检索结果-内蒙古大学图书馆

4th International Conference on Multimedia processing, Communication and Information Technology, MPCIT 2024

作者： Suneel, J.S. Dileep, M.R. Visvesvaraya Technological University Nitte Meenakshi Institute of Technology Department of Master of Computer Applications Bengaluru India Nitte Meenakshi Institute of Technology Department of Master of Computer Applications Bengaluru India

ISBN: (数字)9798350375466

ISBN: (纸本)9798350375466

This research is mainly concerned with enhancing the object recognition and classification of multispectral imagery imagery especially of people and vehicles in the heavily vegetated regions. Sub-technology such as PCA and WT have inherent limit with regards to the ability to preserve both spatial and spectral properties. To fill the above-mentioned gaps, this work presents a CAMFNet;a framework that integrates multiscale fusion together with Visible (VIS), Near-Infrared (NIR) and Thermal Infrared (TIR) data for fusion and feature extraction and classification. CAMFNet uses classifiers like Gradient Tree Boost and SVM for differentiating people, cars, trees and other such objects. Feature extraction is carried out using PCA and HOG for enhancing the methods prior to the extraction. One of the radical innovations is the employment of certain aspects in CAMFNet, including multiscale feature extraction and attention mechanisms for boosted data fusion. The framework also involves generative aerial networks (GANs) and it is capable of preserving important spatial and spatial details profiles thereby making it to be more accurate, to more recalls and has low false positives compared to normal methods. Experiments made on real-world datasets coming from different landscapes, revealed that the CAMFNet outperformed the other networks in the classification metrics, as well as in PSNR and SSIM. Surveillance, agriculture, and the military are some of its uses to emphasize work in large-scale and distant investigations. It pushes the state-of-art in multispectral image fusion with this strong, scalable, real-time method for nonmilitary and military domains for large-scale objects recognition. © 2024 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Statistical Robust Estimation of Spatial Symmetric Transformations Based on Mahalanobis Distance

引用

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

作者： Hu, Yu Fang, Xing Zeng, Wenxian Kutterer, Hansjoerg Li, Dawei Wuhan Univ Sch Geodesy & Geomat Wuhan 430079 Peoples R China Karlsruhe Inst Technol Geodet Inst D-76131 Karlsruhe Germany Wuhan Univ Hubei Luojia Lab Wuhan 430079 Peoples R China

This article explores the problem of symmetric transformation in the presence of outliers for photogrammetric and remote-sensing applications. We propose a pointwise robust objective for symmetric coordinate transformation by assuming the corresponding structure of the downweighting matrix and choosing the squared Mahalanobis distance (MD) as the statistic to evaluate the downweighting factors. Compared with the previous work, our method regards all the coordinates of one point as a whole. It is practical, in principle, since the displacement and correspondence relation are pointwise;it is statistically rigorous, since the stochasticity of both frames is considered;it is flexible, since the incorporated constraints enable all kinds of transformation. By utilizing the parameter partition technique, a more intelligent iteration manner is proposed for the implementation aspect, which specially suits globally distributed geoscience data. The developed method is vetted in the synthetic and real examples, including geodetic datum conversion and point cloud registration. The algorithms have potential in many areas, including cross-source registration, image analysis, pattern recognition, surface modeling, and remote-sensing image registration.

关键词： Symmetric matrices Estimation Vectors remote sensing Covariance matrices Anomaly detection Point cloud compression Mahalanobis distance (MD) parameter partition point cloud registration pointwise robust estimation symmetric transformation

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional Doppler-associated radar imaging method based on bi-directional data processing

引用

IET RADAR SONAR AND NAVIGATION 2022年第1期16卷 145-160页

作者： Hayashi, Takumi Ando, Takeru Kidera, Shouhei Univ Electrocommun Grad Sch Informat & Engn Tokyo 1828585 Japan

Using a microwave or millimetre wave radar system, this study aims to achieve highly accurate Doppler velocity estimation and radar imaging that would be suitable for various remote-sensing sensors, such as self-driving, surveillance, or security applications. In particular, micro-Doppler signatures are one of the most promising approaches for human recognition;however, the traditional limitations of both velocity and temporal resolution need to be addressed. The weighted kernel density (WKD) algorithm using super-resolution Doppler velocity estimation has been one solution. Using WKD, this study incorporates the range points migration (RPM) method of radar imaging to enhance accuracy in both Doppler velocity and radar imaging using an iterative data selection scheme. Furthermore, to obtain more informative Doppler-associated RPM-based images using less data by exploiting a unique feature of WKD and RPM methods, this study introduces the image integration approach along the slow-time profile. In this framework, bi-directional data processing between Doppler velocity and imaging analysis is achieved. At each pulse hit sequence, both numerical and experimental tests demonstrate that the proposed method yields a more accurate Doppler-associated radar image compared with the methods in previous studies.

关键词： Doppler radar millimetre wave radar radar imaging radar signal processing

来源：评论

学校读者我要写书评

暂无评论

SUPER RESOLUTION FOR SINGLE SATELLITE image USING A GENERATIVE ADVERSARIAL NETWORK 24

SUPER RESOLUTION FOR SINGLE SATELLITE IMAGE USING A GENERATI...

引用

24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow

作者： Lil, Ran Liu, Wangzeng Gong, Wenyu Zhu, Xiuli Wang, Xinpeng Natl Geomat Ctr China Beijing Peoples R China China Earthquake Adm Inst Geol State Key Lab Earthquake Dynam Beijing Peoples R China

Inspired by the immense success of deep neural network in image processing and object recognition, learning-based image super resolution (SR) methods have been highly valued and have become the mainstream direction of super resolution research. Base on the recent proposed state-of-art convolution neural network (CNN) super-resolution methods, this paper proposed a generative adversarial network for single satellite image Super Resolution reconstruction. It built on a trained deep residual network to generate preliminary SR images, combined with a discriminative network learns to differentiate preliminary SR images and High resolution samples. The experiments results show that our method can use existing model parameters to refine SR image performance.

关键词： Super Resolution Satellite imagery Generative Adversarial Network Residual Network

来源：评论

学校读者我要写书评

暂无评论

Design of Virtual Display System for Digital Museum Based on Edge Detection Algorithm

Design of Virtual Display System for Digital Museum Based on...

引用

International Conference on Smart Applications and Sustainability in the Artificial Intelligence of Things, SAS-AIoT 2024

作者： Fu, Yi Yu, Yiting School of Design Art Shenyang Jianzhu University Liaoning Shenyang110168 China

ISBN: (纸本)9783031782756

Under the rapid development of virtual reality, the display of many products has been transformed from the traditional physical display to a combination of physical and virtual displays, thus enabling users to better understand the products. In this process, the role of consumers in the display of goods is also increasing. Especially for certain works of art that require display effect, the display effect will directly affect the artistic value of the work. The system can realize the display of virtual products to a greater extent. But when facing the art works, it does not show the details very well, so the display effect is not good enough. Edge extraction of images is a very effective method in many fields such as computer vision, pattern recognition and remote sensing. Edge extraction refers to the extraction of the region of the image with sudden changes in brightness, which is the edge of the target, which contains most of the features in the image and is the basis for image analysis. The edge detection algorithm can make the details of the art work more perfect. The experimental results prove that the correct rate of image segmentation based on Canny edge detection algorithm is in the range of 70% to 80%. The correct rate of image segmentation based on Laplacian operator fluctuates around 70%. The correct rate of image segmentation based on Roberts operator is 70% up and down. It can be clearly seen that the correct rate of image segmentation based on Sobel operator is the highest, which is conducive to the visual experience of the virtual display design of the digital museum. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Neural network big data fusion in remote sensing image processing technology

引用

JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期33卷

作者： Wu, Xiaobo Lingnan Normal Univ Sch Business Zhanjiang 524048 Guangdong Peoples R China

remote sensing (RS) image processing has made significant progress in the past few years, but it still faces some problems such as the difficulty in processing large-scale RS image data, difficulty in recognizing complex background, and low accuracy and efficiency of processing. In order to improve the existing problems in RS image processing, this study dealt with ConvNext-convolutional neural network (CNN) and big data (BD) in parallel. Moreover, it combined the existing RS image processing with the high dimensional analysis of data and other technologies. In this process, the parallel processing of large data and high-dimensional data analysis technology improves the difficulty and low efficiency of large-scale RS image data processing in the preprocessing stage. The ConvNext-CNN optimizes the two modules of feature extraction and object detection in RS image processing, which improves the difficult problem of complex background recognition and improves the accuracy of RS image processing. At the same time, the performance of RS image processing technology after neural networks (NNs) and BD fusion and traditional RS image processing technology in many aspects are analyzed by experiments. In this study, traditional RS image processing and RS image processing combined with NN and BD were used to process 2,328 sample datasets. The image processing accuracy and recall rate of traditional RS image processing technology were 81 and 82%, respectively, and the F1 score was about 0.81 (F1 value is the reconciled average of accuracy and recall, a metric that combines accuracy and recall to evaluate the quality of the results, a higher F1 value indicates a better overall performance of the retrieval system). The accuracy rate and recall rate of RS image processing technology, which integrates NN and BD, were 97 and 98%, respectively, and its F1 score was about 0.97. After analyzing the process of these experiments and the final output results, it can be determined that the

关键词： remote sensing image image processing neural networks big data high dimensional data analysis

来源：评论

学校读者我要写书评

暂无评论

2023 4th International Conference on Computer Vision, image and Deep Learning, CVIDL 2023

2023 4th International Conference on Computer Vision, Image ...

引用

4th International Conference on Computer Vision, image and Deep Learning, CVIDL 2023

ISBN: (纸本)9798350326444

The proceedings contain 136 papers. The topics discussed include: comparison of image generation methods based on diffusion models;research on image preprocessing and target detection of vehicle-machine cooperative system;a research on traditional tangka image classification based on visual features;research on image recognition based on neural network model learning algorithm;research on image recognition based on reinforcement learning;low-quality image binarization method based on threshold array system;comprehensive study of image processing techniques for low-altitude target recognition;visual cryptography scheme by freeform optics based on optimal mass transport;SPECT bone scan image classification by fusing multi-attention mechanism with deep residual networks;fine-grained image recognition method based on input perception joint probability prediction;deep learning in image classification: an overview;auricular images with annotations for segmenting key-organ mapping regions in auricular diagnosis;insulator image dataset generation based on generative adversarial network;structure-preserving domain adaptation network for generating pencil sketches;underwater image recovery method considering target polarization characteristics;and a dual attention network for multimodal remote sensing image matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MERS-Net: A Lightweight and Efficient remote sensing image Object Detector

引用

IEEE GEOSCIENCE AND remote sensing LETTERS 2025年 22卷

作者： Zhang, Yao Zhao, Hongyang Li, Xingdong Li, HongGang Jin, Jing Northeast Forestry Univ Coll Mech & Elect Engn Harbin 150042 Peoples R China Harbin Inst Technol Coll Astronaut Harbin 150001 Peoples R China

With the rapid advancement of deep learning technology, the problem of object detection in the field of remote sensing has received increasing attention. However, existing methods still face challenges when dealing with remote sensing image detection tasks, such as insufficient accuracy in small object recognition, an imbalance between recognition precision and detection efficiency, and difficulties in handling multiscale variations. Based on the above problems, this letter proposes a lightweight and efficient remote sensing image object detector MERS-Net. First, we propose an enhanced subchannel feature extraction (SCFE) module based on subchannel mixing to improve the feature extraction capability of the model under complex scale transformation. Second, we incorporated the WaveletPool module along with the GSConv and VoVGSCSP modules from Slimneck into the model to reduce computational parameters. Finally, we designed a lightweight detection head MRF-Detect based on the parameter sharing mechanism to improve the recognition capability of the model under limited hardware conditions. We verified the effectiveness of MERS-Net on the public datasets DOTA, AI-TOD, and DIOR. Compared with current mainstream algorithms such as YOLOv11, the average accuracy [mean average precision (mAP)] is improved by 2.6%, 2.5%, and 2.7%, respectively. At the same time, the parameter quantity and giga floating point operations (GFLOPs) are significantly reduced, showing its superior detection performance.

关键词： Feature extraction remote sensing Convolution Head Accuracy image recognition Transformers Computer architecture Computational modeling Computer vision Multiscale feature object detection (OD) parameter sharing mechanism remote sensing images subchannel processing

来源：评论

学校读者我要写书评

暂无评论

A Semi-Supervised Deep Rule-Based Approach for Complex Satellite Sensor image Analysis

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2022年第5期44卷 2281-2292页

作者： Gu, Xiaowei Angelov, Plamen P. Zhang, Ce Atkinson, Peter M. Aberystwyth Univ Dept Comp Sci Aberystwyth SY23 3DB Dyfed Wales Univ Lancaster Sch Comp & Commun Lancaster LA1 4WA England Univ Lancaster Lancaster Environm Ctr Lancaster LA1 4YQ England UK Ctr Ecol & Hydrol Lancaster LA1 4AP England

Large-scale (large-area), fine spatial resolution satellite sensor images are valuable data sources for Earth observation while not yet fully exploited by research communities for practical applications. Often, such images exhibit highly complex geometrical structures and spatial patterns, and distinctive characteristics of multiple land-use categories may appear at the same region. Autonomous information extraction from these images is essential in the field of pattern recognition within remote sensing, but this task is extremely challenging due to the spectral and spatial complexity captured in satellite sensor imagery. In this research, a semi-supervised deep rule-based approach for satellite sensor image analysis (SeRBIA) is proposed, where large-scale satellite sensor images are analysed autonomously and classified into detailed land-use categories. Using an ensemble feature descriptor derived from pre-trained AlexNet and VGG-VD-16 models, SeRBIA is capable of learning continuously from both labelled and unlabelled images through self-adaptation without human involvement or intervention. Extensive numerical experiments were conducted on both benchmark datasets and real-world satellite sensor images to comprehensively test the validity and effectiveness of the proposed method. The novel information mining technique developed here can be applied to analyse large-scale satellite sensor images with high accuracy and interpretability, across a wide range of real-world applications.

关键词： Satellites image segmentation Feature extraction Semantics Semisupervised learning Mathematical model Prototypes deep rule-based system deep learning satellite sensor image analysis semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning of remote sensing Scene Representations Using Contrastive Multiview Coding

Self-Supervised Learning of Remote Sensing Scene Representat...

引用

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

作者： Stojnic, Vladan Risojevic, Vladimir Univ Banja Luka Fac Elect Engn Banja Luka Bosnia & Herceg

ISBN: (纸本)9781665448994

In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-supervised pre-training on the performance on downstream tasks. We show that, for the downstream task of remote sensing image classification, using self-supervised pre-training on remote sensing images can give better results than using supervised pre-training on images of natural scenes. Besides, we also show that self-supervised pre-training can be easily extended to multispectral images producing even better results on our downstream tasks.

关键词： Visualization image segmentation image coding Conferences Object detection Feature extraction pattern recognition

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：