检索结果-内蒙古大学图书馆

image processing and Media Computing (ICIPMC), International Conference on

作者： Min Gong Kun Yan Shenglin Peng Shuyi Qu School of Information Science and Technology Northwest University Xi’an China China Academy of Space Technology(Xi’an) Xi’an China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality Xi’an China

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

In recent years, research on remote sensing object detection has primarily focused on oriented box representation and optimization, while overlooking the importance of studying feature extraction networks, leading to inaccurate identification of some targets. The conventional feature extraction networks employ fixed-size convolutional kernels, which fail to capture different levels of visual features for targets of varying sizes. In this paper, we propose a mechanism called the 3D-Weight Guide Selective Kernel (3D-WGSK) to jointly utilize spatial and channel information of input features to derive three-dimensional weights. These weights are then employed for convolutional kernel selection, enabling adaptive receptive field acquisition for capturing features of targets with different sizes. We devise a network architecture named the 3D-WGSK Net for feature extraction in remote sensing object detection. It possesses the capability of multi-scale information fusion and adaptive kernel adjustment, effectively extracting crucial features of targets with varying sizes. Experimental results on the publicly available DOTA-v1.5 dataset demonstrate the superior detection performance of our method.

关键词： Location awareness Visualization Target recognition Object detection Feature extraction Reliability engineering Kernel

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multisource Label Learning for Underground Object recognition

引用

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

作者： Lyu, Derui Chen, Lyuzhou Ban, Taiyu Wang, Xiangyu Zhu, Qinrui Zhou, Xiren Chen, Huanhuan Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230026 Peoples R China Univ Sci & Technol China Lab Big Data & Decis Hefei 230026 Peoples R China

Currently, numerous deep learning (DL) methods have been proposed for the recognition of ground penetrating radar (GPR) B-scan images. Due to the sensitivity of GPR imaging to local underground conditions, DL models trained in other underground environment areas are likely to fail in new areas. Consequently, organizing and labeling new GPR images to train models have become a widely adopted approach in practical applications. However, expert annotation is costly, making it often difficult to collect large-scale datasets with high-quality annotations. Some studies have attempted to improve the quality of image annotations by integrating the efforts of multiple annotators. This process can be constrained by the varying levels of expertise and attention spans of the annotators, which may lead to the presence of errors or contradictions in the provided labels. To address these challenges, this article proposes a method for underground target recognition aimed at multisource annotation tasks. A probability multisource label aggregation (PMLA) module is designed to estimate the reliability of multisource labels, and a label-sensitive regularization (LSR) module is introduced to mitigate the negative impact of potentially erroneous labels on model training. Extensive experiments are conducted on multiple GPR B-scan datasets. The experimental results demonstrate the advantages of the proposed method in handling annotation conflicts and improving the accuracy of underground target recognition.

关键词： Annotations Data models Reliability Task analysis Deep learning Accuracy Training Buried object detection data processing GPR data annotation ground penetrating radar (GPR)

来源：评论

学校读者我要写书评

暂无评论

Edge-Guided and Cross-Scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution 27th

Edge-Guided and Cross-Scale Feature Fusion Network for Effic...

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Yang, Zhiyuan Zhang, Bo Zeng, Zhiqiang Yeo, Si Yong School of Electronic and Information Engineering Beihang University Beijing China College of Computing and Data Science Nanyang Technological University Singapore Singapore Beijing Institute of Remote Sensing Equipment Beijing China Lee Kong Chian School of Medicine Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783031783975

In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods primarily focus on texture similarities at the same scale, neglecting cross-scale similarities that provide comprehensive information. Moreover, the misalignment between features of different scales impedes effective aggregation of information flow. To address the limitations, we propose a novel edge-guided and cross-scale feature fusion network, namely ECFNet. Specifically, we develop a pipeline consisting of the deformable convolution and the cross-attention transformer to align features of different scales. The cross-scale fusion strategy fully integrates the texture information from different scales, significantly enhancing the super-resolution. In addition, a novel structure information collaboration module is developed to guide the super-resolution reconstruction with implicit structure priors. The structure information enables the network to focus on high-frequency components of the image, resulting in sharper details. Extensive experiments on the IXI and BraTS2020 datasets demonstrate that our method achieves state-of-the-art performance compared to other multi-contrast MRI super-resolution methods, and our method is robust in terms of different super-resolution scales. Our code is available at https://***/zhiyuan-yang/Edge-Guided-Cross-Scale-MRI-Super-resolution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Object Detection and Classification of Ground Objects from Thermal Infrared remote sensing image Based on Deep Learning 4th

Efficient Object Detection and Classification of Ground Obje...

引用

4th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Wu, Falin Zhou, Guopeng He, Jiaqi Li, Haolun Liu, Yushuang Yang, Gongliu Beihang Univ Sch Instrumentat & Optoelect Engn SNARS Lab Beijing 100191 Peoples R China Beijing Syst Design Inst Electromech Engn Beijing 100854 Peoples R China

ISBN: (纸本)9783030880132;9783030880125

Wild searching and nature reserve monitoring are formidable tasks. In order to relieve the current pressure of generalmanpower observation, drone aerial surveillance using visible and thermal infrared (TIR) cameras is increasingly being adopted. Automatic data acquisition has become easier with advances in unmanned aerial vehicles (UAVs) and sensors like TIR cameras, which enables executives to search and detect ground objects at night. However, it's still a challenge to accurately and quickly process the large amount of TIR data generated from this. In response to the above problems, this paper designs an enhanced ground object detection network (UAV-TIR Retinanet) for theUAVthermal imaging system. The network uses the Retinanet as infrastructure, extracts shallowfeatures according to the characteristics of thermal infrared remote sensing images, introduces an attention mechanism and adaptive receptive field mechanism. The method achieves the best speed-accuracy trade-off on the dataset, reporting 74.47% AP at 23.48 FPS.

关键词： Ground object detection Thermal infrared remote sensing image Deep learning Attention mechanism Adaptive multiscale receptive field

来源：评论

学校读者我要写书评

暂无评论

remote sensing Predicts Long-term Indicators of Governance, Stability, and Well-being

Remote Sensing Predicts Long-term Indicators of Governance, ...

引用

IEEE Applied imagery pattern recognition Workshop (AIPR)

作者： Irvine, John M. Angelini, Brigid Crystal, Michael MITRE Corp Burlington Rd Bedford MA 01730 USA Liberty Mutual Boston MA USA Draper Lab Cambridge MA USA

ISBN: (纸本)9781665424714

Understanding a region's socio-economic conditions can inform the development of policies in both the public and private sectors. Commercial satellite imagery provides a potential avenue for abstracting socio-economic context in a quick and relatively inexpensive manner. Satellite images contain infrastructural and agricultural information that, in a previous study focused on Afghanistan and Botswana, provided a useful for characterizing regional socio-economic information. Previous studies have compared survey responses to imagery feature, using supervised machine learning models. Building on previous work, this study explores long-term assessments of a country. As with previous studies, image features extracted from commercial imagery form the explanatory variables for our models. In this case, however, we seek to predict annual indicators of conditions for a country as assessed by the World Bank. The models relate imagery-derived features to indicators of Political Stability, Control of Corruption, Rule of Law, Government Effectiveness, Voice and Accountability, and Gross Domestic Product using data from multiple countries.

关键词： remote sensing imagery economic analysis governance social indicators

来源：评论

学校读者我要写书评

暂无评论

Unsupervised double weighted graphs via good neighbours for dimension reduction of hyperspectral image

引用

INTERNATIONAL JOURNAL OF remote sensing 2022年第15-16期43卷 6152-6175页

作者： Chou, Jiahui Zhao, Siyu Chen, Yingyi Jing, Ling China Agr Univ Coll Sci Beijing 100091 Peoples R China China Agr Univ Natl Innovat Ctr Digital Fishery Beijing Peoples R China China Agr Univ Yantai Inst Yantai Shandong Peoples R China China Agr Univ Coll Informat & Elect Engn Beijing Peoples R China Minist Agr & Rural Affairs Key Lab Smart Farming Technol Aquat Anim & Livest Beijing Peoples R China

As the major research in pattern recognition, unsupervised dimension reduction is a challenging problem because of no label information. Most unsupervised dimension reduction methods usually construct similarity graph by k-nearest neighbour to preserve local structure in the low-dimensional subspace. However, k-nearest neighbour is calculated by Euclidean distance, which is sensitive to noise and outliers. And only considering local structure will reduce the classification accuracy. In this paper, a new unsupervised dimension reduction method called unsupervised double-weighted graphs via good neighbours (uDWG-GN) is proposed. First, uDWG-GN proposes a local structure Low-Rank Representation to learn similarity matrix and then uses the similarity matrix to find good neighbours of each sample. Second, according to good neighbours of the sample, uDWG-GN considers similar and dissimilar relationship between samples and constructs double-weighted graphs. Finally, based on L-2,L-1 norm, uDWG-GN finds the optimal projection matrix by maximizing the distance of dissimilar samples and minimizing the distance of similar samples. Experimental results on three hyperspectral images demonstrate the superiority and effectiveness of our method compared with other dimension reduction methods.

关键词： Unsupervised learning dimension reduction good neighbour feature extraction hyperspectral data

来源：评论

学校读者我要写书评

暂无评论

Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial imagery

Superpixels and Graph Convolutional Neural Networks for Effi...

引用

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

作者： Dadsetan, Saba Pichler, David Wilson, David Hovakimyan, Naira Hobbs, Jennifer Univ Pittsburgh Pittsburgh PA 15260 USA Intelinair Inc San Francisco CA USA Univ Illinois Urbana IL USA

ISBN: (纸本)9781665448994

Advances in remote sensing technology have led to the capture of massive amounts of data. Increased image resolution, more frequent revisit times, and additional spectral channels have created an explosion in the amount of data that is available to provide analyses and intelligence across domains, including agriculture. However, the processing of this data comes with a cost in terms of computation time and money, both of which must be considered when the goal of an algorithm is to provide real-time intelligence to improve efficiencies. Specifically, we seek to identify nutrient deficient areas from remotely sensed data to alert farmers to regions that require attention;detection of nutrient deficient areas is a key task in precision agriculture as farmers must quickly respond to struggling areas to protect their harvests. Past methods have focused on pixel-level classification (i.e. semantic segmentation) of the field to achieve these tasks, often using deep learning models with tens-of-millions of parameters. In contrast, we propose a much lighter graph-based method to perform node-based classification. We first use Simple Linear Iterative Cluster (SLIC) to produce super-pixels across the field. Then, to perform segmentation across the non-Euclidean domain of superpixels, we leverage a Graph Convolutional Neural Network (GCN). This model has 4-orders-of-magnitude fewer parameters than a CNN model and trains in a matter of minutes.

关键词： image segmentation Semantics Agriculture Real-time systems Computational efficiency pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

VIGIA: A Thermal and Visible imagery System to Track Volcanic Explosions

引用

remote sensing 2022年第14期14卷 3355页

作者： Vasconez, Freddy Moussallam, Yves Harris, Andrew J. L. Latchimy, Thierry Kelfoun, Karim Bontemps, Martial Macias, Carlos Hidalgo, Silvana Cordova, Jorge Battaglia, Jean Mejia, Jessica Arrais, Santiago Velez, Luis Ramos, Cristina Univ Clermont Auvergne Lab Magmas & Volcans OPGC CNRSIRD F-63000 Clermont Ferrand France Escuela Politec Nacl Inst Geofis Ap 17-01-2759 Quito 170525 Ecuador Columbia Univ Lamont Doherty Earth Observ New York NY 10964 USA Tech Univ Kaiserslautern Div Control Syst LRS D-67663 Kaiserslautern Germany

The monitoring of the frequency, intensity/magnitude and dynamics of explosive events at volcanoes in a state of unrest is key to surveying and forecasting their activity. Thermal and visual video observations of eruptive phenomena, and their correlation with data from deformation and seismic networks, are often limited by technical constraints including lack of time synchronisation, data volumes and power consumption. Several solutions are currently available and here we present an instrument designed for the permanent and real-time observation of volcanic explosive events in the visible and thermal infrared wavelengths, the output of which can be fully synchronised with ancillary monitoring data. Our system (VIGIA: visual and infrared ground-based imagery analyser) follows an edge computing approach whereby information is processed on-site, and periodic reports are sent to the local observatory and the system "decides" when to acquire high-temporal resolution data so as to capture key explosive events. As a permanent installation, VIGIA enables the continuous, long-term and time-synchronised observation of volcanic activity while reducing power consumption and data volumes. We suggest that VIGIA-style instruments could provide useful scientific and monitoring information, and provide here the key details of the components, assembly, and code so that observatories can replicate the system and build their own VIGIA at minimal cost. We use the Reventador volcano, in Ecuador, as a case study to present the capabilities of the instrument.

关键词： volcanic explosions thermal image video surveillance pattern recognition

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: A structured support vector machine for hyperspectral satellite image segmentation and classification based on modified swarm optimization approach (Retracted Article)

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2021年第3期12卷 3659-3668页

作者： Manju, S. Helenprabha, K. Velammal Inst Technol Dept Elect & Commun Engn Chennai Tamil Nadu India RMD Engn Coll Dept Elect & Commun Engn Kavaraipettai India

The hyperspectral image analysis improved by the most powerful and fastest growing technologies in the field of remote sensing in recent years. The hyperspectral image classification involves the identification and recognition by capturing spectral information over the region and consequently analysis by the pixel value. The conventional method uses the wiener filter for pre-processing and GLCM approach to extract the second order statistical features with dragonfly optimization technique for image extraction. The machine learning techniques used in the conventional technique is extreme learning machine and relevance vector machine. Here the high-resolution hyperspectral remote sensing datasets are taken from hyperspectral remote sensing scenes. This scene acquired by the AVIRIS sensor during a flight campaign over the Indian pines test site in Northwestern Indian. The hyperspectral images are filtered by a modified swarm optimization approach and these images are extracted by threshold-based segmentation process with the use of OTSU's binary threshold method. The structured support vector machine is proposed for the classification of the satellite image. By the use of the optimization process, the structured support vector machine is improved its performance. Since overall sensitivity, specificity, and accuracy is improved. The simulation part carried out the data set for Indian pines and Salinas's scene and the overall design is done with MATLAB.

关键词： Hyperspectral image Structured support vector machine Otsu's binary threshold method Modified particle swarm optimization image segmentation Classification

来源：评论

学校读者我要写书评

暂无评论

Iterative structure transformation and conditional random field based method for unsupervised multimodal change detection

引用

pattern recognition 2022年 131卷

作者： Sun, Yuli Lei, Lin Guan, Dongdong Wu, Junzheng Kuang, Gangyao Natl Univ Def Technol Coll Elect Sci Changsha 410073 Peoples R China High Tech Inst Xian Xian 710025 Peoples R China

Change detection between heterogeneous images has become an increasingly interesting research topic in remote sensing. The different appearances and statistics of heterogeneous images bring great challenges to this task. In this paper, we propose an unsupervised iterative structure transformation and conditional random field (IST-CRF) based multimodal change detection (MCD) method, combining an imaging modality-invariant based structure transformation method with a random filed framework specifically designed for MCD, to acquire an optimal change map within a global probabilistic model. IST-CRF first constructs graphs to represent the structures of the images, and transforms the heterogeneous images to the same differential domain by using graph based forward and backward structure transformations. Then, the change vectors are calculated to distinguish the changed and unchanged areas. Finally, in order to classify the change vectors and compute the binary change map, a CRF model is designed to fully explore the spectral-spatial information, which incorporates the change information, local spatially-adjacent neighbor information, and global spectrally-similar neighbor information with a random field framework. As the changed samples will influence the structure transformation and reduce the quality of change vectors, we use an iterative framework to propagate the CRF segmentation results back to the structure transformation process that removes the changed samples, and thus improve the accuracy of change detection. Experiments conducted on different real data sets show the effectiveness of IST-CRF. Source code of the proposed method will be made available at https://***/yulisun/IST-CRF .(c) 2022 Elsevier Ltd. All rights reserved.

关键词： Unsupervised change detection KNN graph image transformation Multimodal Conditional random field

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：