检索结果-内蒙古大学图书馆

Small object detection in remote sensing images based on super-resolution

pattern recognition LETTERS 2022年 153卷 107-112页

作者： Fang Xiaolin Hu Fan Yang Ming Zhu Tongxin Bi Ran Zhang Zenghui Gao Zhiyuan Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian Peoples R China Tianjin Jinhang Comp Technol Res Inst Tianjin Peoples R China Air Force Equipment Dept Tianjin Mil Representat Off 3 Tianjin Peoples R China

Accurate objects detection in remote sensing images is very important, because security, transportation, and rescue applications in military and civilian fields require fully analyzing and using these images. To address the problem that many small-sized objects in remote sensing images are difficult to detect, this paper proposes an improved S(2)ANET-SR model based on S(2)A-NET network. In this paper, the original and reduced image are fed to the detection network at the same time, and then a super-resolution enhancement module for the reduced image is designed to enhance the feature extraction of small objects, after that, the perceptual loss and texture matching loss is proposed as supervision. Extensional experiments are conducted to evaluate the performance on the general remote sensing dataset DOTA, and the results show that our proposed method can achieve 74.47% mAP, which is 0.79% better than the accuracy of S(2)A-NET. (C) 2021 Elsevier B.V. All rights reserved.

关键词： remote sensing images Object detection Super-Resolution

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral image Classification

Quantum-Inspired Spectral-Spatial Pyramid Network for Hypers...

引用

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

作者： Zhang, Jie Zhang, Yongshan Zhou, Yicong Univ Macau Dept Comp & Informat Sci Macau Peoples R China China Univ Geosci Sch Comp Sci Wuhan Peoples R China

ISBN: (纸本)9798350301298

Hyperspectral image (HSI) classification aims at assigning a unique label for every pixel to identify categories of different land covers. Existing deep learning models for HSIs are usually performed in a traditional learning paradigm. Being emerging machines, quantum computers are limited in the noisy intermediate-scale quantum (NISQ) era. The quantum theory offers a new paradigm for designing deep learning models. Motivated by the quantum circuit (QC) model, we propose a quantum-inspired spectral-spatial network (QSSN) for HSI feature extraction. The proposed QSSN consists of a phase-prediction module (PPM) and a measurement-like fusion module (MFM) inspired from quantum theory to dynamically fuse spectral and spatial information. Specifically, QSSN uses a quantum representation to represent an HSI cuboid and extracts joint spectral-spatial features using MFM. An HSI cuboid and its phases predicted by PPM are used in the quantum representation. Using QSSN as the building block, we further propose an end-to-end quantum-inspired spectral-spatial pyramid network (QSSPN) for HSI feature extraction and classification. In this pyramid framework, QSSPN progressively learns feature representations by cascading QSSN blocks and performs classification with a softmax classifier. It is the first attempt to introduce quantum theory in HSI processing model design. Substantial experiments are conducted on three HSI datasets to verify the superiority of the proposed QSSPN framework over the state-of-the-art methods.

关键词： Photogrammetry and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Adversarial Shape Learning for Building Extraction in VHR remote sensing images

引用

IEEE TRANSACTIONS ON image processing 2022年 31卷 678-690页

作者： Ding, Lei Tang, Hao Liu, Yahui Shi, Yilei Zhu, Xiao Xiang Bruzzone, Lorenzo Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland Tech Univ Munich TUM Chair Remote Sensing Technol D-80333 Munich Germany German Aerosp Ctr DLR Remote Sensing Technol Inst IMF D-82234 Wessling Germany Tech Univ Munich TUM Data Sci Earth Observat SiPEO D-80333 Munich Germany Tech Univ Munich TUM Signal Proc Earth Observat D-80333 Munich Germany

Building extraction in VHR RSIs remains a challenging task due to occlusion and boundary ambiguity problems. Although conventional convolutional neural networks (CNNs) based methods are capable of exploiting local texture and context information, they fail to capture the shape patterns of buildings, which is a necessary constraint in the human recognition. To address this issue, we propose an adversarial shape learning network (ASLNet) to model the building shape patterns that improve the accuracy of building segmentation. In the proposed ASLNet, we introduce the adversarial learning strategy to explicitly model the shape constraints, as well as a CNN shape regularizer to strengthen the embedding of shape features. To assess the geometric accuracy of building segmentation results, we introduced several object-based quality assessment metrics. Experiments on two open benchmark datasets show that the proposed ASLNet improves both the pixel-based accuracy and the object-based quality measurements by a large margin. The code is available at: https://***/ggsDing/ASLNet.

关键词： Buildings Shape image segmentation Feature extraction Adversarial machine learning Semantics Convolutional neural networks Building extraction generative adversarial networks (GANs) image segmentation convolutional neural network deep learning remote sensing

来源：评论

学校读者我要写书评

暂无评论

Robust Approach for Butterfly Species Classification Using a Single Spatio-Hyperspectral image 14

Robust Approach for Butterfly Species Classification Using a...

引用

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

作者： Adje, Erick A. Delmaire, Gilles Ahouandjinou, Arnaud S. R. M. Puigt, Matthieu Roussel, Gilles Univ. Littoral Côte d'Opale LISIC - UR 4491 LonguenesseF-62219 France Univ. d'Abomey-Calavi LRSIA Cotonou Benin

ISBN: (纸本)9798331513139

Distinguishing between pest and pollinator butterfly species is a major challenge in precision agriculture. However, traditional RGB cameras, capturing only shape and surface color, are insufficient for detailed insect analysis. This work explores the rich spectral information provided by hyperspectral imaging for effective butterfly species identification. For this purpose, we use a single spatio-spectral image that provides partial spectral information to identify the butterfly species. The proposed classification approach consists of a convex combination of the probabilistic decisions obtained by the Gaussian Naive Bayes and Z-score methods for each butterfly reflectance. Compared to traditional classification models, this approach showed higher robustness and performance. © 2024 IEEE.

关键词： Butterfly recognition Gaussian mixture models Hyperspectral Imaging Precision agriculture Spatio-spectral camera

来源：评论

学校读者我要写书评

暂无评论

Research on synthetic aperture radar recognition method based on deep learning

Research on synthetic aperture radar recognition method base...

引用

2024 International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2024

作者： Hua, Zhendong Wang, Haifeng Wang, Haoxin Chinese Flight Test Establishmen Xi’an China

ISBN: (纸本)9781510685840

Target recognition in SAR images is a key issue in remote sensing image processing, which is widely used in many fields. Traditional recognition methods face many challenges due to the complexity of SAR images. In this paper, we propose an improved method based on GoogLeNet and improved YOLOV5 algorithm to cope with the limitations of MSTAR dataset. In this paper, GoogLeNet is introduced to improve the performance of target recognition in complex backgrounds, and its unique module improves the efficiency while reducing the parameters, which is especially suitable for handling small targets and complex textures in SAR images. Meanwhile, YOLOV5 is improved to enhance the detection accuracy and reduce the computational complexity. The effectiveness and superiority of the method is verified through experiments on the MSTAR dataset. © 2024 SPIE.

关键词： Synthetic aperture radar Target detection Convolution Target recognition Education and training Detection and tracking algorithms Feature extraction image processing Performance modeling Neck

来源：评论

学校读者我要写书评

暂无评论

In situ monitoring of defects in steel structures using a robot-assisted ultrasonic inspection technique

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2024年第9期18卷 578-597页

作者： Besharatifard, Hamidreza Hasanzadeh, Saeed Qom Univ Technol Dept Elect & Comp Engn Qom Iran

Incidents in extreme environments can bring unprecedented consequences that would endanger the lives of many humans. Real-time and early detection of cracks and defects in the steel used for the construction of industrial sites can bring many benefits to remote operators and site managers. Although different methods and systems have been proposed in the past, they are not suitable for real-time fault detection or long-term operation in harsh environments. Therefore, this paper proposes a low-power robotic platform with a magnetic actuator mechanism which is capable of wireless inspection of steel structures using the ultrasonic method. The proposed magnetic motion uses the inertia force generated by the piston vibration and the difference in frictional force during movement. The paper evaluates the performance of the steel structure defect detection system from four different perspectives: sensing principle, wireless communication network, driving part, and power supply. This work proposes a new fault detector robot with the ability to adhere to metal surfaces and a full description of its functionality. Also, a novel design of a PM linear DC source-driven actuator with higher efficiency than the previous designs which were supplied by the PWM pulses is proposed. A comprehensive model of the proposed actuator is conducted and its performance is evaluated using the EMworks software. A method of signal analysis and defect recognition that can be used in the online monitoring of steel structures using ultrasonic sensors is also proposed. Some valuable points in improving the performance of the proposed design which can be helpful in the real-life implementation of the actuator in different applications are suggested. image

关键词： fault diagnosis magnetic field measurement pattern recognition ultrasonic measurement

来源：评论

学校读者我要写书评

暂无评论

Temporal and spatial pattern analysis and forecasting of methane: Satellite image processing

引用

ECOLOGICAL INFORMATICS 2025年 89卷

作者： Elshukri, Fatima Abusirriya, Noor Hussam Braganza, Nathan Joseph Amhamed, Abdulkarem Alrebei, Odi Fawwaz Hamad Bin Khalifa Univ Qatar Environm & Energy Res Inst QEERI Doha 34110 Qatar

Atmospheric dispersion modeling is a critical tool in environmental research, offering insights into spatial and temporal patterns of pollutants. This study introduces an innovative approach leveraging remote sensing technology to analyze and predict methane (CH4) levels, specifically focusing on Qatar. Utilizing data from the Sentinel-5P satellite, captured through the Tropospheric Monitoring Instrument (TROPOMI), this research presents a detailed examination of methane concentrations. The methodology includes generating daily, monthly, and yearly average images, alongside Sobel gradient images to enhance the analysis of daily and monthly variations. A thresholding technique is applied to each month's data to identify critical methane concentration levels. Moreover, the study extends to forecasting methane levels for the latter half of 2024 and the entirety of 2025. These predictions are rigorously validated by comparing the predicted methane concentrations with observed data, resulting in a Root Mean Square Error (RMSE) that underscores the model's predictive accuracy. The R-squared (R2) value further demonstrates the model's robustness, particularly in scenarios where conventional prediction methods would be hampered by incomplete datasets. This research not only advances the understanding of methane dynamics in arid regions but also illustrates the potential of remote sensing as a costeffective alternative to traditional data-intensive approaches. The accompanying Python code, detailed in the Appendix, is made publicly available to facilitate further research and application in similar environmental studies.

关键词： Atmospheric dispersion modeling (ADM) remote sensing Satellite imagery Earth engine GIS Climate change Prediction Modeling Sobel gradient Root mean square error R-squared (R2) Python

来源：评论

学校读者我要写书评

暂无评论

Implementation of the image super-resolution DWT based algorithm on Raspberry Pi platform for real-time applications

Implementation of the image super-resolution DWT based algor...

引用

Conference on Real-Time processing of image, Depth, and Video Information

作者： Osorno-Ortiz, Raul J. Ponomaryov, Volodymyr, I Reyes-Reyes, Rogelio Cruz-Ramos, Clara Garcia-Salgado, Beatriz P. Sadovnychiy, Sergiy Inst Politecn Nacl ESIME Culhuacan Ciudad De Mexico Mexico Inst Mexicano Petr Ciudad De Mexico Mexico

ISBN: (纸本)9781510673199;9781510673182

Super resolution (SR) is a technique designed for increasing the spatial resolution in an image from a low resolution (LR) to high resolution (HR) size. SR technology has had a considerable demand in a wide variety of applications to recover HR images, such as medicine, engineering, computer vision, pattern recognition and video production, etc. In contrast to interpolation-based algorithms that often introduce distortions or irregular borders, this study proposes an implementation that can preserve the edges and fine details of an original image through the computation of the wavelet decomposition. Different Discrete Wavelet Transform (DWT) families such as: Daubechies, Symlet, and Coiflet were evaluated. The proposed system was implemented on a Raspberry Pi 4 model B, an embedded device, to get around the PC's mobility limitations, making it possible to create an in-expensive and energy- efficient SR system, reducing their complexity in realtime applications. To investigate the visual performance, SR images have been analysed in subjective matter via human perception view, guaranteeing good perception for the images of different nature from three different datasets such as FullHD (DIV2K), medical (Raabin WBC), and remote sensing (Sentinel- 1). The experimental results of designed implementations appear to demonstrate good performance in commonly used objective criteria: execution time, SSIM, and PSNR (0.742 sec., 0.9164, and 38.72 dB), respectively for images with a super resolution size of 1356 x 2040 pixels.

关键词： Super resolution Discrete Wavelet Transform (DWT) Parallel programing Raspberry Pi real-time processing

来源：评论

学校读者我要写书评

暂无评论

SkyPole: a geolocation algorithm based on polarized vision without using astronomical ephemerides 16

SkyPole: a geolocation algorithm based on polarized vision w...

引用

Conference on Polarization - Measurement, Analysis, and remote sensing XVI

作者： Kronland-Martinet, Thomas Poughon, Leo Pasquinelli, Marcel Duche, David Serres, Julien R. Viollet, Stephane Aix Marseille Univ CNRS ISM Marseille France Aix Marseille Univ CNRS IM2NP Marseille France Inst Univ France IUF Paris France

ISBN: (纸本)9781510674196;9781510674189

Global Navigation Satellite Systems (GNSS) are widely used due to their easy access to outdoor GNSS signals and their spatial precision. However, such systems are sensitive to jamming and spoofing. Simple and robust navigation strategies can be found in animals deprived by essence of any GNSS system. Studies have shown that animals like bees or ants utilize the sky's polarization pattern for navigation. We recently proposed a method inspired by migratory birds, which calibrate their magnetic compass through the celestial rotation of night stars or the daytime polarization pattern. By considering the temporal properties of the sky's polarization pattern as a relevant navigation information, we developed a bio-inspired method to find the geographical north bearing and the observer's latitude, requiring only skylight polarization observations during day. To reduce the noise susceptibility of our method, we added a pre-processing step using a least square method based on skylight polarization models, and a segmentation process based on a convolutional autoencoder neural network, trained with simulated data.

关键词： Celestial Navigation Celestial compass Polarized vision GPS-less geolocation image processing

来源：评论

学校读者我要写书评

暂无评论

remote sensing image building detection method based on Mask R-CNN

引用

COMPLEX & INTELLIGENT SYSTEMS 2022年第3期8卷 1847-1855页

作者： Han, Qinzhe Yin, Qian Zheng, Xin Chen, Ziyi Beijing Normal Univ Sch Artificial Intelligence Image Proc & Pattern Recognit Lab Beijing Peoples R China

Quickly and conveniently identifying buildings in disaster areas plays an important role in disaster assessment. To achieve the technical requirements of flood disaster relief projects, this paper proposes a building extraction method for use with remote sensing images that combines traditional digital image processing methods and convolution neural networks. First, the threshold segmentation method is used to select and construct a training dataset. Then, a variety of preprocessing methods are used to enhance the selected dataset. Finally, the improved Mask R-CNN algorithm is used to detect buildings in the images. Experiments show that compared to the R-CNN algorithm, the proposed method improves detection accuracy and reduces the computational time.

关键词： Target detection remote sensing image Deep learning Mask R-CNN

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：