help of the label-sufficient source domain in the presence of the distribution difference, namely, domain shift, between the two domains. However, the off-the-shelf DA methods for image segmentation not only struggle to cope with the more complex domain shift problems in remote sensing imagery but also almost cannot process heterogeneous data directly without information loss. While the current heterogeneous DA methods mostly still rely on some supervision information from the target domain, which is typically inaccessible in the real world. To overcome these drawbacks, we propose the multilevel heterogeneous unsupervised DA (UDA) method, termed MHDA, which unifies the instance-level DA based on cycle consistency, the feature-level DA based on contrastive learning, and the decision-level DA based on task consistency into a framework to more effectively handle the complex domain shift and heterogeneous data. After that, extensive DA experiments are conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) dataset, the BigCity dataset constructed by ourselves, and the Wuhan University (WHU) dataset, to explore the effect of each module in MHDA, the necessity of heterogeneous DA, and the effectiveness of multilevel DA. And the results demonstrate that MHDA can achieve superior performance on the remote sensing image segmentation task, compared with several state-of-the-art DA methods.

The challenge of performing relative radiometric correction on raw Night-Time-Light (NTL) images captured by the Glimmer Image for Urbanization (GIU) sensor of the SDGSAT-1 satellite is the presence of stripe noise and vignetting. To address this issue, this paper presents a universal method for relative radiometric correction of NTL images captured by the push-broom system. A new automated approach to NTL pixel identification based on Gray-level Co-occurrence Matrix (GLCM) was developed to mask NTL ground object pixels from stripe noise, allowing for the calculation of credible stripe noise thresholds. A novel calibration data called "Night-Day" orbital data was introduced for vignetting correction. The "Night-Day" orbital data features an abnormal transition zone that can be used to determine the vignetting correction parameters. The stripe noise thresholds and vignetting correction parameters can be applied to other raw orbital images. Experiments were conducted on raw images from different dates to verify the universality and robustness of the method, and the results were found to be superior to existing methods. A comparison was also made between the calibrated images and original official Level-1 products, with the results indicating that the correction parameters calculated by the proposed method resolve the defects in the original Level-1 products. The correction parameters have been accepted by the official and have been used to update the original GIU Level-1 products. Finally, the results of relative radiometric correction on raw images from around the world further demonstrate the universality and credibility of the correction parameters.

Mine information extraction is of great significance to the construction of ecological civilization, the dynamic monitoring of mine development and the scientific management of mineral resources. With the emergence of high spatial resolution remote sensing imagey, traditional machine learning method gradually cannot meet the increasing demands of image interpretation. CNN-based semantic segmentation method provides a great solution for this issue. With the deepening of network layers, more the high-level features can be obtained, which brings the outstanding performance of many computer vision tasks, but also leads to the loss of structural information, which is crucial for mine information extraction. Therefore, in order to improve these drawbacks, we proposed a novel network based on the classical semantic segmentation network, SegNet, and Graph Convolutional Network (GCN) that makes our method more sensitive to structural information. Then, taking the iron mine located in Qian'an City, Hebei Province as experimental area, we employed our method to extract five mainly mine objects: stopes, ore heap, waste dump, tailings reservoir and concentration based on GF-1 imagery. Compared with SegNet, the mIoU of our method was improved by about 5% on our dataset and was improved by about 2.2% on PASCAL VOC2012 dataset.