检索结果-内蒙古大学图书馆

7th Chinese Conference on pattern recognition and Computer Vision

作者： Song, Shitao Liu, Ye Su, Jintao Nanjing Univ Posts & Telecommun Sch Automat & Artificial Intelligence Nanjing 210003 Peoples R China

ISBN: (纸本)9789819785049;9789819785056

Vision Mamba (VMamba) has recently attracted great research attention due to its ability to obtain a global receptive field with linear computational complexity. However, similar to Vision Transformer (ViT), due to its mechanism of dividing patches, it also faces the issue of insufficient description ability of local details. To address this issue, we design in this paper a dual-stream network that combines VMamba and CNN, aiming to enable the network to possess both the global receptive field of VMamba and the local detail description capability of CNN. Both of the two characteristics are crucial for remote sensing image semantic segmentation. The two streams are supervised and trained through independent loss functions. On the other hand, to enable sufficient information exchange between the two branches, we introduce an auto-scaling fusion module aiming at bridging the semantic gap between VMamba and CNN. Experiments demonstrate that the method proposed in this paper outperforms state-of-the-art methods on multiple remote sensing semantic segmentation datasets.

关键词： Vision Mamba CNN Auto-scaling Semantic segmentation remote sensing

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Cloud Detection Algorithm Based on Residual Network Module and Pyramid Structure of Dilated Convolution 12

Remote Sensing Image Cloud Detection Algorithm Based on Resi...

引用

SPIE 12th International Symposium on Multispectral image processing and pattern recognition, MIPPR 2023

作者： Chen, Yi Zhu, Ying School of Electrical and Information Engineering Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan430205 China

ISBN: (数字)9781510675001

ISBN: (纸本)9781510674998

Approximately 50% of the Earth's surface is covered by clouds. Optical remote sensing satellites encounter challenges in capturing clear ground images due to the difficulty of visible photoelectric magnetic waves penetrating clouds. Therefore, cloud detection is an essential and basic step in the processing and application of optical satellite remote sensing images. The traditional threshold-based cloud detection methods utilize spectral information of images to set thresholds, which is sensitive and less adaptable to varying imaging conditions. To enhance cloud detection performance, this paper proposes a deep learning method that combines residual network module and pyramid structure of dilated convolution. The method employs an encoder-decoder structure where the residual convolution module replaces conventional convolution kernels, reducing parameter quantity while enhancing feature expression capabilities. Furthermore, a pyramid structure of dilated convolution is introduced between the encoder and decoder to improve the acquisition of global information and reduce misjudgment of cloud pixels. In this work, ablation experiments are conducted to validate the reliability of the proposed network model. To evaluate the effectiveness of the proposed method, GaoFen-1 remote sensing image data was used for experimental verification. The results indicated that compared to traditional methods, the proposed approach achieves satisfactory cloud detection results in various surface types, including barren land, forests, grasslands/crops, and wetlands, while having a smaller model size and parameter quantity. © 2024 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Increase the Coherent processing Interval for SAR Focusing of Maneuvering Ships by Data Resampling

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2024年 62卷 1页

作者： Shi, Shuo Zhang, Heng Deng, Yunkai Ren, Mingshan Chinese Acad Sci Aerosp & Informat Res Inst Dept Space Microwave Remote Sensing Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100039 Peoples R China

Synthetic aperture radar (SAR) is important for marine surveillance. The image resolution of SAR is obtained via coherent integration. However, with increasing coherent processing intervals (CPIs), the focusing quality of maneuvering ships in images will worsen, impacting target recognition. Defocusing is caused mainly by the change in the image projection plane (IPP) of the maneuvering ship and the change in the effective rotation vector (ERV). In this article, an improved inverse SAR (ISAR) method is used to focus the ships in SAR images. First, the factors influencing the instantaneous imaging position are analyzed. Then, a new method based on data resampling for maneuvering ship imaging with a long CPI is proposed. This method consists of two main steps: ERV estimation and data resampling. The change in the ERV is estimated by using the instantaneous imaging position of all the scatterers, and the ship echo is resampled according to the estimation of the time-varying ERV. After resampling, we can obtain the echo from a constant rotating ship and can ensure a well-focused ship by using the traditional range-Doppler algorithm. This new method overcomes the restriction of ERV variation. Thus, a longer CPI can be used for imaging, while the IPP remains stable. Finally, simulation and measured data are used to verify the effectiveness of the proposed algorithm.

关键词： Marine vehicles Imaging Radar imaging Estimation image resolution Doppler effect Radar Data resampling inverse synthetic aperture radar (ISAR) long coherent processing interval (CPI) maneuvering ships imaging time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

processing Model of LUCC Temporal Characteristics in Urban and Rural Space Based on remote sensing Data Validation

引用

INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS 2024年第4期32卷 469-490页

作者： Chen, Ningjing Southeast Univ Chengxian Coll Nanjing 210088 Jiangsu Peoples R China

The spatial land change of villages and towns can be analyzed through external spatio-temporal characteristics, which can realize the evaluation of historical development and assist the implementation of planning and design norms and the implementation of problem rectification. To explore the specific process and the overall pattern of land use change, it is necessary to analyze and predict all kinds of data in a unified way to grasp the law of development and the direction of future development. This paper takes the spatial development and planning of villages and towns as the research object, selects the remote sensing image data of regional historical development as the driving factor, combines with Gaussian function fitting to calculate the training samples, and constructs the regional spatial environment analysis system. According to the processing model of external characteristics of time series, the spatial distribution and evolution of Risk-Screening Environmental Indicators (RSEI) and its components are analyzed. The multi-dimensional remote sensing data is innovatively fused into the time series processing model. Besides, the curve which can characterize the spatial change law and is not completely symmetrical is obtained through the least square method fitting so that the data with unequal time series intervals can be flexibly processed. Finally, through the experimental analysis, the traditional Asymmetric Gaussian model (A-G) and Savitzky-Golay (S-G) are taken to compare and analyze the effect of various factors on the processing of time series characteristics. Tests show that the proposed algorithm is superior to the comparison method in noise removal of remote sensing data. The data fitting coefficient is 0.02, and the root mean square measurement error is more than 7% higher than the comparison method. It can predict the trend of land use change distribution, play a key role in assisting decision-making for different land use transformations and util

关键词： Spatial variation remote sensing data Time series features Multi-dimensional feature fusion Gaussian function fitting

来源：评论

学校读者我要写书评

暂无评论

MIPPR 2023: remote sensing image processing, Geographic Information Systems, and Other Applications

MIPPR 2023: Remote Sensing Image Processing, Geographic Info...

引用

SPIE 12th International Symposium on Multispectral image processing and pattern recognition, MIPPR 2023

ISBN: (纸本)9781510674998

The proceedings contain 25 papers. The topics discussed include: a method for cloud removal in remote sensing images based on attention mechanism and residual symmetric connection structure;research on deep learning-based land cover extraction method using multi-source mixed samples;a lossless compression of remote sensing images based on ANS entropy coding algorithm;research on the impact of change features for remote sensing image change detection;supervised spiking neural network for SAR image recognition: analysis of encoding methods and performance under strong noise influence;an edge-guided network for building footprint extraction from optical remote sensing images;and planting areas extraction of sugarcane using multi-feature fusion method based on Sentinel-2A satellite images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HSDFormer: an improved transformer for remote sensing image semantic segmentation

HSDFormer: an improved transformer for remote sensing image ...

引用

2024 International Conference on image, Signal processing, and pattern recognition, ISPP 2024

作者： Bai, Yang Gao, Suixiang University of Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Zhongguancun Laboratory Beijing100049 China

ISBN: (纸本)9781510680425

The extraction of building locations is crucial in the field of remote sensing, commonly applied in tasks such as emergency response, urban planning, and environmental monitoring. Existing methods often employ convolutional models such as ResNet and U-Net. however, these models struggle to capture long-range features of geographical objects, limiting their practical effectiveness. Meanwhile, Transformer based models face challenges due to their quadratic computational complexity. Additionally, the characteristics of remote sensing images, including dense arrangement, small scale, and class imbalance, pose difficulties for traditional patch-merging modules in downsampling, leading to the loss of significant building information. To address such limitations, we present the HSDFormer model in this paper. The model achieves a reduction in the computational complexity of self-attention calculation through a straightforward sequential reduction process. Additionally, our model has optimized the downsampling process specifically for remote sensing semantic segmentation tasks, effectively minimizing the loss of crucial information during layer-wise feature extraction. We evaluate the HSDFormer on the WHU Building Dataset and Satellite Dataset II (East Asia). The results demonstrate the model's effectiveness in accurately segmenting building locations, surpassing performance compared to other baseline models. © 2024 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Geospatial Time Machine: A Generative Model to Enhance Spectral-Temporal Data Resolution

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Lopes, Felipe A. Sagan, Vasit Sarkar, Supria Stylianou, Abby Esposito, Flavio St Louis Univ Remote Sensing Lab St Louis MO 63108 USA St Louis Univ Dept Comp Sci St Louis MO 63108 USA

Geospatial artificial intelligence (GeoAI) and data processing techniques have significantly advanced object detection, prediction, and classification tasks. However, the availability of machine learning-ready, labeled data for specific applications such as plant disease detection remains the major challenge for the broader adoption of GeoAI. For instance, collecting temporal unmanned aerial vehicle (UAV) imagery of agricultural crops to track disease emergence and progress requires substantial human labor and resources, which is often limited to a small spatial scale. Recognizing the pivotal role of temporal data in pattern recognition, object detection, and scene reconstruction, we introduce an innovative approach to augment multispectral temporal datasets: the geospatial time machine (GTM). Our proposed methodology combines graph neural network (GNN) and generative adversarial network (GAN) architectures to generate comprehensive synthetic temporal data encompassing multivariate time series. The results demonstrate that imagery generated through backcasting can enhance the accuracy of downstream classification tasks by up to 53% in plant disease detection, particularly in the initial stages of analyzing a crop growth using multispectral and multitemporal datasets.

关键词： Data models Predictive models Accuracy image reconstruction Generative adversarial networks Graph neural networks Time series analysis Imputation remote sensing Crops Data augmentation deep learning generative adversarial networks (GANs) generative artificial intelligence (GenAI) graph neural networks (GNNs) multispectral

来源：评论

学校读者我要写书评

暂无评论

LMFNet: Lightweight Multimodal Fusion Network for high-resolution remote sensing image segmentation

引用

pattern recognition 2025年 164卷

作者： Wang, Tong Chen, Guanzhou Zhang, Xiaodong Liu, Chenxi Wang, Jiaqi Tan, Xiaoliang Zhou, Wenlin He, Chanjuan Wuhan Univ State Key Lab informat Engn Surveying Mapping & Re 129 Luoyu Rd Wuhan 430072 Hubei Province Peoples R China Wuhan Univ Elect Informat Sch 299 Bayi Rd Wuhan 430072 Hubei Province Peoples R China

Despite the rapid evolution of semantic segmentation for land cover classification in high-resolution remote sensing imagery, integrating multiple data modalities such as Digital Surface Model (DSM), RGB, and Near- infrared (NIR) remains a challenge. Current methods often process only two types of data, missing out on the rich information that additional modalities can provide. Addressing this gap, we propose a novel Lightweight Multimodal data Fusion Network (LMFNet) to accomplish the tasks of fusion and semantic segmentation of multimodal remote sensing images. LMFNet uniquely accommodates various data types simultaneously, including RGB, NirRG, and DSM, through a weight-sharing, multi-branch vision transformer that minimizes parameter count while ensuring robust feature extraction. Our proposed multimodal fusion module integrates a Multimodal Feature Fusion Reconstruction Layer and Multimodal Feature Self-Attention Fusion Layer, which can reconstruct and fuse multimodal features. Our method achieves a mean Intersection over Union (mIoU) of 85.09% on the US3D dataset, marking a significant improvement over existing methods. We also studied the scalability of our method, directly extending the input modality to the SAR and hyperspectral fields. Our experimental results on the C2Seg dataset show that our method has generalization applicability to data of various modalities.

关键词： Multimodal data fusion remote sensing Lightweight network Semantic segmentation Digital surface model

来源：评论

学校读者我要写书评

暂无评论

A multiscale bidirectional fuzzy-driven learning network for remote sensing image segmentation

引用

INTERNATIONAL JOURNAL OF remote sensing 2023年第21期44卷 6860-6881页

作者： Chong, Qianpeng Xu, Jindong Ding, Yang Dai, Zhe Yantai Univ Sch Comp & Control Engn Yantai Peoples R China Australian Natl Univ ANU Coll Engn Comp & Cybernet Canberra Australia Changan Univ Sch Transportat Engn Xian Peoples R China Changan Univ Sch Transportat Engn Xian 710061 Peoples R China

Semantic segmentation is a fundamental but meaningful task in the remote sensing image understanding community. Great progress has been made in optical sensor photography technology, which poses an opportunity and a challenge for remote sensing image segmentation task. But, in fact, a longstanding and intractable problem is that many hard pixels in special position, i.e. the prevalent intra-class noise and a poor boundary delineation, is difficult to classify due to their inherent uncertainty. In this paper, we comprehensively consider the characteristics of deep learning and introduce traditional pattern recognition methods to drive structure learning, which can leverage the corresponding fuzzy logic model to alleviate the aforementioned problem in remote sensing images. Specifically, this paper designs a multiscale bidirectional fuzzy-driven learning network (MBFNet), which takes advantage of both deep learning and fuzzy logic to effectively alleviate the inherent uncertainty of these hard pixels. The structure of convolutional neural networks driven by fuzzy systems also provides a new modelling paradigm for solving the uncertain problem in remote sensing images. Meanwhile, multiscale techniques and bidirectional fusion are introduced to enhance feature aggregation and avoid the potential adverse effects of fuzzy systems, respectively. Experimental results on two datasets demonstrate qualitatively and quantitatively that the proposed MBFNet is competitive.

关键词： remote sensing semantic segmentation fuzzy learning bidirectional fusion

来源：评论

学校读者我要写书评

暂无评论

Language-Enhanced Dual-Level Contrastive Learning Network for Open-Set Hyperspectral image Classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Qin, Boao Feng, Shou Zhao, Chunhui Li, Wei Tao, Ran Zhou, Jun Harbin Engn Univ Minist Ind & Informat Technol Coll Informat & Commun Engn Harbin 150001 Peoples R China Harbin Engn Univ Minist Ind & Informat Technol Key Lab Adv Marine Commun & Informat Technol Harbin 150001 Peoples R China Minist Nat Resources Technol Innovat Ctr South China Sea Remote Sensing Guangzhou 510300 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Griffith Univ Sch Informat & Commun Technol Nathan Qld 4111 Australia

In recent years, language-supervised vision models have demonstrated impressive potential in learning open-world concepts. Some research has introduced this learning paradigm to the hyperspectral image (HSI) processing domain;however, there has been limited work integrating textual information into the hyperspectral open-set recognition task. To fill this gap, we leverage textual supervision information in open-set HSI classification (HSIC) and propose a language-enhanced dual-level contrastive learning network (LDCLNet). Specifically, we introduce a linguistic mode with prior knowledge as a supervised signal to enhance the metric distances between closed-set samples and provide supplementary semantic information for open-set samples. Second, a dual-level visual-language (V-L) contrastive learning (CL) approach, which can align visual and language embeddings separately at the instance level and manifold level, is proposed to establish a more accurate link between visual and language representations. Finally, a distance-refined open-set recognition method is proposed, which aims to effectively discover unknown class samples during testing by refining predictions of known and unknown classes. Extensive experiments and analysis on three public HSI datasets validate the effectiveness of LDCLNet.

关键词： Visualization Training Testing Feature extraction Hyperspectral imaging Contrastive learning Artificial intelligence Semantics image classification Computational modeling Dual-level contrastive learning (CL) hyperspectral image (HSI) language-supervised vision model open-set classification

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：