检索结果-内蒙古大学图书馆

Attention-based multi-image super-resolution reconstruction for remote sensing

signal image AND vIDEO processing 2025年第6期19卷 1-9页

作者： Ding, Xueyan Wang, Wenshan Zhang, Bingbing Zhang, Jianxin Dalian Minzu Univ Sch Comp Sci & Engn 31 Jinshi Rd Dalian 116000 Liaoning Peoples R China Dalian Minzu Univ Res Ctr Multimodal Informat Percept & Intelligent 31 Jinshi Rd Dalian 116000 Liaoning Peoples R China

Multi-image Super-Resolution (MISR) reconstructs high-resolution images from multiple satellite-acquired low-resolution images, emerging as a key technique in remote sensing. However, image sequences collected by satellites usually have diverse views and extended time spans, making the integration of multiple low-resolution images into a single high-resolution image with intricate details a challenging problem. In this paper, we propose AttMISR, an attention-based multi-image super-resolution network for remote sensing. AttMISR is composed of three key modules: a feature extraction module utilizing residual dynamic convolution blocks, a hybrid non-local feature fusion module, and a multi-attention-based image reconstruction module. The feature extraction module integrates the residual structure with dynamic convolution to efficiently capture complex features and textures in remote sensing images, while the hybrid non-local feature fusion module optimizes feature aggregation across multiple remote sensing images by calculating both cross-correlation and non-cross-correlation features. Moreover, a coordinate-window attention mechanism is proposed to construct the multi-attention-based image reconstruction module, enabling more precise reconstruction. Comprehensive experiments conducted on PROBA-v Kelvin dataset demonstrate the superiority of the proposed method.

关键词： Deep learning Multi-image super-resolution remote sensing Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

MvITP: MULTI-vIEW image-TEXT PERCEPTION FOR FEW-SHOT remote sensing image CLASSIFICATION 49

MVITP: MULTI-VIEW IMAGE-TEXT PERCEPTION FOR FEW-SHOT REMOTE ...

引用

49th IEEE International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yang, Chen Liu, Tongtong Jiao, Didi Li, Wenhui Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Few-shot learning has been extensively applied in current remote sensing image classification, enabling rapid identification of new classes by leveraging prior knowledge effectively. However, current methods mainly rely on image modality to address the issue of low intra-class similarity and high interclass similarity, while the utilization of multimodal methods in remote sensing tasks remains largely unexplored. Therefore, we propose a novel framework for few-shot remote sensing image classification, named multi-view image-text perception (MvITP). Specifically, it leverages maximum mutual information across multiple views to train an image encoder and generate image features. A text encoder is employed to generate text features. Next, we introduce a multimodal fusion encoder to capture the similarity between image features and text features. Finally, class predictions are further made by computing the similarity between the support set and the query set. We conduct experiments on three remote sensing datasets, demonstrating the outstanding performance of MvITP.

关键词： Maximum mutual information multimodal fusion few-shot learning remote sensing image classification

来源：评论

学校读者我要写书评

暂无评论

Enhanced YOLOv8 framework for precision vehicle detection in high-resolution remote sensing images

引用

signal image AND vIDEO processing 2025年第3期19卷 1-10页

作者： Shao, Zhaowei He, Kunyu Yuan, Baohua Xu, Sheng Nanjing Forestry Univ Coll Informat Sci & Technol & Artificial Intellige Nanjing Jiangsu Peoples R China Changzhou Univ Coll Informat Sci & Engn Changzhou Jiangsu Peoples R China

vehicle detection in high-resolution remote sensing imagery faces challenges such as varying scales, complex backgrounds, and high intra-class variability. We propose an enhanced YOLOv8 framework, incorporating three key advancements: the Adaptive Feature Pyramid Network (AFPN), Omni-Dimensional Convolution (ODConv), and a Slim Neck with Generalized Shuffle Convolution (GSConv). These enhancements improve vehicle detection accuracy, computational efficiency, and visual AI capabilities for applications such as computer animation and virtual worlds. Our model achieves a Mean Average Precision (mAP) of 0.7153, representing a 4.99% improvement over the baseline YOLOv8. Precision and recall increase to 0.9233 and 0.9329, respectively, while box loss is reduced from 1.213 to 1.054. This framework supports real-time surveillance, traffic monitoring, and urban planning. The NEPU-OWOD v2.0 dataset, used for evaluation, includes high-resolution images from multiple regions and seasons, along with diverse annotations and augmentations. Our modular approach allows for separate assessments of each enhancement. The dataset and source code are available for future research and development at (https://***/10.5281/zenodo.13075939).

关键词： Object detection High-resolution remote sensing imagery Multi-scale feature representation Real-time processing

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Scene Classification Based on Convolutional Neural Networks

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第9期49卷 45-54页

作者： Liu, Yumei Chongqing City Vocational College Chongqing402160 China

remote sensing image classification, a specific application of digital signal technology in remote sensing, addresses the challenge of effectively processing and categorizing remote sensing imagery. This research proposes a neural network (CNN)-based approach for remote sensing image classification, aiming to overcome the limitation of single-feature inadequacy. The method involves making a multi-site and multi-combination strategy that effectively combines spectral features, spatial patterns, and more remote sensing images as vectors or matrices. We then train the CNN model based on the length of the data. Experimental results demonstrate a significant reduction of approximately 80% in the training time for the PCA-free CNN (SST) method after implementing the PCA transformation. This reduction not only expedites the training process but also enhances overall accuracy by approximately 3.49. The CNN-style network model contributes to efficiency improvement. Larger training models increase the number of models to be taught, slowing down the training process and prolonging learning times. The incorporation of multi-location and multi-combination strategies accelerates tracking speed and enhances the classification accuracy of remote sensing images. Comparative analysis indicates that, in contrast to other classification methods, CNN achieves superior classification performance, demonstrating its capability for increased categorization and improved accuracy. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multi-Source remote sensing image Matching Approach Based on Texture-Enhanced Region Features

A Multi-Source Remote Sensing Image Matching Approach Based ...

引用

9th International conference on signal and image processing (ICSIP)

作者： Zhao Zilu Wang Feng You Hongjian Li Peifeng Zhang Tingtao Chinese Acad Sci Aerosp Informat Res Inst Beijing Peoples R China Key Lab Technol Geospatial Informat Proc & Applic Beijing Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing Peoples R China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350920

Multi-source remote sensing image matching is crucial for remote sensing technology applications. However, the variations in factors such as grayscale, perspective, and sensors between multi-source images present certain challenges for image matching. In response to the challenges in matching multi-source remote sensing images, a matching method based on texture-enhanced region features is proposed. Initially, Gabor filters and the gray-level co-occurrence matrix (GLCM) are used to obtain the texture energy maps, followed by the extraction of maximally stable extremal regions (MSER) on the texture energy maps to acquire region features. Subsequently, the contour descriptors of the features are computed using Fourier descriptors. Finally, feature matching and refinement of the matching results are conducted in conjunction with the fast sample consensus (FSC). We conducted experimental region feature matching on multiple pairs of multi-source remote sensing images, and the results validate the effectiveness of our method.

关键词： feature region matching remote image match maximally stable extremal regions (MSER) Fourier descriptors

来源：评论

学校读者我要写书评

暂无评论

UNSUPERvISED remote sensing HAZE REMOvAL BASED ON SALIENCY-GUIDED TRANSMISSION REFINEMENT 49

UNSUPERVISED REMOTE SENSING HAZE REMOVAL BASED ON SALIENCY-G...

引用

49th IEEE International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Zheng, Ruohui Zhang, Libao Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Haze causes information loss and quality degradation in remote sensing images. Unsupervised learning-based dehazing methods aim to reduce reliance on paired hazy images and their labels. However, complex mapping relationships often increase the difficulty in network convergence, resulting in color distortion and loss of texture details in remote sensing images. To address these issues, we propose an unsupervised haze removal method based on saliency-guided transmission refinement for remote sensing images. Firstly, we introduce a saliency-guided transmission refinement method, which decomposes and recombines two transmission maps obtained under different conditions, guided by saliency information. Secondly, we propose a loss function comprising energy loss and texture loss. The energy loss provides an energy reference based on the coarse transmission estimation, while the texture loss enhances the preservation of texture details. Experimental results demonstrate that our method achieves comparable performance to several supervised methods.

关键词： image restoration image enhancement remote sensing dehazing unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

SEMANTIC SEGMENTATION FOR MULTI-SCENE remote sensing imageS WITH NOISY LABELS BASED ON UNCERTAINTY PERCEPTION 49

SEMANTIC SEGMENTATION FOR MULTI-SCENE REMOTE SENSING IMAGES ...

引用

49th IEEE International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Lyu, Xinran Zhang, Libao Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China

ISBN: (纸本)9798350344868;9798350344851

As the annotation of remote sensing images requires domain expertise, it is difficult to construct a large-scale and accurate annotated dataset. image-level annotation data learning has become a research hotspot. In addition, due to the difficulty in avoiding mislabeling, label noise cleaning is also a concern. In this paper, a semantic segmentation method for remote sensing images based on uncertainty perception with noisy labels is proposed. The main contributions are three-fold. First, a label cleaning method based on iterative learning is presented to handle noise labels such as missing or incorrect annotations. Second, a two-stage semantic segmentation model is proposed for image-level annotation, which eliminates the need for post-processing steps during testing. Lastly, a complementary uncertainty perception function is introduced to improve the utilization of dataset features and enhance the accuracy of segmentation. The effectiveness of this method was verified through comprehensive evaluation with 7 models on four datasets.

关键词： remote sensing weak annotation label noise cleaning iterative learning uncertainty perception

来源：评论

学校读者我要写书评

暂无评论

ENCODER-MINIMAL AND DECODER-MINIMAL FRAMEWORK FOR remote sensing image DEHAZING 49

ENCODER-MINIMAL AND DECODER-MINIMAL FRAMEWORK FOR REMOTE SEN...

引用

49th IEEE International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Wen, Yuanbo Gao, Tao Li, Ziqi Zhang, Jing Chen, Ting Changan Univ Sch Informat Engn Xian Peoples R China Australian Natl Univ Coll Engn & Comp Sci Canberra ACT Australia

ISBN: (纸本)9798350344868;9798350344851

Haze obscures remote sensing images, hindering valuable information extraction. To this end, we propose RSHazeNet, an encoder-minimal and decoder-minimal framework for efficient remote sensing image dehazing. Specifically, regarding the process of merging features within the same level, we develop an innovative module called intra-level transposed fusion module (ITFM). This module employs adaptive transposed self-attention to capture comprehensive context-aware information, facilitating the robust context-aware feature fusion. Meanwhile, we present a cross-level multi-view interaction module (CMIM) to enable effective interactions between features from various levels, mitigating the loss of information due to the repeated sampling operations. In addition, we propose a multi-view progressive extraction block (MPEB) that partitions the features into four distinct components and employs convolution with varying kernel sizes, groups, and dilation factors to facilitate view-progressive feature learning. Extensive experiments demonstrate the superiority of our proposed RSHazeNet. We release the source code and all pre-trained models at https://***/chdwyb/RSHazeNet.

关键词： image dehazing remote sensing image computer vision efficient network

来源：评论

学校读者我要写书评

暂无评论

visual Cardiac signal Classifiers: A Deep Learning Classification Approach for Heart signal Estimation From video

引用

IEEE ACCESS 2024年 12卷 144377-144394页

作者： Moustafa, Mohamed Farooq, Muhammad Ali Elrasad, Amr Lemley, Joseph Corcoran, Peter Univ Galway Dept Elect & Elect Engn Imaging Lab C3I Galway H91 TK33 Ireland FotoNation Sensing Team Galway H91 V0TX Ireland

Heart rate is a crucial metric in health monitoring. Traditional computer vision solutions estimate cardiac signals by detecting physical manifestations of heartbeats, such as facial discoloration caused by blood oxygenation changes, from subject videos using regression methods. As continuous signals are more complex and expensive to de-noise, this study introduces an alternative approach, employing end-to-end classification models to remotely derive a discrete representation of cardiac signals from face videos. These visual cardiac signal classifiers are trained on discretized cardiac signals, a novel pre-processing method with limited precedent in health monitoring literature. Consequently, various methods to convert continuous cardiac signals into binary form are presented, and their impact on training is evaluated. An implementation of this approach, the temporal shift convolutional attention binary classifier, is presented using the regression-based convolutional attention network architecture. The classifier and a baseline regression model are trained and tested using publicly available and locally collected datasets designed for heart signal detection from face video. The model performance is then assessed based on the heart rate error from the extracted cardiac signals. Results show the proposed method outperforms the baseline on the UBFC-rPPG dataset, reducing cross-dataset root mean square error from 2.33 to 1.63 beats per minute. However, both models struggled to generalize to the PURE dataset, with root mean square errors of 12.40 and 16.29 beats per minute, respectively. Additionally, the proposed approach reduces the computational complexity of model output post-processing, enhancing its suitability for real-time applications and deployment on systems with restricted resources.

关键词： Convolutional neural networks Heart rate Computer vision Training Estimation remote sensing visualization Standards Monitoring Feature extraction Deep learning Biomedical signal processing Photoplethysmography deep learning image classification remote monitoring remote sensing biomedical signal processing heart rate photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

TWO-STAGE TRIPLETNET: LIGHT WEIGHT remote sensing SCENE CLASSIFICATION 31

TWO-STAGE TRIPLETNET: LIGHT WEIGHT REMOTE SENSING SCENE CLAS...

引用

2024 International conference on image processing

作者： Hu, Xianbin Wu, Wei Li, Zhu Luo, Xueliang Chen, Zhengfeng Xidian Univ State Key Lab Integrated Serv Networks Xian Peoples R China Univ Missouri Kansas City Dept Comp Sci Elect Engn Kansas City MO USA

ISBN: (纸本)9798350349405;9798350349399

remote sensing scene classification (RSSC) seeks to allocate correct semantic labels to remote sensing images. Recently, numerous algorithms have made significant contributions to enhancing the accuracy of RSSC. However, models with high parameters and computational complexity still dominate. To address this issue, we propose a lightweight network architecture, namely Two-Stage TripletNet. In this proposed algorithm, we employ a two-stage optimizing strategy involving label optimization and loss function optimization. First, a KD-tree generated by remote sensing image features is utilized to produce visual labels. Secondly, we establish the triplet sampling method based on the visual and semantic labels of the images. Finally, the triplet loss and cross-entropy loss are jointly applied to train our model. Experimental results on mainstream datasets demonstrate the effectiveness of our proposed framework. Meanwhile, the two-stage optimizing strategy renders our model more competitive compared to other state-of-the-art algorithms.

关键词： remote sensing Scene Classification Classification Accuracy Model Complexity visual Label Triplet Loss

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：