检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Shasha Sun Wenxing Bao Hao Guo Kewen Qu Wei Feng School of Computer Science and Engineering North Minzu University Yinchuan China Department of Remote Sensing Science and Technology School of Electronic Engineering Xidian University Xi’an China

Hyperspectral image super resolution (HSI-SR) problem aims to fuse a low-resolution hyperspectral image (HSI) with its corresponding multispectral image (MSI) to obtain a high-resolution hyperspectral image (HSR). However, the commonly used methods have some limitations. For example, the matrix decomposition method does not preserve the spatial or spectral information of the image well, and the tensor decomposition method has a high computational complexity. This paper proposes a method based on spectral subspace sparse tensor factorization (SSTF), which learns the spectral subspace from hyperspectral images, constrains this model using sparse tensor regularisation, transforms it to solve a convex optimisation problem, and iteratively optimises the problem using the alternating direction method of multipliers (ADMM). The computational complexity of the algorithm is effectively reduced while retaining spatial and spectral features. Compared with the state-of-the-art methods, experimental results demonstrate the effectiveness of the SSTF method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A lightweight object detection network based on YOLOv5 for SAR image

A lightweight object detection network based on YOLOv5 for S...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Aijia Shen Liangbo Zhao Fanyun Xu Guoqing Wang Wenchao Liu Zimeng Shen National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

remote sensing image target detection is one of the key technologies in the field of intelligent interpretation of remote sensing images, and it has significant application value in various areas, including military defense. When performing remote sensing image object detection on airborne and spaceborne platforms, the vast amount of remote sensing data processing and limited computational resources impose high real-time requirements on the object detection algorithms. This paper designs a lightweight object detection network model named YOLOv5-tiny, based on the existing deep learning network detection model YOLOv5s, and deploys it on the Jetson TX2 development board for training and testing. Experimental results show that the proposed YOLOv5-tiny model, when tested on the SAR-AIRcraft-1.0 with an input image size of 640x640, is 10 times smaller than YOLOv5s; it has a computational cost of 5.2 GFLOPs, which is 1/5 of YOLOv5s, and the processing time for a single image is reduced to half that of YOLOv5s, with only a 0.1% decrease in accuracy.

关键词： YOLO Deep learning Accuracy Computational modeling Atmospheric modeling Data processing Radar polarimetry remote sensing Load modeling Testing

来源：评论

学校读者我要写书评

暂无评论

Settlement Mapping for Population Density Modelling in Disease Risk Spatial Analysis 6

Settlement Mapping for Population Density Modelling in Disea...

引用

6th International Workshop on Big Data and Information Security, IWBIS 2021

作者： Mutasodirin, Mirza Alim Rizqullah, Rafi Dwi Setiyoko, Andie Arymurthy, Aniati Murni Universitas Indonesia Faculty of Computer Science Depok Indonesia LAPAN Remote Sensing Technology and Data Center Jakarta Indonesia

ISBN: (数字)9781665424516

ISBN: (纸本)9781665424516

In disease risk spatial analysis, many researchers especially in Indonesia are still modelling population density as the ratio of total population to administrative area extent. This model oversimplifies the problem, because it covers large uninhabited areas, while the model should focus on inhabited areas. This study uses settlement mapping against satellite imagery to focus the model and calculate settlement area extent. As far as our search goes, we did not find any specific studies comparing the use of settlement mapping with administrative area to model population density in computing its correlation to a disease case rate. This study investigates the comparison of both models using data on Tuberculosis (TB) case rate in Central and East Java Indonesia. Our study shows that using administrative area density the Spearman's $\rho$ was considered as 'Fair' $(0.566, p © 2021 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bins for Monocular Height Estimation from Single remote sensing Images

Adaptive Bins for Monocular Height Estimation from Single Re...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Sining Chen Yilei Shi Zhitong Xiong Xiao Xiang Zhu Data Science in Earth Observation Technical University of Munich (TUM) Munich Germany Remote Sensing Technology Institute (IMF) German Aerospace Center (DLR) Wessling Germany Remote Sensing Technology Technical University of Munich (TUM) Munich Germany

Monocular height estimation is of great importance in generating 3D city models from single remote sensing images, while it is a challenging task due to the ill-posed nature of the problem. To address the issue, we propose to adopt adaptive bins (AdaBins) for the network design, which enhances the representation capability of the network with the classification-regression paradigm and the incorporation of local features and global context via a vision transformer encoder. Besides, to weaken the biases of the trained networks caused by the long-tailed nature of the dataset, a head-tail cut is conducted for different treatments of head and tail pixels. Experiments show that improvements are expected with the proposed network on the proposed GBH dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of Drifting Ionospheric Irregularities for L-Band Geosynchronous SAR Imaging Simulation

Effects of Drifting Ionospheric Irregularities for L-Band Ge...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Feixiang Tang Yifei Ji Yongsheng Zhang Zhen Dong Heli Gao Bingji Zhao Qingjun Zhang College of Electronic Science and Technology National University of Defense Technology Changsha China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

The L-band geosynchronous synthetic aperture radar (GEO SAR) is susceptible to the ionospheric irregularities due to its lower carrier frequency, which can be more complicated because the velocity of drifting irregularities is comparable with the scanning velocity of ionospheric penetration points (IPPs) of GEO SAR. In this paper, a drifting ionospheric scintillation simulator (DISS) is proposed for generating L-band GEO SAR data affected by the drifting ionospheric irregularities. The DISS is divided into a static 2D scintillation transfer function generator, a drifting IPP offset indexer and a GEO SAR echo simulator. Based on the DISS, the simulation results indicate that the drifting ionospheric irregularities of the L-band GEO SAR will present different artifacts and more serious decorrelations in L-band GEO SAR images, compared with the L-band low-Earth-orbit (LEO) SAR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GLOBAL SPATIAL AND LOCAL SPECTRAL SIMILARITY BASED SAMPLE AUGMENT AND EXTENDED SUBSPACE PROJECTION FOR HYPERSPECTRAL IMAGE CLASSIFICATION

GLOBAL SPATIAL AND LOCAL SPECTRAL SIMILARITY BASED SAMPLE AU...

引用

2021 IEEE International Geoscience and remote sensing Symposium, IGARSS 2021

作者： Shen, Xueji Yu, Haoyang Yu, Chunyan Wang, Yulei Song, Meiping Center of Hyperspectral Imaging in Remote Sensing Information Science and Technology College Dalian Maritime University Dalian116026 China

This paper proposes a method to improve the performance of the supervised classification from two aspects. Firstly, the global spatial and local spectral similarity is used to extend the labeled sample size (GLS). Secondly, extended subspace projection (ESP) which projects the original image to a lower-dimensional subspace is used to alleviate band redundancy. Finally, the two implements are combined with the sparse representation classifier (SRC) to optimize the hyperspectral image classification (HSIC). The proposed method is named GLSESP. Experimental results on real hyperspectral data set demonstrate the practicality and effectiveness of GLSESP for HSIC tasks. © 2021 IEEE

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Mapping Severe Tropical Cyclone Tauktae Across the Arabian Sea and Western Coast of India Using remote sensing and Machine Learning During May 2021

Mapping Severe Tropical Cyclone Tauktae Across the Arabian S...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： K Nagamani Anoop Kumar Mishra Mohammad Suhail Meer B. Anuradha Centre for Remote sensing and Geoinformatics Sathyabama institute of Science and Technology (SIST) Chennai tamil Nadu INDIA SETMET division IMD New delhi Centre for Remote sensing and Geoinformatics Sathyabama institute of Science and Technology (SIST) Chennai Tamil Nadu Department of Civil Engineering Chennai Institute of Technology (CIT) Chennai Tamil Nadu INDIA

In May 2021, the Arabian Sea experienced the formation of a tropical supercyclone, "Tauktae," which resulted in extensive destruction throughout the coastline regions of Mumbai, Goa, and Gujarat. The cyclone initiated from a low-pressure system situated over the Bay of Bengal, progressively strengthening into the cyclonic storm named "Tauktae" and subsequently moving along the western coast of India. The objective of this study is to analyze the characteristics of cyclones by utilizing higher rainfall estimations obtained from the Meteosat-8 satellite. The analysis of Meteosat-8 observations was conducted utilizing machine learning (ML) techniques. During the cyclone, there were notable quantities of precipitation that surpassed 600mm per day. The diurnal changes exhibited pronounced levels of precipitation, with rainfall rates reaching 50-60mm/hr in regions badly impacted by the cyclone, namely Gujarat, Mumbai, and Goa. The study area encountered a substantial precipitation event on May 20, 2021, with an estimated rainfall accumulation of around 650mm. The cyclone “Tauktae" exhibited a northwestward trajectory with a velocity of 16 kilometers per hour across the Arabian Sea. Its point of origin was located at a latitude of $16.2^{\circ}\mathrm{N}$ and a longitude of $72.6^{\circ}\mathrm{E}$, precisely around 1430 Indian Standard Time (IST).The region of Goa saw significant consequences of Cyclone Tauktae, which manifested in the form of powerful winds, elevated sea levels, and heavy precipitation. Moreover, the occurrence of heavy rainstorms on May 20th resulted in significant cumulative precipitation, which subsequently caused landslides and catastrophic flash flooding in multiple regions along India's western coastline. The current investigation highlights the significance of employing high-resolution satellite data and machine learning techniques for real-time mapping and monitoring of atmospheric parameters. This approach is crucial for the successful implement

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global Information Edge Augmentation Network for remote sensing Image Continuous Super-Resolution

Global Information Edge Augmentation Network for Remote Sens...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Shize Gao Yong Lei Jingya Zhang Guoqing Wang Wenchao Liu National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The continuous-scale super-resolution (SR) method for remote sensing (RS) images has the potential to achieve flexible scale SR with a single network, representing a significant research area in the field of RS. However, the majority of prevailing methods learn features from localization, thereby neglecting the global semantic coherence of RS images. This results in unbalanced SR outcomes. Furthermore, the optimization strategy based on the multilayer perceptron (MLP) utilized in the implicit neural representation (INR) method results in blurred reconstructed image edges. To address these issues, a novel continuous-scale SR method for RS images, a global information edge augmentation network (GIEAN), is proposed. Initially, the global state space model (GSSM) aggregates the global information of the image from diverse perspectives and learns the contextual interactions at disparate locations of the image globally. Subsequently, the dual edge enhancement module (DEEM) learns the image body and edges independently through the main branch and edge branch, respectively, with the objective of enhancing the edge component of the SR results. Extensive experimental evaluation on the UCMerced dataset demonstrates the superiority of GIEAN over existing continuous-scale SR techniques.

关键词： Image edge detection Aggregates Superresolution Semantics Coherence Feature extraction Sensors remote sensing Image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Reverse Refinement Network for Narrow Rural Road Detection in High-Resolution Satellite Imagery

arXiv

引用

arXiv 2024年

作者： Wang, Ningjing Wang, Xinyu Pan, Yang Yao, Wanqiang Zhong, Yanfei The School of Surveying and Mapping Xi’an University of Science and Technology Xi’an710054 China The School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China

The automated extraction of rural roads is pivotal for rural development and transportation planning, serving as a cornerstone for socio-economic progress. Current research primarily focuses on road extraction in urban areas. However, rural roads present unique challenges due to their narrow and irregular nature, posing significant difficulties for road extraction. In this article, a reverse refinement network (R2-Net) is proposed to extract narrow rural roads, enhancing their connectivity and distinctiveness from the background. Specifically, to preserve the fine details of roads within high-resolution feature maps, R2-Net utilizes an axis context aware module (ACAM) to capture the long-distance spatial context information in various layers. Subsequently, the multi-level features are aggregated through a global aggregation module (GAM). Moreover, in the decoder stage, R2-Net employs a reverse-aware module (RAM) to direct the attention of the network to the complex background, thus amplifying its separability. In experiments, we compare R2-Net with several state-of-the-art methods using the DeepGlobe road extraction dataset and the WHU-RuR+ global large-scale rural road dataset. R2-Net achieved superior performance and especially excelled in accurately detecting narrow roads. Furthermore, we explored the applicability of R2-Net for large-scale rural road mapping. The results show that the proposed R2-Net has significant performance advantages for large-scale rural road mapping applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided Representation Distribution Optimization for Change Detection in High-Resolution remote sensing Imagery

Prototype-Guided Representation Distribution Optimization fo...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Guoqing Wang He Chen Xin Wei Junqing Shi Liang Chen Wenchao Liu National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Change detection is the process of automatically extracting change areas from bi-temporal remote sensing images. The key of deep learning-based change detection methods is to extract features that represent changes/non-changes. Most of the existing methods only enhance the representation ability of the changed regions through the model architecture design, but lack further constraints in the representation space. This paper introduces a prototype-guided representation distribution optimization method. By comparing pixel features with prototypes, confusing pixels can be determined, and these pixels are adaptively weighted during learning, so that similar representations are closer and different representations are farther apart. In addition, the representation distribution is also applied as transferred knowledge to knowledge distillation for lightweight CD model. Experimental results on two public datasets show the effectiveness of the proposed method.

关键词： Adaptation models Accuracy Space technology Optimization methods Prototypes Feature extraction Data processing Data models remote sensing

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：