检索结果-内蒙古大学图书馆

28th SIBGRAPI conference on Graphics, patterns and images SIBGRAPI

作者： Nogueira, Keiller Miranda, Waner O. dos Santos, Jefersson A. Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte MG Brazil

ISBN: (纸本)9781467379625

The performance of image classification is highly dependent on the quality of extracted features. Concerning high resolution remote image images, encoding the spatial features in an efficient and robust fashion is the key to generating discriminatory models to classify them. Even though many visual descriptors have been proposed or successfully used to encode spatial features of remote sensing images, some applications, using this sort of images, demand more specific description techniques. Deep Learning, an emergent machine learning approach based on neural networks, is capable of learning specific features and classifiers at the same time and adjust at each step, in real time, to better fit the need of each problem. For several task, such image classification, it has achieved very good results, mainly boosted by the feature learning performed which allows the method to extract specific and adaptable visual features depending on the data. In this paper, we propose a novel network capable of learning specific spatial features from remote sensing images, with any pre-processing step or descriptor evaluation, and classify them. Specifically, automatic feature learning task aims at discovering hierarchical structures from the raw data, leading to a more representative information. This task not only poses interesting challenges for existing vision and recognition algorithms, but also brings huge opportunities for urban planning, crop and forest management and climate modelling. The propose convolutional neural network has six layers: three convolutional, two fully-connected and one classifier layer. So, the five first layers are responsible to extract visual features while the last one is responsible to classify the images. We conducted a systematic evaluation of the proposed method using two datasets: (i) the popular aerial image dataset UCMerced Land-use and, (ii) a multispectral high-resolution scenes of the Brazilian Coffee Scenes. The experiments show that the pro

关键词： Deep Learning remote sensing Feature Learning image Classification Machine Learning High-resolution images

来源：评论

学校读者我要写书评

暂无评论

Medical image Registration Based on Grid Matching using Hausdorff Distance and Near set 8

Medical Image Registration Based on Grid Matching using Haus...

引用

8th International conference on Advances in pattern recognition (ICAPR)

作者： Biswas, Biswajit Dey, Kashi Nath Chakrabarti, Amlan Univ Calcutta Dept Comp Sci & Engn Kolkata 700073 W Bengal India Univ Calcutta AKCSIT Kolkata 700073 W Bengal India

ISBN: (纸本)9781479974580

image registration is a method that resolves the discrepancy between spatial alignments of two or more images having an identical view, taken at different times, from different viewpoints and by different image sensors. It is extensively used in many image processing tasks such as medical imaging, remote sensing, military applications and so on. In this work, we propose a new automated image registration method based on virtual grid generation and coequal feature vector matching. Firstly, corners are extracted by Harris corner detector as feature points and are constructed as a collection of virtual grid from the desired corner points. The virtual grids are compared in the source and target images using coequal feature vectors. Two congruent virtual grids are taken from the source and target image. The image transformation parameters are selected from the corresponding grid points. Once feature selection is over, congruent virtual grids are established. Hausdorff Distance and Near set is used to get the correspondence and intensity variation. The experimental results show that the proposed technique is more accurate with respect to the existing state of the art research work.

关键词： image registration Harris corner detector Virtual grid Hausdorff distance Near set Affine transformation

来源：评论

学校读者我要写书评

暂无评论

Cross correlation based clustering for feature selection in hyperspectral imagery 9

Cross correlation based clustering for feature selection in ...

引用

9th International conference on Electrical and Electronics Engineering, ELECO 2015

作者： Çukur, Hüseyin Binol, Hamidullah Uslu, Faruk Sukru Kalayci, Yusuf Bal, Abdullah Department of Electronics and Communications Engineering Yildiz Technical University Istanbul34220 Turkey

ISBN: (纸本)9786050107371

One of the main problems with hyperspectral image processing is to be contained large amount of data. Furthermore, pattern recognition methods are highly sensitive to problems related to high dimensional feature spaces. Therefore, feature selection in hyperspectral remote sensing data is investigated by researchers. This paper propose a clustering strategy that divides a feature set into subsets within which features are closely related to each other by means of cross correlation between all spectral bands. After that a band selection strategy based on Minimum Redundancy Maximum Relevance (mRMR) eliminates redundant bands into band clusters. The effectiveness of the proposed method is carried out on a real hyperspectral data set. The obtained results clearly affirm the superiority of the proposed method. © 2015 Chamber of Electrical Engineers of Turkey.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Classifying Grasslands and Cultivated Pastures in the Brazilian Cerrado Using Support Vector Machines, Multilayer Perceptrons and Autoencoders 11th

Classifying Grasslands and Cultivated Pastures in the Brazil...

引用

11th International conference on Machine Learning and Data Mining (MLDM)

作者： Costa, Wanderson Fonseca, Leila Koerting, Thales Natl Inst Space Res Image Proc Div Sao Jose Dos Campos SP Brazil

ISBN: (纸本)9783319210247;9783319210230

One of the most biodiverse regions on the planet, Cerrado is the second largest biome in Brazil. Among the land changes in the Cerrado, over 500,000km(2) of the biome have been changed into cultivated pastures in recent years. Categorizing types of land cover and its native formations is important for protection policy and monitoring of the biome. Based on remote sensing techniques, this work aims at developing a methodology to map pasture and native grassland areas in the biome. Data related to EVI vegetation indices obtained by MODIS images were used to perform image classification. Support Vector Machine, Multilayer Perceptron and Autoencoder algorithms were used and the results showed that the analysis of different attributes extracted from EVI indices can aid in the classification process. The best result obtained an accuracy of 85.96% in the study area, identifying data and attributes required to map pasture and native grassland in Cerrado.

关键词： Data mining image processing Brazilian cerrado Support vector machine Multilayer perceptron Autoenconder

来源：评论

学校读者我要写书评

暂无评论

Periodic pattern enhancement: A stochastic resonance approach

Periodic pattern enhancement: A stochastic resonance approac...

引用

IEEE International conference on Signal processing, Communications and Computing (ICSPCC)

作者： Zelong Wang Meihua Xie Jubo Zhu Department of Mathematics and System Science National University of Defense Technology Changsha China

ISBN: (纸本)9781479989218

This paper investigates two basic problems about the periodic pattern in pattern recognition and artificial intelligence: weak periodic pattern and the noise. We make use of stochastic resonance (SR) theory to enhance periodic pattern by transferring the noise energy to the pattern energy, which not only removes the noise but also improves the periodic pattern intensity. We firstly analyze the basic principle of the energy transfer by SR theoretically; and then, we design the optimized SR nonlinear system to enhance the periodic pattern; finally, we apply the proposed method to two popular periodic patterns, i.e., the texture pattern of the optical remote sensing image and the spatial pattern of the fingerprint image. The experiments have a good performance and the proposed method can be extended to wider applications of periodic pattern enhancement.

关键词： Fingerprint recognition Signal to noise ratio image matching Nonlinear systems Optimization Optical filters Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Signal processing for underwater archaeology 5

Signal processing for underwater archaeology

引用

5th International Workshop on image Mining. Theory and Applications, IMTA-5 2015 - In conjunction with the 10th Internatioanal Joint conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2015

作者： Moroni, Davide Pascali, Maria Antonietta Reggiannini, Marco Salvetti, Ovidio SILab Institute of Information Science and Technololgies - CNR Via G. Moruzzi 1 Pisa56124 Italy

ISBN: (纸本)9789897580949

About three million wrecks lie scattered on the oceans' seafloors. This huge patrimony is actually threatened by criminal enterprises having advanced tools available for localization and rescue operations. ARROWS, a currently ongoing EU FP7 project, is an example of the effective commitment between cultural institutions and the scientific community towards the safeguard of the sunken cultural heritage. ARROWS is devoted to advanced technologies and tools for mapping, diagnosing, cleaning, and securing underwater and coastal archaeological sites. A fleet of Autonomous Underwater Vehicles (AUVs) will be manufactured with the purpose of surveying the seabed and sensing the underwater environment by means of proper payload sensors (digital cameras, side scan and multi-beam sonars). This paper describes a set of underwater scene understanding procedures specifically tailored to the purposes addressed in the ARROWS frame. In particular the data collected by the AUVs during the acquisition campaigns will be processed to detect targets of interest located on the seabed. The main approach adopted in the object detection procedures is to highlight the amount of regularity in the captured data. This can be pursued by exploiting computer vision algorithms that perform i) the recognition of geometrical curves ii) the classification of seafloor areas by means of textural pattern analysis iii) a large scale map generation to return an overall view of the site and iv) a reliable object recognition process performing the integration of the available multi modal information. Moreover the collected raw data together with the analysis output results will be stored to allow for an offline deep analysis of the archaeological findings. This will represent a powerful tool to be used by expert users or by the general public to enjoy the underwater cultural heritage.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Use of fractal models in the Earth’s remote sensing of the arctic zone

引用

AIP conference Proceedings 2016年第1期1789卷

作者： D. B. Berg A. N. Medvedev I. L. Manzhurov A. A. Taubaev 1Graduate School of Economics and Management Ural Federal University Mira 19 Ekaterinburg RUSSIA 620002 2Institute of Industrial Ecology UB RAS Sophy Kovalevskoy 20 Ekaterinburg RUSSIA 620990 3Karaganda Economic University of Kazpotrebsoyuz Karaganda Republic of Kazakhstan

The development and practical application of new mathematical methods of processing, image analysis and pattern recognition has significant prospects for mapping the Earth from space. In the paper, it is proposed to use the fractal model of the surface contamination distribution, previously developed by the authors, for the analysis of color multispectral satellite images on the example of the territory of the Polar Urals. The research has shown the following: 1) The brightness distribution on remote sensing snapshot has a fractal character. 2) The values of fractal dimension of the territory images in different spectral ranges significantly differ. 3) The hierarchy of geomorphological structures in the range of 13-1700 m may be considered as self-similar. Thus, the proposed method of calculating the fractal dimension value of the snapshot may become one of the informative attributes for remote sensing images interpretation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thermal infrared hyperspectral dimension reduction experiment results for global and local information based linear discriminant analysis

Thermal infrared hyperspectral dimension reduction experimen...

引用

IEEE Signal processing and Communications Applications (SIU)

作者： Ufuk Sakarya TÜBİTAK UZAY ODTÜ Yerleşkesi 06800 Ankara Turkey

Thermal infrared hyperspectral image processing has become an important research topic in remote sensing. One of the research topics in thermal infrared hyperspectral image classification is dimension reduction. In this paper, thermal infrared hyperspectral dimension reduction experiment results for global and local information based linear discriminant analysis is presented. Advantages of the use of not only global pattern information, but also local pattern information are tested in thermal infrared hyperspectral image processing.

关键词： Hyperspectral imaging Linear discriminant analysis Principal component analysis Data integration pattern recognition Thermal analysis

来源：评论

学校读者我要写书评

暂无评论

Medical image registration based on grid matching using Hausdorff Distance and Near set

Medical image registration based on grid matching using Haus...

引用

International conference on Advances in pattern recognition (ICAPR)

作者： Biswajit Biswas Kashi Nath Dey Amlan Chakrabarti Department of Computer Science and Engineering University of Calcutta AKCSIT University of Calcutta

关键词：

来源：评论

学校读者我要写书评

暂无评论

Road segmentation using multipass single-pol synthetic aperture radar imagery

Road segmentation using multipass single-pol synthetic apert...

引用

IEEE Computer Society conference on Computer Vision and pattern recognition Workshops (CVPRW)

作者： Mark W. Koch Mary M. Moya Jim G. Chow Jeremy Goold Rebecca Malinas Sandia National Laboratories Albuquerque NM

Synthetic aperture radar (SAR) is a remote sensing technology that can truly operate 24/7. It's an all-weather system that can operate at any time except in the most extreme conditions. By making multiple passes over a wide area, a SAR can provide surveillance over a long time period. For high level processing it is convenient to segment and classify the SAR images into objects that identify various terrains and man-made structures that we call “static features.” In this paper we concentrate on automatic road segmentation. This not only serves as a surrogate for finding other static features, but road detection in of itself is important for aligning SAR images with other data sources. In this paper we introduce a novel SAR image product that captures how different regions decorrelate at different rates. We also show how a modified Kolmogorov-Smirnov test can be used to model the static features even when the independent observation assumption is violated.

关键词： Roads Synthetic aperture radar image segmentation Speckle Optimization image resolution image edge detection

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：