检索结果-内蒙古大学图书馆

6th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Deng, Feng Huang, Meiyu Bao, Wei Ji, Nan Xiang, Xueshuang China Acad Space Technol Qian Xuesen Lab Space Technol Beijing 100094 Peoples R China Xiangtan Univ Xiangtan 411105 Peoples R China

ISBN: (纸本)9789819985487;9789819985494

Land use classification using optical and Synthetic Aperture Radar (SAR) images is a crucial task in remote sensing image interpretation. Recently, deep multi-modal fusion models have significantly enhanced land use classification by integrating multi-source data. However, existing approaches solely rely on simple fusion methods to leverage the complementary information from each modality, disregarding the intermodal correlation during the feature extraction process, which leads to inadequate integration of the complementary information. In this paper, we propose FASONet, a novel multi-modal fusion network consisting of two key modules that tackle this challenge from different perspectives. Firstly, the feature alignment module (FAM) facilitates cross-modal learning by aligning high-level features from both modalities, thereby enhancing the feature representation for each modality. Secondly, we introduce the multi-modal squeeze and excitation fusion module (MSEM) to adaptively fuse discriminative features by weighting each modality and removing irrelevant parts. Our experimental results on the WHU-OPT-SAR dataset demonstrate the superiority of FASONet over other fusion-based methods, exhibiting a remarkable 5.1% improvement in MIoU compared to the state-of-the-art MCANet method.

关键词： Land use classification Multi-modal fusion Feature alignment

来源：评论

学校读者我要写书评

暂无评论

A comprehensive analysis for crowd counting methodologies and algorithms in Internet of Things

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2024年第1期27卷 859-873页

作者： Gao, Mingliang Souri, Alireza Zaker, Mayram Zhai, Wenzhe Guo, Xiangyu Li, Qilei Shandong Univ Technol Sch Elect & Elect Engn Zibo 255000 Peoples R China Halic Univ Dept Software Engn TR-34060 Istanbul Turkiye Islamic Azad Univ Dept Comp Engn Sci & Res Branch Tehran Iran Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

The Internet of Things (IoT) provides a collaborative infrastructure to communicate smart devices with cloud-edge healthcare applications, medical devices, wearable biosensors, etc. On the other hand, crowd counting as one of computer vision approaches is an emerging topic to detect any objects with static or dynamic mobility in the IoT environments. Smart crowd counting enables pattern recognition for many intelligent applications such as microbiology, surveillance, healthcare systems, crowdedness estimation, and other environmental case studies. According to complicated capturing systems in the IoT environments, crowd counting methods can influence on performance of object detection in the critical case studies using Artificial Intelligence (AI)-based approaches such as machine learning, deep learning, collaborative learning, fuzzy logic and meta-heuristic algorithms. This paper provides a new comprehensive technical analysis for existing AI-based crowd counting approaches in healthcare and medical systems, biotechnology and IoT environments. Meanwhile, it presents a discussion on the existing case studies with respect to analyzing technical aspects and applied algorithms to enhance pattern prediction factors. Finally, some new innovative efforts and challenges are presented for new research upcoming and open issues.

关键词： Internet of Things (IoT) Artificial Intelligence Crowd counting WiFi sensing image processing

来源：评论

学校读者我要写书评

暂无评论

image compression scheme based on region of interest recognition 4

Image compression scheme based on region of interest recogni...

引用

4th International Conference on Electronic Communication, Computer Science and Technology, ECCST 2024

作者： Wu, Dawei Bai, Enjian College of Information Science and Technology Donghua University Shanghai201620 China

With the development of networks, many fields now demand higher quality in specific image areas, such as main characters in photos, lesion areas in medical images, and features in remote sensing. At the same time, these fields need to manage data storage and transmission effectively for subsequent analysis and application. In order to meet the demand for image compression in modern society, this paper proposes an image compression scheme based on region of interest (ROI) recognition, dividing images into ROI and non-ROI regions and processing them with lossless and lossy compression, respectively, to improve efficiency and ensure ROI quality. The scheme uses the object detection network YOLOv4 to recognize the ROI of the image, designs an image block difference transformation to transform the image pixels into smaller values, designs a lossless DC encoding for the ROI of the image based on the difference between adjacent pixels, and designs a lossy DC encoding with quantization coding for the non-ROI of the image. Experimental analysis of uncompressed images shows the scheme effectively enhances compression efficiency while maintaining ROI quality, proving its practical value. © Published under licence by IOP Publishing Ltd.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Deep density estimation based on multi-spectral remote sensing data for in-field crop yield forecasting

Deep density estimation based on multi-spectral remote sensi...

引用

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

作者： Baghdasaryan, Liana Melikbekyan, Razmik Dolmajain, Arthur Hobbs, Jennifer Intelinair Inc Yerevan Armenia Intelinair Inc Chicago IL USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Yield forecasting has been a central task in computational agriculture because of its impact on agricultural management from the individual farmer to the government level. With advances in remote sensing technology, computational processing power, and machine learning, the ability to forecast yield has improved substantially over the past years. However, most previous work has been done leveraging low-resolution satellite imagery and forecasting yield at the region, county, or occasionally farm-level. In this work, we use high-resolution aerial imagery and output from high-precision harvesters to predict in-field harvest values for corn-raising farms in the US Midwest. By using the harvester information, we are able to cast the problem of yield-forecasting as a density estimation problem and predict a harvest rate, in bushels/acre, at every pixel in the field image. This approach provides the farmer with a detailed view of which areas of the farm may be performing poorly so he can make the appropriate management decisions in addition to providing an improved prediction of total yield. We evaluate both traditional machine learning approaches with hand-crafted features alongside deep learning methods. We demonstrate the superiority of our pixel-level approach based on an encoder-decoder framework which produces a 5.41% MAPE at the field-level.

关键词： Deep learning Satellites Conferences Government Estimation Crops pattern recognition

来源：评论

学校读者我要写书评

暂无评论

2024 IEEE International Conference on image processing, ICIP 2024 - Proceedings

2024 IEEE International Conference on Image Processing, ICIP...

引用

31st IEEE International Conference on image processing, ICIP 2024

ISBN: (纸本)9798350349399

The proceedings contain 593 papers. The topics discussed include: MDBFUSION: a visible and infrared image fusion framework capable for motion deblurring;prune channel and distill: discriminative knowledge distillation for semantic segmentation;imbalanced data robust online continual learning based on evolving class aware memory selection and built-in contrastive representation learning;privacy-preserving visual cues communication for hearing-impaired people using deep learning;transformer-based clipped contrastive quantization learning for unsupervised image retrieval;attention enhancement with parallel groups for remote sensing object detection;cross-domain few-shot in-context learning for enhancing traffic sign recognition;and recurrent 3-D multi-level visual transformer for joint classification of heterogeneous 2-D and 3-D radiographic data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Style transformation super-resolution GAN for extremely small infrared target image

引用

pattern recognition LETTERS 2023年第1期174卷 1-9页

作者： Lee, In Ho Chung, Won Young Park, Chan Gook Seoul Natl Univ Automat & Syst Res Inst Dept Aerosp Engn Seoul 08826 South Korea

With the development of generative adversarial networks, the super -resolution technique of reconstructing a high -resolution image from a low -resolution has achieved excellent resolution results. However, small, low resolution images are widespread, such as images taken by a thermal camera or with a lens far from the target. Extremely small target image super -resolution is a challenging problem. The main reason is that the small infrared target has fewer pixels and weaker features. The current optimization methods for the tiny target are mainly based on multi -scale feature fusion or super -resolution enhancement. The low -resolution images characterizing small targets are usually obtained by down sampling with high -resolution images during training, which is different from the style of the tiny target in actual detection applications, resulting in poor resolution. In order to solve the problem, we propose a new resolution network: Style Transformation Super -Resolution Generative Adversarial Network (STSRGAN). It contains two sub -networks: one is style transformation GAN to convert the style of the image, and the other is super -resolution GAN. STSRGAN transforms a blurry infrared small target into a clear target with a distribution similar to the training set. Then the resolution can be increased to get a better enhancement effect. The discriminator distinguishes whether the input comes from the generator or the actual image to assist in generating a better super -resolution image. Meanwhile, we produced an infrared Unmanned Aerial Vehicle (UAV) small target dataset with target pixels below 16 x 16. Our method proves better resolution enhancement of small IR targets and shows superior performance over other methods through experiments.

关键词： Super-resolution remote sensing images Infrared Small target

来源：评论

学校读者我要写书评

暂无评论

2023 Asia-Pacific Conference on image processing, Electronics and Computers, IPEC 2023

2023 Asia-Pacific Conference on Image Processing, Electronic...

引用

2023 Asia-Pacific Conference on image processing, Electronics and Computers, IPEC 2023

The proceedings contain 52 papers. The topics discussed include: improvement of remote sensing image target detection algorithm based on YOLO V5;A Study of Chan-Vese model with the introduction of edge information;real-time monitoring algorithm of muscle state based on sEMG signal;lane detection network with direction context;anomaly pixel detection via dual-branch uncertainty metrics;high precision license plate recognition algorithm in open scene;implementation and design of metro process quality inspection system based on image processing technology;the research on remote sensing image change detection based on deep learning;research on aircraft wheel hub pose detection method based on machine vision;lunar dome detection method based on few-shot object detection;and image enhancement algorithm of foggy sky with sky based on sky segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse and Complete Latent Organization for Geospatial Semantic Segmentation

Sparse and Complete Latent Organization for Geospatial Seman...

引用

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

作者： Yang, Fengyu Ma, Chenyang Univ Michigan Ann Arbor MI 48109 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Geospatial semantic segmentation on remote sensing images suffers from large intra-class variance in both foreground and background classes. First, foreground objects are tiny in the remote sensing images and are represented by only a few pixels, which leads to large foreground intraclass variance and undermines the discrimination between foreground classes (issue firstly considered in this work). Second, background class contains complex context, which results in false alarms due to large background intra-class variance. To alleviate these two issues, we construct a sparse and complete latent structure via prototypes. In particular, to enhance the sparsity of the latent space, we design a prototypical contrastive learning to have prototypes of the same category clustering together and prototypes of different categories to be far away from each other. Also, we strengthen the completeness of the latent space by modeling all foreground categories and hardest (nearest) background objects. We further design a patch shuffle augmentation for remote sensing images with complicated contexts. Our augmentation encourages the semantic information of an object to he correlated only to the limited context within the patch that is specific to its category, which further reduces large intra-class variance. We conduct extensive evaluations on a large scale remote sensing dataset, showing our approach significantly outperforms state-of-the-art methods by a large margin.

关键词： image segmentation Computer vision Computational modeling Semantics Prototypes Organizations Geospatial analysis

来源：评论

学校读者我要写书评

暂无评论

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN For remote sensing image Data 27th

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN F...

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Hirner, Dominik Fraundorfer, Friedrich Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Cologne Germany

ISBN: (纸本)9783031781919

Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is expensive to create and not available in many situations. This is especially true for remote sensing applications, where there is an excess of available data without proper ground truth. To tackle this problem, we propose a self-supervised CNN with self-improving adaptive abilities. In the first iteration, the created disparity map is inaccurate and noisy. Leveraging the left-right consistency check, we get a sparse but more accurate disparity map which is used as an initial pseudo ground-truth. This pseudo ground-truth is then adapted and updated after every epoch in the training step of the network. We use the sum of inconsistent points in order to track the network convergence. The code for our method will be made available after acceptance at https://***/thedodo/SAda-Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

AN OVERVIEW OF THE CONTRIBUTIONS OF JOSE MANUEL BIOUCAS-DIAS TO remote sensing image processing

AN OVERVIEW OF THE CONTRIBUTIONS OF JOSE MANUEL BIOUCAS-DIAS...

引用

IEEE International Geoscience and remote sensing Symposium (IGARSS)

作者： Plazas, Antonio Li, Jun Figueiredo, Mario A. T. Univ Extremadura Hyperspectral Comp Lab Caceres Spain Sun Yat Sen Univ Sch Geog & Planning Guangzhou Peoples R China Univ Lisbon Inst Telecomunicacoes Lisbon Portugal Univ Lisbon Inst Super Tecn Lisbon Portugal

ISBN: (纸本)9781665403696

Jose Manuel Bioucas-Dias was an outstanding expert in many different IEEE-related areas, including inverse problems in imaging, signal and image processing, pattern recognition, optimization, and remote sensing. He authored or co-authored more than 250 publications, including more than 100 journal papers (66 of which published in IEEE journals) and over 200 peer-reviewed international conference papers and book chapters. His contributions have been extremely influential in many different fields, namely phase estimation and unwrapping, convex optimization and Bayesian inference for imaging inverse problems, with a special emphasis on remote sensing, including synthetic aperture radar (SAR), hyperspectral unmixing, fusion, superresolution, classification, and segmentation. In this paper, we provide an overview of his outstanding contributions to remote sensing image processing.

关键词： remote sensing pattern recognition optimization signal and image processing inverse problems

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：