检索结果-内蒙古大学图书馆

17th Chinese Conference on image and Graphics Technologies and Applications, IGTA 2022

作者： Liu, Limin Li, Dingzhe Li, Zhaoxi Meng, Cai The Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China Image Processing Center Beijing University of Aeronautics and Astronautics Beijing100191 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100083 China

ISBN: (纸本)9789811950957

Line and ellipse are important image features in pattern recognition and computer vision. Many methods have been developed to extract line or ellipse in images separately but few try to detect them simultaneously. In this paper, a novel fast line and ellipse detection (FLED) method is proposed to detect line and ellipse simultaneously, even in high resolution images. At first, a detection framework (Pre-SGV) for high detection speed is proposed, which explicitly decomposes the detection into precalculate, segment, grouping, validation phases. Secondly, a simple but efficient algorithm is designed to segment the edges into line or arc candidates. Thirdly, the grouping constraints and fitting methods are further improved. Finally, validation are conducted to exclude erroneous detection. Experiments on synthetic images and real image dataset show that the proposed method, FLED, can robustly detect lines and ellipses fast and efficiently, especially for high resolution image (e.g. remote sensing image, the scanning image). © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Comparative Performance of Maximum Likelihood and Minimum Distance Classifiers on Land Use and Land Cover Analysis of Varanasi District (India) 1

引用

2nd International Conference on Advanced Network Technologies and Intelligent Computing (ANTIC)

作者： Kumari, Annu Karthikeyan, S. Banaras Hindu Univ Dept Comp Sci Varanasi 221005 Uttar Pradesh India

ISBN: (数字)9783031281839

ISBN: (纸本)9783031281822;9783031281839

Monitoring the Land Use/Land Cover (LULC) changes in this present era has become the most demanding task and it is very crucial for planning, proper resource management, regulating the expansion in the fringe areas in the existing cities, etc. Now the collection of reliable data has become easier as the hyperspectral images captured by various remote sensing satellites are readily available in different spatial and spectral resolutions. processing this data according to the Region of Interest (ROI) in order to extract meaningful information is challenging. The most crucial part of this process is to identify various land covers very accurately. Only an automatic classification provides a feasible solution, as the manual process is tedious, expensive, and time-consuming. This paper compares two different image classification algorithms in classifying the covers, which can be utilized for land use and land cover changing pattern analysis in the Varanasi district of India. The experiments were carried out with the two most popular classification algorithms, namely: The Maximum Likelihood classifier and the Minimum Distance classifier. The overall accuracy and kappa co-Efficient values computed are 41.67 and 0.12 for the Minimum Distance Classifier and 82.43 and 0.78 for the Maximum Likelihood Classifier. It has been observed that the Maximum Likelihood Classifier outperforms the Minimum Distance Classifier.

关键词： Land use/land cover remote sensing image classifier Geographic information analysis

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Material and Texture Representation Learning for remote sensing Tasks

Self-Supervised Material and Texture Representation Learning...

引用

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

作者： Akiva, Peri Purri, Matthew Leotta, Matthew Rutgers State Univ New Brunswick NJ 08854 USA Kitware Inc Clifton Pk NY USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Self-supervised learning aims to learn image feature representations without the usage of manually annotated labels. It is often used as a precursor step to obtain useful initial network weights which contribute to faster convergence and superior performance of downstream tasks. While self-supervision allows one to reduce the domain gap between supervised and unsupervised learning without the usage of labels, the self-supervised objective still requires a strong inductive bias to downstream tasks for effective transfer learning. In this work, we present our material and texture based self-supervision method named MATTER (MATerial and TExture Representation Learning), which is inspired by classical material and texture methods. Material and texture can effectively describe any surface, including its tactile properties, color, and specularity. By extension, effective representation of material and texture can describe other semantic classes strongly associated with said material and texture. MATTER leverages multi-temporal, spatially aligned remote sensing imagery over unchanged regions to learn invariance to illumination and viewing angle as a mechanism to achieve consistency of material and texture representation. We show that our self-supervision pretraining method allows for up to 24.22% and 6.33% performance increase in unsupervised and fine-tuned setups, and up to 76% faster convergence on change detection, land cover classification, and semantic segmentation tasks. Code and dataset: https : // github. com / periakiva/MATTER.

关键词： Representation learning Satellites Semantics Transfer learning Self-supervised learning Surface texture Task analysis

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Vision Transformers for Land-cover Segmentation and Classification

Self-supervised Vision Transformers for Land-cover Segmentat...

引用

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

作者： Scheibenreif, Linus Hanna, Joelle Mommert, Michael Borth, Damian Univ St Gallen AIML Lab Sch Comp Sci Rosenbergstr 30 St Gallen Switzerland

ISBN: (纸本)9781665487399

Transformer models have recently approached or even surpassed the performance of ConvNets on computer vision tasks like classification and segmentation. To a large degree, these successes have been enabled by the use of large-scale labelled image datasets for supervised pre-training. This poses a significant challenge for the adaption of vision Transformers to domains where datasets with millions of labelled samples are not available. In this work, we bridge the gap between ConvNets and Transformers for Earth observation by self-supervised pre-training on large-scale unlabelled remote sensing data(1). We show that self-supervised pre-training yields latent task-agnostic representations that can be utilized for both land cover classification and segmentation tasks, where they significantly outperform the fully supervised baselines. Additionally, we find that subsequent fine-tuning of Transformers for specific downstream tasks performs on-par with commonly used ConvNet architectures. An ablation study further illustrates that the labelled dataset size can be reduced to one-tenth after self-supervised pre-training while still maintaining the performance of the fully supervised approach.

关键词： Training Earth Computer vision image segmentation Computational modeling Conferences Transformers

来源：评论

学校读者我要写书评

暂无评论

Deep image Interpolation: A Unified Unsupervised Framework for Pansharpening

Deep Image Interpolation: A Unified Unsupervised Framework f...

引用

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

作者： Gao, Jianhao Li, Jie Su, Xin Jiang, Menghui Yuan, Qiangqiang Wuhan Univ Wuhan Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Pansharpening, whose aim is to acquire high resolution multispectral data (HRMS) by the fusion of low resolution multispectral data (LRMS) and panchromatic data (PAN), is a specific mission of spatial-spectral fusion in remote sensing field. In recent years, deep learning methods have proved the most feasible methods for pansharpening task. However, these deep learning methods have difficulty in training in an unsupervised manner and become useless when it comes to the condition where no training dataset is available. In this paper, we propose a universal algorithm called deep image interpolation for pansharpening task. The main idea is achieving high-quality fusion results by interpolating two low-quality multispectral images in a deep neural network. We apply it to two conditions: 1) unsupervised training a network when there are enough datasets;2) directly optimizing the fusion result where no training datasets are available. Simulation and real-data experiments are conducted on various kinds of satellite data. Quantitative and qualitative evaluation results illustrate that the proposed method outperforms traditional pansharpening methods and even catch up with those supervised methods to some extent.

关键词： Training Deep learning Interpolation Satellites Neural networks Data integration Pansharpening

来源：评论

学校读者我要写书评

暂无评论

A fast bundle adjustment method based on track selection 4

A fast bundle adjustment method based on track selection

引用

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

作者： Liu, Changwei Xiong, Pingfan Yang, Luman Chen, Song Hu, Jinquan School of Remote Sensing and Information Engineering Wuhan University Hubei Wuhan430072 China School of Geodesy and Geomatics Wuhan University Hubei Wuhan430072 China Guangdon Shenzhen518000 China Wuhan Tianjihang Information Technology Co. Ltd. Hubei Wuhan430074 China

ISBN: (纸本)9781510682528

Bundle adjustment is the core of the Structure from Motion algorithm, and it is also a very time-consuming part, in which redundant observations and initial parameter values with large errors increase the time consumption of the algorithm. In order to improve the efficiency of bundle adjustment, we propose an track selection method based on uniformity, accuracy, coverage and connectivity criteria. Firstly, we divide the space of tracks into several 3D grids. Secondly, we start from the grid with the largest number of tracks, and eliminate the redundant tracks with low connectivity and low accuracy in each grid, while ensuring the connectivity and coverage of tracks. Finally, we use a variety of experimental data to verify this algorithm. The result shows that the algorithm can delete a large number of redundant tracks, and effectively improve the efficiency of the bundle adjustment method on the premise of ensuring the accuracy. When the track retention rate is 0.4, the efficiency of the bundle adjustment method is increased by about 2 times, and the corresponding precision loss value is 0.026. © 2024 SPIE.

关键词： Tunable filters 3D tracking image restoration Point clouds 3D image reconstruction image filtering image processing Pose estimation 3D modeling Atomic force microscopy

来源：评论

学校读者我要写书评

暂无评论

Rethinking Transformers Pre-training for Multi-Spectral Satellite imagery

Rethinking Transformers Pre-training for Multi-Spectral Sate...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Mubashir Noman Muzammal Naseer Hisham Cholakkal Rao Muhammad Anwar Salman Khan Fahad Shahbaz Khan Mohamed bin Zayed University of AI Australian National University Linkoping University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multi-scale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. Sat-MAE++ achieves mean average precision (mAP) gain of 2.5% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at https://***/techmn/satmae_pp.

关键词： image resolution Transformers Optical imaging Satellite images pattern recognition Optical sensors remote sensing

来源：评论

学校读者我要写书评

暂无评论

recognition of wheat rusts in a field environment based on improved DenseNet

引用

BIOSYSTEMS ENGINEERING 2024年 238卷 10-21页

作者： Chang, Shenglong Yang, Guijun Cheng, Jinpeng Fan, Zehua Ma, Xinming Li, Yong Yang, Xiaodong Zhao, Chunjiang Henan Agr Univ Coll Agron Zhengzhou 450002 Peoples R China Beijing Acad Agr & Forestry Sci Informat Technol Res Ctr Key Lab Quantitat Remote Sensing Agr Minist Agr & Rural Affairs Beijing 100097 Peoples R China

Currently, the main methods for detecting plant diseases are sampling and manual visual inspection. However, these methods are time-consuming, laborious and prone to misinterpretation. Rapid advances in Deep Learning (DL) techniques offer new possibilities. This study focused on analysing the confounding factors among three types of wheat rust (stripe rust, leaf rust and stem rust) and aimed to achieve higher classification accuracy. The following approaches were used: (1) images were collected from several crops and diseases: Wheat Rusts Dataset (WRD), Wheat Common Disease Dataset (WDD), and Common Poaceae Disease Dataset (PDD);(2) Seven common convolutional neural network (CNN) models were made and their performance compared. DenseNet121 was selected as the base model, and its classification results further analysed. The results of the above analyses were then considered using phenotypic morphology and model structure analysis, as well as potential confounder discussions;(3) Adjustments and optimisations were made based on the identified confounding factors. The final improved model, designated Imp-DenseNet, achieved the following accuracies with different datasets: Top-1 accuracy = 98.32% (WRD), Top-3 accuracy = 97.30% (WDD) and Top-5 accuracy = 96.60% (PDD) (Top-x Accuracy refers to the accuracy of the top-ranked category that matches or containing the actual results). The study revealed the potential factors contributing to the confusion among the three wheat rusts and successfully achieved higher accuracy. It can provide a new perspective for future research on other diseases of wheat or other crops.

关键词： Plant disease Wheat rust image processing Deep learning Computer vision (CV) DenseNet

来源：评论

学校读者我要写书评

暂无评论

Dual-strategy semi-supervised learning method based on GAN for recognition of tomato leaf diseases

引用

INTERNATIONAL JOURNAL OF remote sensing 2022年第13期43卷 5025-5039页

作者： Tao, Wentao Ma, Junjie Shi, Jinpeng Lv, Wenbing Zhao, Mingyue Zheng, Ling Huang, Linsheng Weng, Shizhuang Anhui Univ Natl Engn Res Ctr Agroecol Big Data Anal & Applic Hefei Peoples R China

Machine vision can provide a convenient and intelligent recognition for tomato leaf diseases. However, limited labelled images affect the performance of such a method to a considerable extent. This study proposes a dual-strategy semi-supervised learning method for recognizing tomato leaf diseases when labelled images are insufficient. One of the dual strategies attaches an additional classifier C to the generative adversarial network (GAN) to construct a semi-supervised learning method (GANC) which generates artificial images to tune itself based on the labelled images with the label removal, and the high confidence pseudo-label comes from the classifier prediction. For the other strategy, the discriminator of the pretrained GAN continues to modify the output as authenticity and class probability (D-GAN), and unlabelled images are integrated to optimize the network. Then, the predicted results of GANC and D-GAN are combined to construct the dual-strategy semi-supervised learning method (GANC - D-GAN). GANC could generate new unlabelled images with a similar data distribution as real disease images and obtain an accuracy of 84.06% in the prediction set (ACC(p)), and D-GAN utilizes exiting unlabelled images to obtain an ACC(P) with 85.31%, outperforming supervised learning with a small number of labelled images. With image augmentation, the ACC(p) of GANC and D-GAN increases to 88.13% and 90.00%, respectively. GANC - D-GAN can achieve an accuracy of 90.62%, which is better than those of the two individual strategies as GANC and D-GAN. Thus, the proposed dual-strategy semi-supervised learning method could offer accurate disease recognition even if the available labelled images are insufficient.

关键词： image processing Agriculture Semi-supervised learning Dual-strategy recognition Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

image processing and Control of Tracking Intelligent Vehicle Based on Grayscale Camera 5

Image Processing and Control of Tracking Intelligent Vehicle...

引用

5th IEEE International Conference on image processing Applications and Systems (IPAS)

作者： Zhang, Jian Liu, Yufan Li, Ao Zeng, Jinshan Xie, Hongtu Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen Campus Shenzhen Peoples R China Nanchang Hangkong Univ Sch Informat Engn Nanchang Jiangxi Peoples R China

ISBN: (纸本)9781665462198

In order to realize the rapid and stable recognition and automatic tracking of various complex roads by the intelligent vehicles, this paper proposes image processing and cascade Proportion Integration Differentiation (PID) steering and speed control algorithms based on CMOS grayscale cameras in the context of the national college student intelligent vehicle competition. First, the grayscale image of the track is acquired by the grayscale camera. Then, the Otsu method is used to binarize the image, and the information of black boundary guide line is extracted. In order to improve the speed of the race, various track elements in the image are identified and classified, and the deviation between the actual centerline position and the ideal centerline position of the intelligent vehicle is calculated. Third, the discrete incremental cascade PID control algorithm is used to calculate the pulse width modulation (PWM) signal corresponding to the deviation. And the PWM signal is acted on the steering motor through the driving circuit, driving the intelligent vehicle to always drive along the middle road, so as to achieve the purpose of automatic tracking guidance. Experiments prove that the intelligent vehicle of this design can identify complex roads quickly and in a stable way, accurately complete automatic tracking, and obtain higher speed performance.

关键词： tracking intelligent vehicle proportional integral derivative control CMOS grayscale camera binary image image processing

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：