检索结果-内蒙古大学图书馆

Efficient distributed matrix for resolving computational intensity in remote sensing

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2025年 166卷

作者： Zou, Weitao Li, Wei Wang, Zeyu Pei, Jiaming Lou, Tongtong Chen, Guangsheng Jing, Weipeng Zomaya, Albert Y. Northeast Forestry Univ Coll Comp & Control Engn 26 Hexing Rd Harbin 150040 Peoples R China Univ Sydney Ctr Distributed & High Performance Comp Sch Comp Sci Sydney NSW 2006 Australia

remote sensing analysis is a dominant yet time-consuming part of geospatial applications. The performance can be optimized based on distributed computing, but current systems still face significant challenges. Firstly, the spatial characteristics of remote sensing data lead to an uneven distribution of computational intensity (CIT), which characterizes computing loads, including computation and IO, indifferent spatial domains. Secondly, it is hard to achieve load-balancing without introducing new computational costs, thus increasing the CIT and reducing the overall performance. Therefore, resolving CIT by decreasing and balancing it is an important research issue for distributed remote sensing computing. This paper proposes LBM-RS, an efficient distributed framework based on load-balancing matrix computing for remote sensing. It implements remote sensing applications based on the distributed matrix, representing the algorithms with a matrix computation and constructing multi-dimensional spatial domains to model computational costs for matrix operation tasks. It resolves the CIT with the minimum computation load and dynamic spatial domain decomposition strategy to support global load balancing. We also exploit the IO efficiency from the task staging strategy and the cache-aware memory structure for remote sensing data. In this way, it can reduce the bandwidth burden and memory access frequency, thus decreasing the overall CIT. Finally, we evaluate the proposed approach on both real and synthetic datasets, and the results demonstrate significant advantages in computation and communication efficiency compared to the benchmarks.

关键词： remote sensing data Computational intensity Load balancing Distributed framework Distributed matrix

来源：评论

学校读者我要写书评

暂无评论

high-performance On-Orbit Intelligent computing and Real-Time Services for remote sensing Satellites Based on Large-Scale computing Power in Space

引用

IEEE Access 2025年 13卷 92114-92133页

作者： Guoping Wang Gang Wan Zhijuan Su Yang Wang Yutong Jia Gong Li Shi Liang Department of Surveying and Mapping and Space Environment Space Engineering University Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Key Laboratory of Target Cognition and Application Technology Beijing China Beijing Institute of Space Mechanics and Electricity Beijing China School of Artificial Intelligence Xidian University Xi’an China

The rapid advancement in Earth observation systems and satellite networks driven by commercial space has led to a significant increase in the number of remote sensing satellites, thereby establishing the groundwork for all-weather, continuous, cluster-collaborative observation. Following anti-irradiation hardening measures, low-cost commercial off-the-shelf (COTS) devices are effectively operated within intricate space environments, leading to substantial enhancements of the on-orbit computing capabilities of individual satellites. The onboard-distributed processing framework can be leveraged to fully utilize wide-area scattered space computing resources; accordingly, it is possible to automatically establish a network of neighboring satellites through inter-satellite communication links to construct a spatially distributed and computationally cooperative cloud computing environment in space. This enables the sharing of space computing resources and facilitates satellite-based mission coordination, reducing reliance on ground-based remote sensing satellite services while enhancing the response efficiency of remote sensing application services. The present paper provides a comprehensive review of the current development status, existing challenges, and problems faced by space-based, on-orbit remote sensing processing platforms and onboard intelligent processing algorithms; we start with the immediate application requirements of the remote sensing satellites used in in-orbit processing. In view of the anticipated surge in large-scale computing resources in space, a distributed processing architecture for remote sensing satellite data, based on large-scale onboard computing power, is constructed. The architecture is designed in detail, with attention paid to the physical architecture, the software architecture, the workflow, and the key technologies. Finally, three real-time service scenarios that align with the construction content of an ultra-low-orbit satellite cons

关键词： Satellites remote sensing Space vehicles Real-time systems Satellite broadcasting Satellite constellations Earth Software Hyperspectral imaging Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Brain-Inspired Online Adaptation for remote sensing With Spiking Neural Network

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Duan, Dexin Liu, Peilin Hui, Bingwei Wen, Fei Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Brain Inspired Applicat Technol Ctr BATC Shanghai 200240 Peoples R China Natl Univ Def Technol ATR Key Lab Sch Elect Sci & Engn Changsha 410073 Peoples R China

On-device computing, or edge computing, is becoming increasingly important for remote sensing, particularly in applications like deep network-based perception on on-orbit satellites and unmanned aerial vehicles (UAVs). In these scenarios, two brain-like capabilities are crucial for remote sensing models: 1) high energy efficiency, allowing the model to operate on edge devices with limited computing resources, and 2) online adaptation, enabling the model to quickly adapt to environmental variations, weather changes, and sensor drift. This work addresses these needs by proposing an online adaptation framework based on spiking neural networks (SNNs) for remote sensing. Starting with a pretrained SNN model, we design an efficient, unsupervised online adaptation algorithm, which adopts an approximation of the backpropagation through time (BPTT) algorithm and only involves forward-in-time computation that significantly reduces the computational complexity of SNN adaptation learning. Besides, we propose an adaptive activation scaling (AAS) scheme to boost online SNN adaptation performance, particularly in low time-steps. Furthermore, for the more challenging remote sensing detection task, we propose a confidence-based instance weighting scheme, which substantially improves adaptation performance in the detection task. To our knowledge, this work is the first to address the online adaptation of SNNs. Extensive experiments on seven benchmark datasets across classification, segmentation, and detection tasks demonstrate that our proposed method significantly outperforms existing domain adaptation and domain generalization approaches under varying weather conditions. The proposed method enables energy-efficient and fast online adaptation on edge devices, and has much potential in applications such as remote perception on on-orbit satellites and UAVs. The code is available at https://***/ThunderDavid/OASNN.

关键词： Adaptation models Neurons Computational modeling remote sensing Brain modeling Satellites Meteorology Energy efficiency Approximation algorithms Sensors Brain-inspired computing neuromorphic computing remote sensing image processing spiking neural network (SNN) unsupervised domain adaptation (UDA)

来源：评论

学校读者我要写书评

暂无评论

CNN-transformer dual branch collaborative model for semantic segmentation of high-resolution remote sensing images

引用

PHOTOGRAMMETRIC RECORD 2025年第189期40卷

作者： Zhu, Xiaotong Peng, Taile Guo, Jia Wang, Hao Cao, Taotao Sch Huaibei Normal Univ Coll Comp Sci & Technol Huaibei Peoples R China

high-resolution remote sensing images play an important role in geological surveys, disaster detection, and other fields. However, highly imbalanced ground target classes and easily confused small ground targets pose significant challenges to the semantic segmentation task. We propose IC-TransUNet, a new dual branch model based on an encoder-decoder structure that fully exploits the advantages of convolutional neural networks and transformers and considers both detailed information and semantic information capture. Specifically, a lightweight CSwin transformer and InceptionNeXt are used as the dual branch backbone of the model. To further improve the model performance, first, we designed the InceptionNeXt-CSwin Transformer Fusion Module (ICFM) and Edge Enhancement Module (EEM) to guide the dual branch backbone to obtain features. Second, a detachable Spatial-channel Attention Fusion Module (SCAFM) is designed to be flexibly inserted into multiple positions of the model. Finally, we designed a decoder with significant performance based on a global local transformer block, SCAFM, and a multilayer perceptron segmentation head. IC-TransUNet achieved highly competitive performance in experiments on the Vaihingen and Potsdam datasets from the International Society for Photogrammetry and remote sensing.

关键词： CNN dual encoder high-resolution remote sensing images semantic segmentation transformer transformer

来源：评论

学校读者我要写书评

暂无评论

HASNet: A Foreground Association-Driven Siamese Network With Hard Sample Optimization for remote sensing Image Change Detection

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Tao, Chao Kuang, Dongsheng Huang, Zhenyang Peng, Chengli Li, Haifeng Cent South Univ Sch Geosci & Info Phys Changsha 410205 Peoples R China

remote sensing change detection (RS-CD) relies on the model's ability to learn features of marked change objects, known as foreground targets. Beyond foreground targets, the background targets are more valuable samples for change detection, such as unlabeled ones, semantically ambiguous ones, pseudo-changes, and non-interesting changes, referred to as hard case samples (HCSs) in this article. There are two additional challenges to learning HCSs: 1) the loss function focusing on the foreground targets with rich labels and ignoring the HCSs in the background, called the imbalance problem and 2) it is difficult for a model to learn the change information of HCSs directly, which is called HCSs missingness. This article proposed a foreground association-driven Siamese network with hard sample optimization (HASNet). To deal with the imbalance problem, we propose an equilibrium optimization loss (EO-loss) function to regulate the optimization focus of the foreground and background, determine the HCSs through the distribution of the loss values, and introduce dynamic weights in the loss term to gradually shift the optimization focus of the loss from the foreground to the background hard cases as the training progresses. To address the HCSs missingness, we propose the scene-foreground association module by using potential remote sensing spatial scene information to model the association between the target of interest in the foreground and the related context to obtain scene embedding to reinforce the feature of hard cases. Experiments on four public datasets with 11 baselines show that HASNet outperforms current state-of-the-art CD methods, particularly in detecting HCSs. The source code is available at https://***/GeoX-Lab/HASNet.

关键词： Change detection foreground-scene association hard case samples (HCSs) hard case samples (HCSs) remote sensing image remote sensing image remote sensing image

来源：评论

学校读者我要写书评

暂无评论

RNAF-YOLO: a model for highlighting difficult-to-detect targets in remote sensing images

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第3期36卷 035405-035405页

作者： Wang, Manyi Gao, Weiwei Fang, Yu Liu, Xintian Jin, Xiaoyi Shanghai Univ Engn Sci Inst Mech & Automot Engn Shanghai 201620 Peoples R China

Challenges like scale variations, shape diversity, complex backgrounds, and sample imbalance in remote sensing images make some targets difficult to detect. Consequently, a model called RNAF-You Only Look Once (YOLO) is proposed, combining a composite convolution module with an Intersection over Union (IoU)-based weighted loss function for remote sensing object detection. A composite convolution module, RepFocalNet, is designed and incorporated into the backbone network to replace the original C2f layer, enhancing multi-scale modeling and feature extraction capabilities in complex backgrounds. Adaptive spatial correlation pyramid attention is introduced after the ninth layer, enhancing sensitivity to subtle features and improving small object detection. Furthermore, Focal Inner Soft IoU is designed to replace the original loss function. Ablation experiments were conducted on the DIOR dataset to verify the effectiveness of each module. Following this, the proposed method was compared with several leading methods to further evaluate its performance. Compared to the YOLOv8 model, RNAF-YOLO improved mAP@50 by 1.5% and increased recall by 3%. Additionally, the classification accuracy for the bridge and vehicle categories increased by 4.2% and 8.9%. Compared to other methods, RNAF-YOLO demonstrates superior performance across multiple classification accuracy metrics. As a consequence, the proposed method demonstrates superior performance in remote sensing object detection, effectively highlighting difficult-to-detect targets.

关键词： YOLOv8 ASCP attention remote sensing object detection DIOR dataset

来源：评论

学校读者我要写书评

暂无评论

Neural Network Based on Dynamic Collaboration of Flows for Temporal Downscaling

引用

remote sensing 2025年第8期17卷 1434-1434页

作者： Wang, Junkai Lin, Lianlei Zhang, Yu Zhang, Zongwei Gao, Sheng Zhao, Hanqing Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China Technol Innovat Ctr Littoral Test Harbin 150001 Peoples R China

Time downscaling is one of the most challenging topics in remote sensing and meteorological data processing. Traditional methods often face the problems of high computing cost and poor generalization ability. The framework interpolation method based on deep learning provides a new idea for the time downscaling of meteorological data. A deep neural network for the time downscaling of multivariate meteorological data is designed in this paper. It estimates the kernel weight and offset vector of each target pixel independently among different meteorological variables and generates output frames guided by the feature space. Compared with other methods, this model can deal with a large range of complex meteorological movements. The 2 h interval downscaling experiments for 2 m temperature, surface pressure, and 1000 hPa specific humidity show that the MAE of the proposed method is reduced by about 14%, 25%, and 18%, respectively, compared with advanced methods such as AdaCof and Zooming Slow-Mo. performance fluctuates very little over time, with an average performance fluctuation of only about 1% across all metrics. Even in the downscaling experiment with a 6 h interval, the proposed model still maintains a leading performance advantage, which indicates that the proposed model has not only good performance and robustness but also excellent scalability and transferability in the downscaling task in the multivariate meteorological field.

关键词： remote sensing data meteorological data time downscaling dynamic collaboration of flows neural network

来源：评论

学校读者我要写书评

暂无评论

CE-CDNet:A Transformer-Based Channel Optimization Approach for Change Detection in remote sensing

引用

Computers, Materials & Continua 2025年第4期83卷 803-822页

作者： Jia Liu Hang Gu Fangmei Liu Hao Chen Zuhe Li Gang Xu Qidong Liu Wei Wang School of Computer Science and Technology Zhengzhou University of Light IndustryZhengzhou450002China Department of Computing Xi’an Jiaotong-Liverpool UniversitySuzhou215123China

In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multiple layers of Transformer blocks,which achieves considerable improvement in capturing variations,but at a rather high computational *** propose a channel-Efficient Change Detection Network(CE-CDNet)to address the problems of high computational cost and imbalanced detection accuracy in remote sensing building change *** adaptive multi-scale feature fusion module(CAMSF)and lightweight Transformer decoder(LTD)are introduced to improve the change detection *** CAMSF module can adaptively fuse multi-scale features to improve the model’s ability to detect building changes in complex *** addition,the LTD module reduces computational costs and maintains high detection accuracy through an optimized self-attention mechanism and dimensionality reduction *** test results on three commonly used remote sensing building change detection data sets show that CE-CDNet can reduce a certain amount of computational overhead while maintaining detection accuracy comparable to existing mainstream models,showing good performance advantages.

关键词： remote sensing change detection attention mechanism channel optimization multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

Research on computer multi feature fusion SVM model based on remote sensing image recognition and low energy system

RESULTS IN ENGINEERING

引用

RESULTS IN ENGINEERING 2025年 26卷

作者： Wu, Yangming Wu, Hao Tang, Xin Lv, Jianwei Zhang, Rufei Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 211106 Peoples R China Nanjing Vocat Inst Transport Technol Sch Elect & Informat Engn Nanjing 211188 Peoples R China Beijing Inst Control & Elect Technol Beijing 100045 Peoples R China

With the development of remote sensing technology, remote sensing image is widely used in environmental monitoring, land use and other fields. However, traditional image recognition methods often face the problems of high consumption of computing resources and slow processing speed, especially in low-energy systems. Therefore, this paper aims to explore a low-energy multi-feature fusion support vector machine (SVM) model based on remote sensing image recognition. The characteristics of remote sensing images and their application requirements in low energy consumption systems are analyzed, and a multi-feature extraction method combining spectral features, texture features and shape features is proposed. Aiming at the limitations of the traditional SVM model in processing high-dimensional data, an optimization algorithm is designed to reduce the computational complexity and improve the recognition accuracy of the model through dimensionality reduction and feature selection. Based on the model, a series of experiments were carried out on a low-energy hardware platform to test its performance in different scenarios. The experimental results show that the proposed multi-feature fusion SVM model has significantly improved recognition accuracy compared with the single feature method, and can effectively control the computing resource consumption, and can realize real-time recognition on low-energy systems.

关键词： remote sensing image recognition Low energy consumption system Computer Multi-feature fusion SVM model

来源：评论

学校读者我要写书评

暂无评论

Small water body extraction in remote sensing with enhanced CNN architecture

引用

APPLIED SOFT computing 2025年 169卷

作者： Farooq, Bazila Manocha, Ankush Lovely Profess Univ Jalandhar 144411 Punjab India Natl Inst Technol Kurukshetra 136118 Haryana India

In climate change, the precise acquisition of data about natural resources is essential and poses a significant difficulty in remote sensing. Identifying water resources has become a key focus in addressing the global issue of water scarcity. Using remote sensing techniques to extract water bodies from satellite images is complex. While Convolutional Neural Networks (CNNs) have shown potential in image segmentation, challenges such as unclear boundaries, the requirement for extensive training data, and a high number of trainable parameters persist. To address these challenges, a CNN architecture called "WaterNet" has been developed by integrating two residual refinement capsules to improve predicted results and ensure continuity in boundary pixels. Incorporating dense layers within the network reduces the total count of trainable parameters, thus alleviating the computational burden. To assess the effectiveness of the proposed method, a comparison was made with several conventional and deep learning approaches. These included the use of NDWI, Unet, Deepunet, Segnet, DeepwaterMap, and Multi-layered Feature Fusion Approach (MFFA). The proposed solution demonstrated superior performance, surpassing all existing approaches, with an outstanding accuracy of 0.97% in extracting water resources from high-resolution satellite imagery. The model is accurate in distinguishing water from other features such as land, ice, clouds, and shadows using sentinel data as input. The uniqueness of this work lies in the development of the "WaterNet" system tailored for water body extraction, showcasing improved accuracy, efficient context transmission, incorporation of dense layers, utilization of residual refinement modules, and addressing the limitations of conventional approaches. These contributions collectively advance remote sensing and deep learning used in the detection of small bodies of water from imagery captured by satellites.

关键词： Computer vision Water resources remote sensing Sentinal Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：