检索结果-内蒙古大学图书馆

3rd World Conference on Intelligent and 3D Technologies, WCI3DT 2024

作者： Liang, Zikang Jin, Runpeng Tian, Hongwei Electronics and Information Engineering Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China

ISBN: (纸本)9789819791231

remote sensing image (RS) classification has a broad range of potential applications in various fields. However, remotely sensed images comprise various land cover elements arranged in intricate spatial patterns, presenting a challenge for accurate recognition. Fortunately, breakthroughs in deep learning techniques brought new opportunities for revolutionizing RS image processing. The convolutional neural network (CNN), as a deep learning technique, has garnered considerable attention in recent years, particularly for its widespread application in remote-sensing image scene classification. Recent advancements have demonstrated its effectiveness in this domain. This study uses CNN as the basis for the land-use scene classification task. We chose the UC-Merced dataset as the experimental object, which contains 21 different categories of land-use scene images. Then, we leverage a modified version of the ResNet50 model to overcome the feature degradation problem in the deep learning process. The experimental results show that ResNet50 with transfer learning exhibits the best performance in the land-use scene classification task, and its accuracy (95.29% (±0.66%)), precision (95.35% (±0.68%)), F1-score (95.23% (±0.67%)), and Kappa coefficient (95.05% (±0.70%)) are all better than the other models. In conclusion, this study serves as a valuable reference for selecting deep learning models for land-use scene classification tasks and offers insightful guidance for future research and applications in related domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

3DRRDB: Super Resolution of Multiple remote sensing images using 3D Residual in Residual Dense Blocks

3DRRDB: Super Resolution of Multiple Remote Sensing Images u...

引用

IEEE/CVF Conference on Computer Vision and pattern recognition (CVPR)

作者： Ramzy Ibrahim, Mohamed Benavente, Robert Lumbreras, Felipe Ponsa, Daniel Arab Acad Sci & Technol Comp Engn Dept Alexandria Egypt Univ Autonoma Barcelona Dept Comp Sci Barcelona Spain Comp Vis Ctr Campus UAB Barcelona Spain

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The rapid advancement of Deep Convolutional Neural Networks helped in solving many remote sensing problems, especially the problems of super-resolution. However, most state-of-the-art methods focus more on Single image Super-Resolution neglecting Multi-image Super-Resolution. In this work, a new proposed 3D Residual in Residual Dense Blocks model (3DRRDB) focuses on remote sensing Multi-image Super-Resolution for two different single spectral bands. The proposed 3DRRDB model explores the idea of 3D convolution layers in deeply connected Dense Blocks and the effect of local and global residual connections with residual scaling in Multi-image Super-Resolution. The model tested on the Proba-V challenge dataset shows a significant improvement above the current state-of-the-art models scoring a Corrected Peak Signal to Noise Ratio (cPSNR) of 48.79 dB and 50.83 dB for Near Infrared (NIR) and RED Bands respectively. Moreover, the proposed 3DRRDB model scores a Corrected Structural Similarity Index Measure (cSSIM) of 0.9865 and 0.9909 for NIR and RED bands respectively.

关键词： Training Solid modeling Three-dimensional displays PSNR Convolution Superresolution pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Fifth Symposium on pattern recognition and Applications, SPRA 2024

Fifth Symposium on Pattern Recognition and Applications, SPR...

引用

5th Symposium on pattern recognition and Applications, SPRA 2024

ISBN: (纸本)9781510688797

The proceedings contain 18 papers. The topics discussed include: generalization of Brady-Yong algorithm for fast Hough transform to arbitrary image size;leveraging machine learning to predict factors that drive successful basketball team formation;real-time reconstruction on Micro-CT setup;stability of artificial intelligence methods in computed tomography metal artifacts reduction task;orthotropic alignment for X-ray computed tomography images;X-ray computed tomography traps and challenges for deep learning scientist;denoising diffusion probabilistic model for accurate super-resolution in landslide and debris flow disaster remote sensing images;and trajectory refinement in SLAM: the impact of Adam, AdamW, and SGD with momentum.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Color Texture Analysis: A Survey

引用

IEEE ACCESS 2022年 10卷 107993-108003页

作者： Humeau-Heurtier, Anne Univ Angers LARIS SFR MATHSTIC F-49000 Angers France

In the field of image processing, texture features and color are fundamental visual cue with complementary roles. They are used in many applications and in a large variety of areas such as quality control, content-based image retrieval, remote sensing, industrial inspection, surface inspection, object recognition, and medical image analysis. For this purpose, a large number of algorithms have been proposed for texture feature extraction. Some of them are dedicated to gray-scale images while others aim at processing both color and texture. It has been shown that, for many cases, the use of color improves the performance of gray level texture classification. This paper provides a comprehensive survey of the texture feature extraction methods that consider both texture and color information. We propose a categorization of these methods into seven classes, two of them being very recent. For each method, we present the concept, the advantages and drawbacks, and we give examples of application.

关键词： image color analysis Histograms Feature extraction Colored noise Visualization Lighting Color Chrominance classification color texture feature extraction image processing image synthesis luminance segmentation shape from texture texture

来源：评论

学校读者我要写书评

暂无评论

基于自适应非局部模式一致性的多模态遥感影像变化检测方法

引用

遥感学报 2024年第12期28卷 3197-3212页

作者：韩特汤玉奇陈玉增张芳艳杨欣邹滨冯徽徽中南大学地球科学与信息物理学院长沙410083 中南大学有色金属成矿预测与地质环境监测教育部重点实验室长沙410083 宁夏大学前沿交叉学院中卫755000

亚热带地区环境复杂,自然灾害频发。多模态遥感影像变化检测可在监测其环境变化与灾害现象中发挥重要作用,已成为当下遥感影像处理的研究热点。针对现有方法存在的目标空间结构特征和影像变化信息利用不足的问题,本文假设地物变化将导... 详细信息

亚热带地区环境复杂,自然灾害频发。多模态遥感影像变化检测可在监测其环境变化与灾害现象中发挥重要作用,已成为当下遥感影像处理的研究热点。针对现有方法存在的目标空间结构特征和影像变化信息利用不足的问题,本文假设地物变化将导致对应影像区域的空间结构特征变化,提出了一种基于自适应非局部模式一致性ANLPC(Adaptive Non-local pattern Consistency)的多模态遥感影像变化检测方法。该方法通过度量多模态影像的空间结构变化提取影像变化信息。首先利用块相似性构建多模态影像的自适应非局部模式,实现空间结构特征表达;然后通过前/后向模式映射度量其与另一时相影像的空间结构差异;最后融合前/后向变化强度图的频率域信息获取鲁棒的变化强度图,并通过阈值分割得到二值变化检测图。本文采用4组多模态遥感影像数据集(两组光学—SAR(Synthetic Aperture Radar)数据集,两组光学—LiDAR数据集)和两组单模态遥感影像数据集(一组光学影像数据集,一组SAR影像数据集)验证了本文方法的有效性。相对于现有方法,本文方法在6组数据集中的卡帕系数KC平均至少提升17.28%。

关键词：遥感多模态影像变化检测结构特征自适应非局部模式模式映射影像融合

来源：评论

学校读者我要写书评

暂无评论

remote sensing Few-shot Object Detection Using Adaptive Feature Modification and Gaussian Dynamic Dilated Convolution 16

Remote Sensing Few-shot Object Detection Using Adaptive Feat...

引用

2024 16th International Conference on Graphics and image processing, ICGIP 2024

作者： Zhiwei, Zhang Jiangtao, Wang Penglei, Chen Cheng, He School of Physics and Electronic Information Huaibei Normal University Anhui Province Huaibei City China Anhui Province Key Laboratory of Intelligent Computing and Applications Anhui Province Huaibei City China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

Object detection in remote sensing images relies on a large amount of annotated data for training, but adequately annotating novel classes is difficult. Few-shot object detection(FSOD) address this problem by fine-tuning on finitely annotated novel classes, this results in its within-class variation being limited, making it difficult to adequately fit the within-class distribution. In order to alleviate this problem, this paper proposed a few-shot object detection method in remote sensing based on adaptive feature modification and guided by Gaussian dynamic dilated convolution. Firstly, in view of the difficulty of novel classes recognition, an adaptive feature modification algorithm is proposed. By using the characteristics of the two-branch network architecture of meta-learning itself, the support features are integrated into the query feature extraction network as convolutional bias to adaptively modify the query features. Secondly, in order to simulate intra-class variation of noise (feature perturbation caused by noise in the foreground), the backbone network weights were reparameterized to make them fit Gaussian distribution variables during fine-tuning, and the feature perturbation was achieved with parameter variation. Finally, in order to simulate intra-class scale variation (different foreground sizes), the convolution is changed into a dynamic dilation convolution, and different dilation rates are used to replace feature scale variation. Extensive experiments on two widely used remote sensing datasets (NWPU.V2, dior) demonstrate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Ship and Course Detection in remote sensing images Based on Key-Point Extraction

Ship and Course Detection in Remote Sensing Images Based on ...

引用

2023 International Conference on Algorithm, Imaging processing, and Machine Vision, AIPMV 2023

作者： Zhang, Tao Yang, Xiaogang Lu, Ruitao Li, Qi Xia, Wenxin Su, Shuang Tang, Bin Xi'an Research Institute of High Technology Xi'an710025 China

ISBN: (纸本)9781510672444

remote sensing image ship target detection and course discrimination is one of the important supports for building a maritime power. Since ship target in remote sensing images are generally in strips, the IOU score is very sensitive to the angle of bounding box. Moreover, the angle of the ship is a periodic function, this discontinuity will cause performance degeneration. Meanwhile, methods generally use oriented bounding boxes as anchors to handle rotated ship target and thus introduce excessive hyper-parameters such as box size, aspect ratios. Aiming at the problem of complex calculation of anchor frame traversal mechanism and discontinuity of angle regression caused by increasing angle attribute in ship target detection of remote sensing image, a ship target heading detection method based on ship head point is proposed. The discontinuous angle regression problem is transformed into a continuous key point estimation problem, and the ship target detection and heading recognition are unified. Second, CA attention mechanism is added to the feature extraction network to enhance the attention to the ship target and predict the center point of the ship target. The offset and target width at the center point are regressed. Then, return the heading point and offset to obtain the accurate heading point position. Next, the rotation angle of the ship is determined according to the coordinates of the center point and the ship head point. Combined with the predicted width and height of the ship, the rotation frame detection of the ship target is completed. Finally, the center point and the bow point are connected to determine the course of the ship target. The effectiveness of the proposed method is verified on the RFUE and open source HRSC2016 datasets, respectively, and it also has good robustness in complex environments. © 2024 SPIE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Exploring Applications of Convolutional Neural Networks in Analyzing Multispectral Satellite imagery: A Systematic Review

引用

BIG DATA MINING AND ANALYTICS 2025年第2期8卷 407-429页

作者： Ivanda, Antonia Seric, Ljiljana Braovic, Maja Univ Split Fac Elect Engn Mech Engn & Naval Architecture Dept Elect & Comp Sci Split 21000 Croatia

remote sensing is of great importance for analyzing and studying various phenomena occurrence and development on Earth. Today is possible to extract features specific to various fields of application with the application of modern machine learning techniques, such as Convolutional Neural Networks (CNN) on MultiSpectral images (MSI). This systematic review examines the application of 1D-, 2D-, 3D-, and 4D-CNNs to MSI, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. This review addresses three Research Questions (RQ): RQ1: "In which application domains different CNN models have been successfully applied for processing MSI data?", RQ2: "What are the commonly utilized MSI datasets for training CNN models in the context of processing multispectral satellite imagery?", and RQ3: "How does the degree of CNN complexity impact the performance of classification, regression or segmentation tasks for multispectral satellite imagery?". Publications are selected from three databases, Web of Science, IEEE Xplore, and Scopus. Based on the obtained results, the main conclusions are: (1) The majority of studies are applied in the field of agriculture and are using Sentinel-2 satellite data;(2) Publications implementing 1D-, 2D-, and 3D-CNNs mostly utilize classification. For 4D-CNN, there are limited number of studies, and all of them use segmentation;(3) This study shows that 2D-CNNs prevail in all application domains, but 3D-CNNs prove to be better for spatio-temporal pattern recognition, more specifically in agricultural and environmental monitoring applications. 1D-CNNs are less common compared to 2D-CNNs and 3D-CNNs, but they show good performance in spectral analysis tasks. 4D-CNNs are more complex and still underutilized, but they have potential for complex data analysis. More details about metrics according to each CNN are provided in the text and supplementary files, offering a comprehensive overview of the evaluation metrics

关键词： remote sensing MultiSpectral images (MSI) MultiSpectral images (MSI) satellite images satellite images Convolutional Neural Networks (CNN) Convolutional Neural Networks (CNN) machine learning machine learning classification classification regression regression segmentation segmentation segmentation

来源：评论

学校读者我要写书评

暂无评论

Toward robust pattern similarity metric for distributed model evaluation

引用

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT 2024年第10期38卷 4007-4025页

作者： Yorulmaz, Eymen Berkay Kartal, Elif Demirel, Mehmet Cuneyd Istanbul Tech Univ Dept Civil Engn TR-34467 Istanbul Turkiye

SPAtial EFficiency (SPAEF) metric is one of the most thoroughly used metrics in hydrologic community. In this study, our aim is to improve SPAEF by replacing the histogram match component with other statistical indices, i.e. kurtosis and earth mover's distance, or by adding a fourth or fifth component such as kurtosis and skewness. The existing spatial metrics i.e. SPAtial efficiency (SPAEF), structural similarity (SSIM) and spatial pattern efficiency metric (SPEM) were compared with newly proposed metrics to assess their converging performance. The mesoscale hydrologic model (mHM) of the Moselle River is used to simulate streamflow (Q) and actual evapotranspiration (AET). The two-source energy balance AET during the growing season is used as monthly reference maps to calculate the spatial performance of the model. The moderate resolution imaging spectroradiometer based leaf area index is utilized by the mHM via pedo-transfer functions and multi-scale parameter regionalization approach to scale the potential ET. In addition to the real monthly AET maps, we also tested these metrics using a synthetic true AET map simulated with a known parameter set for a randomly selected day. The results demonstrate that the newly developed four-component metric i.e. SPAtial Hybrid 4 (SPAH4) slightly outperforms conventional three-component metric i.e. SPAEF (3% better). However, SPAH4 significantly outperforms the other existing metrics i.e. 40% better than SSIM and 50% better than SPEM. We believe that other fields such as remote sensing, change detection, function space optimization and image processing can also benefit from SPAH4.

关键词： mHM Model calibration Spatial pattern SPAEF MODIS TSEB

来源：评论

学校读者我要写书评

暂无评论

RSNet: The Search for remote sensing Deep Neural Networks in recognition Tasks

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2021年第3期59卷 2520-2534页

作者： Wang, Junjue Zhong, Yanfei Zheng, Zhuo Ma, Ailong Zhang, Liangpei Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China Wuhan Univ Hubei Prov Engn Res Ctr Nat Resources Remote Sens Wuhan 430079 Peoples R China

Deep learning algorithms, especially convolutional neural networks (CNNs), have recently emerged as a dominant paradigm for high spatial resolution remote sensing (HRS) image recognition. A large amount of CNNs have already been successfully applied to various HRS recognition tasks, such as land-cover classification and scene classification. However, they are often modifications of the existing CNNs derived from natural image processing, in which the network architecture is inherited without consideration of the complexity and specificity of HRS images. In this article, the remote sensing deep neural network (RSNet) framework is proposed using an automatically search strategy to find the appropriate network architecture for HRS image recognition tasks. In RSNet, the hierarchical search space is first designed to include module- and transition-level spaces. The module-level space defines the basic structure block, where a series of lightweight operations as candidates, including depthwise separable convolutions, is proposed to ensure the efficiency. The transition-level space controls the spatial resolution transformations of the features. In the hierarchical search space, a gradient-based search strategy is used to find the appropriate architecture. In RSNet, the task-driven architecture training process can acquire the optimal model parameters of the switchable recognition module for HRS image recognition tasks. The experimental results obtained using four benchmark data sets for land-cover classification and scene classification tasks demonstrate that the searched RSNet can achieve a satisfactory accuracy with a high computational efficiency and, hence, provides an effective option for the processing of HRS imagery.

关键词： High-resolution remote sensing image remote sensing recognition search for convolutional neural networks (CNNs)

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：