Search results

High-resolution remote sensing images possess a wealth of semantic information. However, these images often contain objects of different sizes and distributions, which make the semantic segmentation task challenging. In this paper, a bidirectional feature fusion network (BFFNet) is designed to address this challenge, which aims at increasing the accurate recognition of surface objects in order to effectively classify special features.

There are two main crucial elements in BFFNet. Firstly, the mean-weighted module (MWM) is used to obtain the key features in the main network. Secondly, the proposed polarization enhanced branch network performs feature extraction simultaneously with the main network to obtain different feature information. The authors then fuse these two features in both directions while applying a cross-entropy loss function to monitor the network training process. Finally, BFFNet is validated on two publicly available datasets, Potsdam and Vaihingen.

In this paper, a quantitative analysis method is used to illustrate that the proposed network achieves superior performance of 2–6%, respectively, compared to other mainstream segmentation networks from experimental results on two datasets. Complete ablation experiments are also conducted to demonstrate the effectiveness of the elements in the network. In summary, BFFNet has proven to be effective in achieving accurate identification of small objects and in reducing the effect of shadows on the segmentation process.

The originality of the paper is the proposal of a BFFNet based on multi-scale and multi-attention strategies to improve the ability to accurately segment high-resolution and complex remote sensing images, especially for small objects and shadow-obscured objects.

This paper aims to give an oversight of what is being done by researchers in GIS and remote sensing (field) to explore minerals. The main objective of this review is to explore how GIS and remote sensing have been beneficial in identifying mineral deposits for easier and cost-effective mining.

The approach of this research used Web of Science to generate a database of published articles on the application of GIS and remote sensing techniques for mineral exploration. The literature was further digested, noting the main findings, adopted method, illustration and research scales.

When applied alone, each technique seems effective, but it is important to know that combining different methods is more effective in identifying ore deposits.

This paper also examined and provided possible solutions to both current and future perspective issues relating to the application of GIS and remote sensing to mineral exploration. The authors believe that the conclusions and recommendations drawn from case studies and literature review will be of great importance to geoscientists and policymakers.

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

This research aims to propose a model for the complex decision-making involved in the ecological restoration of mega-infrastructure (e.g. railway engineering). This model is based on multi-source heterogeneous data and will enable stakeholders to solve practical problems in decision-making processes and prevent delayed responses to the demand for ecological restoration.

Based on the principle of complexity degradation, this research collects and brings together multi-source heterogeneous data, including meteorological station data, remote sensing image data, railway engineering ecological risk text data and ecological restoration text data. Further, this research establishes an ecological restoration plan library to form input feature vectors. Random forest is used for classification decisions. The ecological restoration technologies and restoration plant species suitable for different regions are generated.

This research can effectively assist managers of mega-infrastructure projects in making ecological restoration decisions. The accuracy of the model reaches 0.83. Based on the natural environment and construction disturbances in different regions, this model can determine suitable types of trees, shrubs and herbs for planting, as well as the corresponding ecological restoration technologies needed.

Managers should pay attention to the multiple types of data generated in different stages of megaproject and identify the internal relationships between these multi-source heterogeneous data, which provides a decision-making basis for complex management decisions. The coupling between ecological restoration technologies and restoration plant species is also an important factor in improving the efficiency of ecological compensation.

Unlike previous studies, which have selected a typical section of a railway for specialized analysis, the complex decision-making model for ecological restoration proposed in this research has wider geographical applicability and can better meet the diverse ecological restoration needs of railway projects that span large regions.

Classification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.

This work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.

Extensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.

MBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

The digitalization of archival management has rapidly developed with the maturation of digital technology. With data's exponential growth, archival resources have transitioned from single modalities, such as text, images, audio and video, to integrated multimodal forms. This paper identifies key trends, gaps and areas of focus in the field. Furthermore, it proposes a theoretical organizational framework based on deep learning to address the challenges of managing archives in the era of big data.

Via a comprehensive systematic literature review, the authors investigate the field of multimodal archive resource organization and the application of deep learning techniques in archive organization. A systematic search and filtering process is conducted to identify relevant articles, which are then summarized, discussed and analyzed to provide a comprehensive understanding of existing literature.

The authors' findings reveal that most research on multimodal archive resources predominantly focuses on aspects related to storage, management and retrieval. Furthermore, the utilization of deep learning techniques in image archive retrieval is increasing, highlighting their potential for enhancing image archive organization practices; however, practical research and implementation remain scarce. The review also underscores gaps in the literature, emphasizing the need for more practical case studies and the application of theoretical concepts in real-world scenarios. In response to these insights, the authors' study proposes an innovative deep learning-based organizational framework. This proposed framework is designed to navigate the complexities inherent in managing multimodal archive resources, representing a significant stride toward more efficient and effective archival practices.

This study comprehensively reviews the existing literature on multimodal archive resources organization. Additionally, a theoretical organizational framework based on deep learning is proposed, offering a novel perspective and solution for further advancements in the field. These insights contribute theoretically and practically, providing valuable knowledge for researchers, practitioners and archivists involved in organizing multimodal archive resources.

As China has pressed ahead with rural revitalization in recent years, its rural financial sector has also developed rapidly and the financial environment has been greatly improved. But compared with urban areas, the rural financial sector makes rather limited contributions to rural economic development for a variety of reasons, including single types of service providers, narrow coverage, and lack of services and products. The underdevelopment of the rural financial system is closely related to the characteristics of its target customers and the economic system. The deficient rural financial credit system, the low level of IT application, the difficulty in data collection and integration, and the insufficient collateral of farmers pose high costs and huge risks for financial institutions when providing credit and other financial services.

In the present case, fintech and financial innovation complement each other: The application of fintech makes innovation possible, and the need for financial development fuels the development of fintech. Leveraging fintech and new business models, MYbank has overcome the main obstacles in the development of rural finance to provide convenient financial services for farmers and rural MSEs. Fintech is the abbreviation of “financial technology.” It can be understood as the combination of finance and technology for easier understanding, but it is more than that. Fintech refers to the innovation of traditional financial products and services with various technologies to improve efficiency and reduce operating costs. The emergence and development of fintech have led to the creation of new business models, applications, and processes, which have triggered major changes in financial markets, financial institutions, and the ways financial services are delivered, and are reshaping the financial landscapes of countries and even the world.

There are three major problems in the development of rural finance: difficult access to data, difficult risk management, and difficult market penetration. In order to gradually remove the obstacles and guarantee sustainable business development, MYbank has created three new business models with the power of fintech: digital inclusive finance at the county level, industrial finance, and platform finance. With these models, MYbank is searching for a “Chinese solution” to the worldwide problem of rural inclusive finance.

Observation of the animal world is an important component of nature surveys. It provides a number of different information concerning aspects such as population sizes, migration directions, feeding sites and many other data. The paper below presents the results from the flights of an unmanned aerial vehicle (UAV) aimed at detecting animals in their natural environment.

The drone used in the research was equipped with RGB and thermal infrared (TIR) cameras. Both cameras, which were mounted on the UAV, were used to take pictures showing the concentration of animals (deer). The overview flights were carried out in the villages of Podlaskie Voivodeship: Szerokie Laki, Bialousy and Sloja. Research flights were made in Bialousy and Sloja. A concentration of deer was photographed during research flights in Sloja. A Durango unmanned platform, equipped with a thermal imaging camera and a Canon RGB camera, was used for research flights. The pictures taken during the flights were used to create orthomaps. A multicopter, equipped with a GoPro camera, was used for overview flights to film the flight locations. A flight control station was also used, consisting of a laptop with MissionPlanner software.

Analysis of the collected images has indicated that environmental, organisational and technical factors influence the quality of the information. Sophisticated observation precision is ensured by the use of high-resolution RGB and TIR cameras. A proper platform for the cameras is an UAV provided with advanced positioning systems, which makes it possible to create high-quality orthomaps of the area. When observing animals, the time of day (temperature contrast), year season (leaf ascent) or flight parameters is important.

The paper introduces the conclusions of the research flights, pointing out useful information for animal observation using UAVs.

The purpose of this study is to explore a new assembly process planning and execution mode to realize rapid response, reduce the labor intensity of assembly workers and improve the assembly efficiency and quality.

Based on the related concepts of digital twin, this paper studies the product assembly planning in digital space, the process execution in physical space and the interaction between digital space and physical space. The assembly process planning is simulated and verified in the digital space to generate three-dimensional visual assembly process specification documents, the implementation of the assembly process specification documents in the physical space is monitored and feed back to revise the assembly process and improve the assembly quality.

Digital twin technology enhances the quality and efficiency of assembly process planning and execution system.

It provides a new perspective for assembly process planning and execution, the architecture, connections and data acquisition approaches of the digital twin-driven framework are proposed in this paper, which is of important theoretical values. What is more, a smart assembly workbench is developed, the specific image classification algorithms are presented in detail too, which is of some industrial application values.

The purpose of this paper is to propose a whole set of methods for underwater target detection, because most underwater objects have small samples, low quality underwater images problems such as detail loss, low contrast and color distortion, and verify the feasibility of the proposed methods through experiments.

The improved RGHS algorithm to enhance the original underwater target image is proposed, and then the YOLOv4 deep learning network for underwater small sample targets detection is improved based on the combination of traditional data expansion method and Mosaic algorithm, expanding the feature extraction capability with SPP (Spatial Pyramid Pooling) module after each feature extraction layer to extract richer feature information.

The experimental results, using the official dataset, reveal a 3.5% increase in average detection accuracy for three types of underwater biological targets compared to the traditional YOLOv4 algorithm. In underwater robot application testing, the proposed method achieves an impressive 94.73% average detection accuracy for the three types of underwater biological targets.

Underwater target detection is an important task for underwater robot application. However, most underwater targets have the characteristics of small samples, and the detection of small sample targets is a comprehensive problem because it is affected by the quality of underwater images. This paper provides a whole set of methods to solve the problems, which is of great significance to the application of underwater robot.