检索结果-内蒙古大学图书馆

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

作者： Berton, Gabriele Stoken, Alex Caputo, Barbara Masone, Carlo Politecn Torino Turin Italy NASA Jacobs Technol Johnson Space Ctr Houston TX USA

ISBN: (纸本)9798350353006

Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response. Despite their significance, accurately localizing the geographical extent of these images, which is crucial for effective utilization, poses substantial challenges. Current, manual localization efforts are time-consuming, motivating the need for automated solutions. We propose a novel approach - leveraging image retrieval - to address this challenge efficiently. We introduce innovative training techniques which contribute to the development of a high-performance model, EarthLoc. We develop six evaluation datasets and perform a comprehensive benchmark comparing EarthLoc to existing methods, showcasing its superior efficiency and accuracy. Our approach marks a significant advancement in automating the localization of astronaut photography, which will help bridge a critical gap in Earth observations data. Code and datasets are available at https://***/gmberton/EarthLoc.

关键词： dataset image retrieval large scale remote sensing visual geolocalization Visual Localization

来源：评论

学校读者我要写书评

暂无评论

Parallel Optimization of remote sensing image Geometric Correction on DCU 5

Parallel Optimization of Remote Sensing Image Geometric Corr...

引用

5th International Conference on Computer Engineering and Application (ICCEA)

作者： Liu, Runjie Wang, Siqi Zhengzhou Univ Natl Supercomp Ctr Zhengzhou Zhengzhou Henan Peoples R China Zhengzhou Univ Sch Comp & Artificial Intelligence Zhengzhou Henan Peoples R China

ISBN: (纸本)9798350386783;9798350386776

Geometric correction is essential in the preprocessing of remote sensing images, ensuring the precision and reliability of spatial data, crucial for further analysis such as target recognition and feature extraction. Nevertheless, handling a lot of high-resolution images often encounters computational inefficiencies and limited real-time processing capabilities. This paper introduces a parallel optimization approach for geometric correction on multi-DCU heterogeneous clusters, leveraging a detailed thread mapping strategy tailored to the DCU architecture. It capitalizes on the specific hardware characteristics and execution models of the DCU for parallel processing. The study delves into the common bicubic interpolation resampling method used in geometric correction, optimizing thread mapping to match the DCU's computational and storage architecture. This method allows a single thread to handle multiple pixel computations, enhancing data reuse during interpolation. The research accomplishes parallel geometric correction processing on DCU and significantly curtails memory access through optimization, improving algorithmic efficiency. Comparative experimental outcomes show that the proposed parallel strategy markedly outperforms traditional serial CPU processing, multicore CPU processing, and unoptimized DCU acceleration, evidencing substantial speedup across processing different image sizes.

关键词： Geometric correction Parallel computing DCU HIP

来源：评论

学校读者我要写书评

暂无评论

Learning-based Classification Approach for Coded Aperture Compressive Spectral image

Learning-based Classification Approach for Coded Aperture Co...

引用

2023 International Conference on image, Signal processing, and pattern recognition, ISPP 2023

作者： Wang, Peng Ma, Xu Zhao, Qile Key Laboratory of Photoelectronic Imaging Technology System of Ministry of Education of China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781510666351

Spectral images include rich spatio-spectral information of target scene, which can accurately identify and distinguish the features of ground objects. Therefore, spectral image classification is widely used in remote sensing. However, traditional spectral imaging techniques need to scan the region of interest along the spatial dimension or spectral dimension, which takes a long acquisition time and increases the burden of data transmission and storage. To overcome these shortcomings, coded aperture snapshot spectral imaging (CASSI) system based on compressive sensing theory appeared. In this paper, we build a testbed of dual-disperser CASSI (DD-CASSI) system, which can reconstruct the three-dimensional (3D) spectral image datacube of target object from a few two-dimensional compressive measurements. Then, a 3D convolutional neural network is applied to accomplish the spectral image classification based on the reconstructed datacube. Different classification methods are compared based on the experimental data. It shows that the proposed compressive spectral image classification method achieves pretty close results compared to the classification methods based on the original datacube. But, the proposed method is beneficial to improve the acquisition efficiency of the spectral image data. © 2023 SPIE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Small object detection in remote sensing images based on improved YOLOV7 4

Small object detection in remote sensing images based on imp...

引用

4th International Conference on Computer Vision and pattern Analysis, ICCPA 2024

作者： Lu, Jian Chen, Yulong Yang, Zhiyong School of Software Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510682528

remote sensing images have a wide range of applications in geological exploration, disaster warning, military reconnaissance and other fields, and the detection of specific targets in remote sensing images can improve the efficiency of image analysis. However, due to the high shooting height of remote sensing images, the target pixel area obtained is small, and the complex background of the image is unfavorable for detection. To address this problem, a practical feature extraction network for remote sensing images is designed and transplanted into the YOLO v7 algorithm. Firstly, a multiscale nested Vision Transformer model is proposed, compared with the standard Vision Transformer model, which can simultaneously compute multiple attention to multiple feature maps at different scales and merge the multi-scale features to enhance the perception of the Vision Transformer model for the global features;secondly, a fission type multi-field convolution model is proposed, which is a multi-field convolution model. fission multi-perceptual field convolution module, which enhances the processing capability of local features by grouping feature maps for computation;finally, a multi-level feature extraction network is designed to combine global and local features in remote sensing maps to enhance the feature richness of the network. The related experimental tests are carried out on three datasets, including RSOD, and the experimental results show that the designed algorithm improves the F1-Score index by 3.65% on average compared with YOLO v7, and improves the mAP index by 3.53% on average compared with YOLO v7. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantification of Hyperspectral Planes Effectiveness - A Semantic Segmentation Perspective 14

Quantification of Hyperspectral Planes Effectiveness - A Sem...

引用

14th Workshop on Hyperspectral Imaging and Signal processing: Evolution in remote sensing, WHISPERS 2024

作者： Florea, Corneliu Racoviteanu, Andrei Ivanovici, Mihai National University of Science and Technology POLITEHNICA Image Processing Analysis Laboratory Bucharest Romania Transilvania University of Braşov MIV Laboratory Braşov Romania

ISBN: (纸本)9798331513139

Automatic monitoring of agricultural crops with remote sensing data allows significant improvement in the face of climate change and environmental degradation. Hyperspectral imaging supports this process with spectrally detailed data, which goes beyond visible spectrum. In this paper we investigate how much information is actually brought by the richness and the details of additional spectral information. The assumed perspective is that of agricultural crop semantic segmentation approached with a powerful visual transformer based solution. Into more detail, we explore the effectiveness of various spectral bands in hyperspectral images, used as input, measured by five metrics quantifying the performance of agricultural crop segmentation. The evaluation relies on the UAV-HSI database. The primary conclusion is that there is significant redundancy in hyperspectrum, yet the full spectrum provides always top results. A secondary conclusion is that the recognition of specific crops such as 'cotton' and 'holly' benefits from removal of certain bands. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Contextual Information Classification of remotely Sensed images 6

Contextual Information Classification of Remotely Sensed Ima...

引用

6th International Conference on pattern recognition and image Analysis (IPRIA)

作者： Dori, Alirza Ghassemian, Hassan Imani, Maryam TarbiatModares Univ Fac Elect & Comp Engn Image Proc & Informat Anal Lab Tehran Iran

ISBN: (纸本)9798350314557

This work proposes a multidisciplinary contextual information extraction and decision fusion approach for increasing the classification accuracy. It improves the image classification with integrating the results of various classifiers. The proposed method is implemented in three-steps: 1) contextual feature extraction using four different feature extractors methods: a) Gray Level Cooccurrence Matrix,b) Gabor filters, c) Laplacian Gaussian filters and d) Gaussian Derivatives Functions;2) classification of contextual features using four different classification rules (ML, Tree, KNN and SVM) by using only 2% of data for training the classifiers;and 3) finally, decision fusion using six decision fusion rules. The experimental results on real remotely sensed images have been presented.

关键词： contextual information feature extraction classification decision fusion remote sensing

来源：评论

学校读者我要写书评

暂无评论

Research on Aircraft Whole day Location Technology Based on Aerial and remote sensing image Matching 6

Research on Aircraft Whole day Location Technology Based on ...

引用

6th International Conference on Artificial Intelligence and pattern recognition, AIPR 2023

作者： Qiao, Pingan Zhang, Xiaofan Lei, Ziying Yang, Dongfang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an China Xian High Tech Research Institute Xi'an710025 China

ISBN: (纸本)9798400707674

Nowadays, aircraft positioning is mainly based on GNSS, but GNSS signal receiving equipment is difficult to ensure the stability and reliability of the positioning signal in the presence of obstruction or strong electromagnetic interference environments. In recent years, with the development of image matching technology, intelligent positioning technology for aircraft based on remote sensing image feature matching has received widespread attention. This article conducts research on the problem of aircraft positioning based on aerial photography and remote sensing image matching. Firstly, in order to solve the problem of significant differences in style between remote sensing images and aerial images, resulting in poor direct matching results, the CycleGAN style transfer network was used as the basis to study the style transfer of remote sensing images and reduce the differences between different modal images;Secondly, based on the LoFTR matching algorithm, the matching between remote sensing images and aerial images after style transfer was studied;Finally, in order to solve the problem of aircraft positioning based on image matching, the application of homography transformation in remote sensing and aerial image matching mapping was studied, and a method for calculating geographic location after successful image matching was provided. Finally, the method proposed in this paper was validated through experiments. © 2023 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

FNRegion: A fast NAM-based region extraction algorithm

引用

IET image processing 2023年第14期17卷 4076-4088页

作者： Zheng, Yunping Yang, Bowen Sarem, Mudar South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Gen Org Remote Sensing GORS Damascus Syria

Region extraction is usually used by many computer vision tasks as a pre-processing step to extract image features. However, how to efficiently extract effective regions remains a challenging problem. In this paper, inspired by the non-symmetry and anti-packing pattern representation model (NAM) and the FatRegion algorithm, a fast NAM-based region extraction algorithm which is called FNRegion is proposed. A NAM-based homogeneous block generation algorithm is first presented to represent an image as a combination of multiple homogeneous blocks, each of which is a square region with visually indistinguishable intra-region colour difference. Then, these homogeneous blocks are merged into larger regions according to their colour and shape information. To group these regions into larger ones in order to progressively build a region tree, a distance function is defined using variety of regional information to measure the distance between adjacent regions. Also, a multi-feature region merging algorithm with linear complexity both in time and space is *** proposed algorithm has been evaluated on multiple public datasets in comparison with the state-of-the-art region extraction algorithms. The experimental results show that in the case of almost the same or even less running time as other fast region extraction algorithms, the proposed algorithm is able to extract higher-quality regions. In this paper, inspired by the non-symmetry and anti-packing pattern representation model (NAM) and the FatRegion algorithm, a fast NAM-based region extraction algorithm which is called FNRegion is proposed. A NAM-based homogeneous block generation algorithm is first presented to represent an image as a combination of multiple homogeneous blocks, each of which is a square region with visually indistinguishable intra-region colour difference. Then, these homogeneous blocks are merged into larger regions according to their colour and shape information. To group these regions into lar

关键词： image processing image representation

来源：评论

学校读者我要写书评

暂无评论

Broadband convolutional processing using band-alignment-tunable heterostructures

引用

NATURE ELECTRONICS 2022年第4期5卷 248-254页

作者： Pi, Lejing Wang, Pengfei Liang, Shi-Jun Luo, Peng Wang, Haoyun Li, Dongyan Li, Zexin Chen, Ping Zhou, Xing Miao, Feng Zhai, Tianyou Huazhong Univ Sci & Technol Sch Mat Sci & Engn State Key Lab Mat Proc & Die & Mould Technol Wuhan Peoples R China Nanjing Univ Collaborat Innovat Ctr Adv Microstruct Natl Lab Solid State Microstruct Inst Brain Inspired IntelligenceSch Phys Nanjing Peoples R China

Broadband convolutional processing is critical to high-precision image recognition and is of use in remote sensing and environmental monitoring. Implementing in-sensor broadband convolutional processing using conventional complementary metal-oxide-semiconductor technology is, however, challenging because broadband sensing and convolutional processing require the use of the same physical processes. Here we show that a palladium diselenide/molybdenum ditelluride van der Waals heterostructure can provide simultaneous broadband image sensing and convolutional processing. The band alignment between type-II and type-III heterojunctions of the photovoltaic heterostructure is gate tunable, and the devices exhibit linear light-intensity dependence for both positive and negative photoconductivity, as well as linear gate dependence for the broadband photoresponse. Our in-sensor broadband convolutional processing improves recognition accuracy for multi-band images compared with conventional single-band-based convolutional neural networks. A palladium diselenide/molybdenum ditelluride van der Waals photovoltaic heterostructure can provide simultaneous broadband image sensing and convolutional processing.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Combining the Convolution and Transformer for Classification of Smoke-Like Scenes in remote sensing images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2022年 60卷 1页

作者： Chen, Shikun Li, Weixuan Cao, Yichao Lu, Xiaobo Southeast Univ Sch Automat Nanjing 210096 Peoples R China Minist Educ Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Peoples R China Nanjing Enbo Technol Co Ltd Nanjing 210014 Peoples R China

remote sensing (RS) images are used in a wide range of tasks. In the fire detection field, smoke in RS images is considered as an indicator of wildfires. However, smoke-like scenes, e.g., cloud, in RS images increase the difficulty of smoke recognition. Convolutional neural networks (CNNs) have greatly promoted the development of image processing. CNNs are good at capturing local features;however, their ability to capture global features is relatively weak. Recently, the transformer deep learning model has shown strong potential in vision tasks. The transformer model utilizes self-attention modules to extract global features but may lose local details. recognition of smoke in RS images depends strongly on the combination of both local and global features. Thus, this article proposes the transformer enhanced convolutional network (TECN) to classify RS smoke-like scenes. The proposed hybrid TECN model exploits the advantages of the CNN and transformer techniques at the same time. In TECN, the feature merge and intelligent aggregation modules are used to promote conversion and aggregation between CNN feature maps and transformer patch embeddings. Experiments are conducted on the USTC_SmokeRS dataset, which is developed for the classification of RS smoke-like scenes. The experimental results demonstrate that the proposed TECN achieves a competitive accuracy of 98.39% on this dataset.

关键词： Transformers Feature extraction image analysis Convolutional neural networks Task analysis Convolution image recognition Convolutional neural network (CNN) scene classification smoke-like scenes transformer

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：