Search

Extraction of vectorized building instances from remote sensing images has made significant progress in recent years. The extraction of vectorized building maps enables rapid, large-scale updates to geospatial databases. Recently, the contour-based methods have achieved amazing success because their learning goals are more compatible with vectorized polygons. However, existing contour-based approaches achieve contour updates only by learning the local features at each vertex, which can lead to a contour smoothing problem. Besides, these methods achieve classification via features at the center point, which hinders the receptive field at the instance level. Our primary motivation is to overcome existing limitations introduced by local modeling during contour regression while simultaneously improving the instance classification performance. In this article, we utilize instance-level features to guide the contour learning process. An instance-aware contour regression (IACR) module is designed to update the local contour features via cross attention on the instance-level features. Furthermore, based on the IACR module, we propose a novel vectorized building extraction framework BuildingVec, which interacts between the contour regression branch and instance classification branch through a well-designed cascade architecture. We also build a vectorized building dataset with fine-grained categories, named UBCv2 (vec), to benefit the study of vectorized extraction for fine-grained buildings. Experiments on the UBCv2 (vec) dataset demonstrate that BuildingVec achieves state-of-the-art performance compared to both mask-based methods and contour-based methods. When compared to other vectorized extraction methods on the Crowd AI dataset, BuildingVec also achieves a state-of-the-art performance with an $\text{AP}_{50}$ of 93.1%.

Most state-of-the-art synthetic aperture radar (SAR) ship detection methods based on deep learning require large amounts of labeled data for network training. However, the annotation process requires significant manpower and resources especially for SAR images, since relevant background knowledge should be necessary for the annotators. Considering the available optical imagery datasets with labels, we propose an unsupervised oriented SAR ship detection method based on cross-modality distribution alignment, termed as CroMoDa. It consists of four components: 1) image-level feature alignment; 2) low-level feature despeckling; 3) cross-modality pseudo-label self-training; and 4) cross-modality object alignment. By aligning the multilevel feature distributions, modality-invariant features across the two imagery modalities can be learned. Considering speckle noise and other interferences in SAR images, the proposed loss term conducted on low-level features can enhance the object information to improve the detection accuracy. Moreover, the proposed pseudo-label self-training can better generate oriented SAR ship annotations than the other methods, which facilitates learning more discriminative features for SAR ship instances. With two optical–SAR dataset configurations, the proposed method is effectively evaluated by comparing to the other state of the arts, which demonstrates the great potential for SAR ship detection in real applications.

The metaverse signifies the amalgamation of virtual and tangible realms through human-computer interaction. The seamless integration of human, cyber, and environments within ubiquitous computing plays a pivotal role in fully harnessing the metaverse’s capabilities. Nevertheless, metaverse operating systems face substantial hurdles in terms of accessing ubiquitous resources, processing information while safeguarding privacy and security, and furnishing artificial intelligence capabilities to downstream applications. To tackle these challenges, this paper introduces the UbiMeta model, a specialized ubiquitous operating system designed specifically for the metaverse. It extends the capabilities of traditional ubiquitous operating systems and focuses on adapting downstream models and operational capacity to effectively function within the metaverse. UbiMeta comprises four layers: the Ubiquitous Resource Management Layer (URML), the Autonomous Information Mastery Layer (AIML), the General Intelligence Mechanism Layer (GIML), and the Metaverse Ecological Model Layer (MEML). The URML facilitates the seamless incorporation and management of various external devices and resources. It provides a framework for integrating and controlling these resources, including virtualization, abstraction, and reuse. The AIML is responsible for perceiving information and safeguarding privacy and security during storage and processing. The GIML leverages large-scale pre-trained deep-learning feature extractors to obtain effective features for processing information. The MEML focuses on constructing metaverse applications using the principles of Model-as-a-Service (MaaS) and the OODA loop (Observation, Orientation, Decision, Action). It leverages the vast amount of information collected by the URML and AIML layers to build a robust metaverse ecosystem. Furthermore, this study explores how UbiMeta enhances user experiences and fosters innovation in various metaverse domains. It highlights the potential of UbiMeta in revolutionizing medical healthcare, industrial practices, education, and agriculture within the metaverse.

Collaborative perception enhances onboard perceptual capability by integrating features from other platforms, effectively mitigating the compromised accuracy caused by a restricted observational range and vulnerability to interference. However, current implementations of collaborative perception overlook the prevalent issues of both limited and low-reliability communication, as well as misaligned observations in remote sensing. To address this problem, this article presents an innovative distributed collaborative perception network (DCP-Net) specifically designed for remote sensing applications. Firstly, a self-mutual information match module is proposed to identify collaboration opportunities and select suitable partners. This module prioritizes critical collaborative features and reduces redundant transmission for better adaptation to weak communication in remote sensing. Secondly, a related feature fusion module is devised to tackle the misalignment between local and collaborative features due to the multiangle observations, improving the quality of fused features for the downstream task. We conduct extensive experiments and visualization analyses using three semantic segmentation datasets, namely Potsdam, iSAID, and DFC23. The results demonstrate that DCP-Net outperforms the existing collaborative perception methods comprehensively, improving mIoU by 2.61% to 16.89% at the highest collaboration efficiency and achieving state-of-the-art performance.

This study proposes a Synthetic Aperture Radar (SAR) aircraft detection and recognition method combined with scattering perception to address the problem of target discreteness and false alarms caused by strong background interference in SAR images. The global information is enhanced through a context-guided feature pyramid module, which suppresses strong disturbances in complex images and improves the accuracy of detection and recognition. Additionally, scatter key points are used to locate targets, and a scatter-aware detection module is designed to realize the fine correction of the regression boxes to improve target localization accuracy. This study generates and presents a high-resolution SAR-AIRcraft-1.0 dataset to verify the effectiveness of the proposed method and promote the research on SAR aircraft detection and recognition. The images in this dataset are obtained from the satellite Gaofen-3, which contains 4,368 images and 16,463 aircraft instances, covering seven aircraft categories, namely A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and other. We apply the proposed method and common deep learning algorithms to the constructed dataset. The experimental results demonstrate the excellent effectiveness of our method combined with scattering perception. Furthermore, we establish benchmarks for the performance indicators of the dataset in different tasks such as SAR aircraft detection, recognition, and integrated detection and recognition.

Cutaneous T‐cell lymphoma (CTCL) encompasses two main subtypes: mycosis fungoides and Sezary syndrome. Global response rates for the systemic treatment of mycosis fungoides and Sezary syndrome are approximately 30%, and none of these treatments are thought to be curative. C–C chemokine receptor type 4 (CCR4) and CD25 are encouraging targets for the treatment of CTCL and are individually targeted by mogamulizumab and denileukin diftitox, respectively. We developed a novel CCR4‐IL2 bispecific immunotoxin (CCR4‐IL2 IT) targeting both CCR4 and CD25. CCR4‐IL2 IT demonstrated superior efficacy against CCR4+CD25+CD30+ CTCL in an immunodeficient NSG mouse tumor model. Investigative New Drug‐enabling studies of CCR4–IL2 IT are ongoing, including Good Manufacturing Practice production and toxicology studies. In this study, we compared the in vivo efficacy of CCR4‐IL2 IT versus the US Food and Drug Administration–approved drug, brentuximab, using an immunodeficient mouse CTCL model. We demonstrated that CCR4–IL2 IT was significantly more effective in prolonging survival than brentuximab, and combination treatment of CCR4–IL2 IT and brentuximab was more effective than brentuximab or CCR4–IL2 IT alone in an immunodeficient NSG mouse CTCL model. Thus, CCR4–IL2 IT is a promising novel therapeutic drug candidate for CTCL treatment.

The formation and stability of soil aggregates affect plant growth, carbon sequestration, and many other physiological and biogeochemical processes. Aggregates may be destabilized by nitrogen (N) deposition due to decreased inputs of binding materials; however, the legacy effects of which are unknown. An increase in labile carbon (C) input could mitigate the negative impacts of N addition on soil aggregate stability through the improvement of soil physical, chemical and biological conditions. Using a field experiment with the addition of NH4NO3 at multiple levels in a meadow steppe, we terminated the addition of N at the sixth year and shifted to applying labile C in the form of sucrose at three levels (C-0, C-200, and C-2000 g C m−2 y−1) to soil for two years. Then we examined the aggregate size distribution and the associated soil properties. The high historical N addition rates decreased the proportion of macroaggregates (>2000 μm) and increased microaggregates (

In recent years, legged robots have been more and more widely used on non-structured terrain, and their foot structure has an important impact on the robot’s motion performance and stability. The structural characteristics of the yak foot sole with a high outer edge and low middle, which has excellent soil fixation ability and is an excellent bionic prototype, can improve the friction between the foot and the ground. At the same time, the foot hooves can effectively alleviate the larger impact load when contacting with the ground, which is an excellent anti-slip buffer mechanism. The bionic foot end design was carried out based on the morphology of the yak sole; the bionic foot design was carried out based on the biological anatomy observation of yak foot skeletal muscles. The virtual models of the bionic foot end and the bionic foot were established and simulated using Solidworks 2022 and Abaqus 2023, and the anti-slip performance on different ground surfaces and the influence of each parameter of the bionic foot on the cushioning effect were investigated. The results show that (1) the curved shape of the yak sole has a good anti-slip performance on both soil ground and rocky ground, and the anti-slip performance is better on soil ground; (2) the curved shape of the yak sole has a larger maximum static friction than the traditional foot, and the anti-slip performance is stronger under the same pressure conditions; (3) the finger pillow–hoof ball structure of the bionic foot has the greatest influence on the buffering effect, and the buffering effect of the bionic foot is best when the tip of the bionic foot touches the ground first.

In order to assess the heavy metal pollution features, ecological dangers, and health risk status posed to human beings by soils in the Ankang Basin, a study was conducted. This involved the collection of 38 surface soil samples, followed by the determination of elemental levels of arsenic, mercury, copper, cadmium, lead, chromium, nickel, and zinc. The concentrations of arsenic, mercury, copper, cadmium, lead, chromium, nickel, and zinc were quantified through the collection of 38 surface soil samples. The data obtained from the study was subjected to analysis and evaluation utilizing various academic methodologies, including the geo-accumulation index method, potential ecological risk assessment method, human health risk assessment model, and Monte Carlo simulation method. The findings indicated that the concentrations of the eight heavy metals in the soil above the background levels, with only Cadmium (Cd) marginally surpassing the threshold set for controlling soil pollution risks. The ground accumulation index revealed a higher degree of soil pollution with mercury, cadmium, copper, and zinc components. According to the possible ecological risk index, the presence of mercury and cadmium elements poses significant ecological hazards. The geographical distribution analysis suggests that these risks mostly stem from the combined impacts of human activities and the topographical and geomorphological characteristics of the river valley. The findings of the human health risk assessment indicated that the non-carcinogenic risk fell within acceptable limits. Additionally, it was observed that the carcinogenic risk associated with arsenic, mercury, cadmium, and nickel was comparatively greater for children as compared to adults. The results of the Monte Carlo simulations indicate that the non-carcinogenic hazards have a negligible effect on human health. However, it was seen that arsenic and nickel have a greater likelihood of presenting a substantial carcinogenic risk to humans, particularly in relation to the pediatric population, hence exerting a more pronounced impact on their health. In general, it is observed that conventional deterministic risk assessments tend to overstate the potential health risks associated with a given situation. Conversely, the utilization of Monte Carlo simulations has been found to effectively mitigate uncertainties in health risk assessments. It has been observed that children exhibit a higher vulnerability to both carcinogenic and non-carcinogenic health impacts resulting from exposure to heavy metals present in soil, in comparison to adults. It is recommended that residents prioritize the surveillance of soil heavy metals in relation to potential impacts on human health.

Few-shot learning, which aims to learn the concept of novel category from extremely limited labeled samples, has received intense interests in remote sensing image scene classification. Most of the existing methods inherit the philosophy of prototype learning and tackle classification as the prototype-based metric matching problem. Despite the achievement that has been obtained so far, the problems of interclass metric misalignment and intraclass variations have become two main challenges that obstacle the performance. In this article, a novel transductive learning framework with conditional metric embedding is proposed to remedy these problems. First, a conditional metric embedding mechanism is introduced to perform anisotropic embedding for each pair of the support category and query instance. This design provides the model with flexible scalability to accommodate the metric biases across classes. Second, a transductive prototype learning strategy is presented to enhance the robustness of the prototype against intraclass variations. The unlabeled query instances are transformed into pseudo instances equipped with credibility coefficients and then leveraged to calibrate the prototype estimation bias in low-data regimes. Third, a long-term consistency regularization is designed, which continuously memorizes the historical prototypes to generate additional supervision of interclass separation in the global label space. Benefiting from this design, the discriminability of the prototypes obtains obvious improvement. Finally, extensive experiments are conducted on three public benchmark remote sensing datasets. The experimental results demonstrate the validity and the superiority of the proposed method in low-shot conditions.

The sample scarcity issue is still challenged for SAR images interpretation. The number of geospatial targets related images is constrained of the SAR images interpretation ability of data acquisition, sample labeling, and the lack of target coverage. Our SAR-ATR method is demonstrated based on scattering information and meta-learning. First, the discrete distribution of the spatial structure of different types of aircraft is quite different in SAR images. An associated scattering classifier is designed to guide the network to learn more discriminative intra-class and inter-class feature descriptions. Our proposed classifier facilitates the modeling of discrete degree of the aircraft target quantitatively and balance the weights of sample pairs dynamically through the differentiated analysis of different target discrete distributions. In addition, an adaptive feature refinement module is designed to optimize the network cohesion for the key parts of the aircraft and reduce the interference of background noise. The proposed method integrates the target scattering distribution properties to the network learning process. On 5-way 1-shot emerging categorized recognition task involved only few samples, our experimental results demonstrate that the recognition accuracy of this method is 59.90%, which is 3.85% higher than the benchmark. After reducing the amount of training data by half, the proposed method is still competitive on the new category of few-shot recognition tasks.

Over the recent years, high-resolution Synthetic-Aperture Radar (SAR) images have been widely applied for intelligent interpretation of urban mapping, change detection, etc. Different from optical images, the acquisition approach and object geometry of SAR images have limited the interpretation performances of the existing deep-learning methods. This paper proposes a novel building footprint generation method for high-resolution SAR images. This method is based on supervised contrastive learning regularization, which aims to increase the similarities between intra-class pixels and diversities of interclass pixels. This increase will make the deep learning models focus on distinguishing building and nonbuilding pixels in latent space, and improve the classification accuracy. Based on public SpaceNet6 data, the proposed method can improve the segmentation performance by 1% compared to the other state-of-the-art methods. This improvement validates the effectiveness of the proposed method on real data. This method can be used for building segmentation in urban areas with complex scene background. Moreover, the proposed method can be extended for other types of land-cover segmentation using SAR images.

Abstract Background Bletilla striata is the main medicine of many skin whitening classic formulas in traditional Chinese medicine (TCM) and is widely used in cosmetic industry recently. However, its active ingredients are still unclear and its fibrous roots are not used effectively. The aim of the present study is to discover and identify its potential anti-melanogenic active constituents by zebrafish model and molecular docking. Methods The antioxidant activities were evaluated by 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity, 2,2′-azino-bis-(3-ethylbenthiazoline-6-sulphonic acid) (ABTS) radical scavenging activity and ferric reducing antioxidant power (FRAP) assay. The anti-melanogenic activity was assessed by tyrosinase inhibitory activity in vitro and melanin inhibitory in zebrafish. The chemical profiles were performed by ultra-high-performance liquid chromatography combined with quadrupole time-of-flight tandem mass spectrometry (UPLC-Q-TOF-MS/MS). Meanwhile, the potential anti-melanogenic active constituents were temporary identified by molecular docking. Results The 95% ethanol extract of B. striata fibrous roots (EFB) possessed the strongest DPPH, ABTS, FRAP and tyrosinase inhibitory activities, with IC50 5.94 mg/L, 11.69 mg/L, 6.92 mmol FeSO4/g, and 58.92 mg/L, respectively. In addition, EFB and 95% ethanol extract of B. striata tuber (ETB) significantly reduced the melanin synthesis of zebrafish embryos in a dose-dependent manner. 39 chemical compositions, including 24 stilbenoids were tentatively identified from EFB and ETB. Molecular docking indicated that there were 83 (including 60 stilbenoids) and 85 (including 70 stilbenoids) compounds exhibited stronger binding affinities toward tyrosinase and adenylate cyclase. Conclusion The present findings supported the rationale for the use of EFB and ETB as natural skin-whitening agents in pharmaceutical and cosmetic industries.

Ship detection and classification in synthetic aperture radar (SAR) images play a vital role for wide applications. Due to the unique SAR imaging mechanism, ship detection and classification tasks have faced numerous challenges, such as land interference, image defocus, and noise. Many detectors and classifiers have been presented to handle these problems. However, the general deep learning-based detectors and classifiers lack the combination of SAR characteristics, which leads to poor performance. Compared with optical images, SAR images lack the texture information of ships, which brings great difficulties to the recognition task. To address the above issues, a novel deep learning-based ship detection and classification network combined with scattering characteristics is proposed in this article. First, to accurately locate ships in large-scale SAR images, this article designs a strong scattering point aware network (SPAN) by capturing the strong scattering points that existed in the ship area. SPAN recognizes the ship category according to their distribution characteristics. Second, to compensate for the feature loss caused by the down-sampling operation, this article designs a more suitable resolution recovery module to replace the bilinear interpolation method. Third, a region of interest automatic generation module is proposed to fully utilize the axis-align feature of oriented proposal boxes and the sufficient information of horizontal proposal boxes. Furthermore, the classification encoder module extracts the distribution feature of scattering points to classify SAR ships. Finally, the comprehensive experiments in the large-scale dataset for ship detection and classification in SAR images (LDSD) demonstrate the superior performance of the proposed method.

Polarimetric synthetic aperture radar (PolSAR) terrain segmentation is a fundamental research topic in PolSAR image interpretation. Recently, many studies have been investigated to handle this task. However, the existing data for PolSAR terrain segmentation have relatively limited scale and their scene complexity is relatively simple. These issues greatly restrict the development of algorithms. Therefore, there is a strong requirement for establishing a large-scale data set for terrain segmentation in complex-scene PolSAR images. In this paper, we present a benchmark data set containing a PolSAR amplitude image with a 9082×9805-pixel region and 2000 image patches with a size of 512×512 for PolSAR terrain segmentation, which is called AIR-PolSAR-Seg. We collect the PolSAR image with a resolution of 8 m from the GaoFen-3 satellite, and it is equipped with pixel-wise annotation which covers six categories. Compared with the previous data resources, AIR-PolSAR-Seg preserves some specific properties. First, AIR-PolSAR-Seg owns a large-size PolSAR image and provides a large quantity of image patches. It offers the research community a complete data resource with adequate training examples and reliable validation results. Second, AIR-PolSAR-Seg is established upon a PolSAR image with high scene complexity. This characteristic motivates robust and advanced segmentation approaches to facilitate complex-scene PolSAR image analysis. Based on AIR-PolSAR-Seg, three tasks are introduced: multi-category segmentation, water body segmentation, and building segmentation. Moreover, a performance analysis of traditional approaches and deep learning-based approaches are conducted, which can be regarded as baselines and provide references for future research.

CD3-epsilon(CD3e) immunotoxins (IT), a promising precision reagent for various clinical conditions requiring effective depletion of T cells, often shows limited treatment efficacy for largely unknown reasons. Tissue-resident T cells that persist in peripheral tissues have been shown to play pivotal roles in local and systemic immunity, as well as transplant rejection, autoimmunity and cancers. The impact of CD3e-IT treatment on these local cells, however, remains poorly understood. Here, using a new murine testing model, we demonstrate a substantial enrichment of tissue-resident Foxp3+ Tregs following CD3e-IT treatment. Differential surface expression of CD3e among T-cell subsets appears to be a main driver of Treg enrichment in CD3e-IT treatment. The surviving Tregs in CD3e-IT-treated mice were mostly the CD3edimCD62Llo effector phenotype, but the levels of this phenotype markedly varied among different lymphoid and nonlymphoid organs. We also found notable variations in surface CD3e levels among tissue-resident T cells of different organs, and these variations drive CD3e-IT to uniquely reshape T-cell compositions in local organs. The functions of organs and anatomic locations (lymph nodes) also affected the efficacy of CD3e-IT. The multi-organ pharmacodynamics of CD3e-IT and potential treatment resistance mechanisms identified in this study may generate new opportunities to further improve this promising treatment.

Applications of mineral nitrogen (N) and phosphorus (P) fertilizer to grasslands become more frequently in recent decade, aiming to improve the grass production. Nonetheless, the ecological impacts of N and P fertilizer on ecosystem components, especially the belowground soil microbes, are not well acknowledged in grasslands ecosystem. We investigated the responses of plant traits, soil properties, bacterial community composition and potential functions to 5-year N and P fertilization in a mid-high latitude meadow grassland in Inner Mongolia, China. Bacterial species richness and diversity significantly (P

The study aimed to assess the gait adjustment techniques of limbs on different slopes and investigate the relationship between forelimb and hindlimb kinetics and the center of mass (COM) during the uphill movement of a specific Boer goat using a pressure-sensitive walkway (PSW). During the uphill and downhill movements at a comfortable walking speed, we measured the ground reaction force (GRF) of the forelimbs and hindlimbs on the slope, the change in the included angle of the propulsive force direction of the forelimbs and hindlimbs, and the impulse relationship between GRF and propulsive force. According to the study, since the forelimbs of the goat were nearer the COM, they were primarily adjusted during the movement on the slope. By lowering the initial included angle of the propulsive force and the angle variation range, the forelimbs and hindlimbs could walk steadily. The forelimbs and hindlimbs exhibited completely different adjustment strategies during uphill and downhill movements. In particular, the forelimbs performed braking and the hindlimbs performed driving. In addition, we discovered that the goat altered its adjustment strategy when climbing the steep slope. All findings of this study indicate the need to understand the gait adjustment mode of the Boer goat during movement on the slope to thoroughly comprehend the driving strategy of quadrupeds with the ability to walk on specialized terrains.

Anti-CD3-epsilon (CD3e) monoclonal antibodies (mAbs) and CD3e immunotoxins (ITs) are promising targeted therapy options for various T-cell disorders. Despite significant advances in mAb and IT engineering, vascular leakage syndrome (VLS) remains a major dose-limiting toxicity for ITs and has been poorly characterized for recent “engineered” mAbs. This study undertakes a direct comparison of non-mitogenic CD3e-mAb (145-2C11 with Fc-silentTM murine IgG1: S-CD3e-mAb) and a new murine-version CD3e-IT (saporin–streptavidin (sZAP) conjugated with S-CD3e-mAb: S-CD3e-IT) and identifies their distinct toxicity profiles in mice. As expected, the two agents showed different modes of action on T cells, with S-CD3e-mAb inducing nearly complete modulation of CD3e on the cell surface, while S-CD3e-IT depleted the cells. S-CD3e-IT significantly increased the infiltration of polymorphonuclear leukocytes (PMNs) into the tissue parenchyma of the spleen and lungs, a sign of increased vascular permeability. By contrast, S-CD3e-mAbs-treated mice showed no notable signs of vascular leakage. Treatment with control ITs (sZAP conjugated with Fc-silent isotype antibodies) induced significant vascular leakage without causing T-cell deaths. These results demonstrate that the toxin portion of S-CD3e-IT, not the CD3e-binding portion (S-CD3e-mAb), is the main driver of vascular leakage, thus clarifying the molecular target for improving safety profiles in CD3e-IT therapy.