检索结果-内蒙古大学图书馆

1st International Conference on Machine Vision and image processing, MVIP 2020

作者： Maneshi, Mehran Ghassemian, Hassan Khademi, Ghassem Imani, Maryam Tarbiat Modares University Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9781728168326

Technical limitations on the satellite sensors make a trade-off between the spectral and spatial resolution in remotely sensed images. To deal with this issue, pansharpening has been emerged to prepare a single image with the high spatial and spectral resolution, simultaneously. This paper presents a pansharpening approach based on the retina-inspired model and the multiresolution analysis (MRA) framework. The retina- inspired model is simplified by the difference of Gaussian (DoG) operator, and we apply it to the panchromatic image to extract the spatial details. Furthermore, the injection gains in the MRA framework are calculated through an iterative process where the gains at each iteration are updated based on the fusion result obtained from its previous iteration. To investigate the performance of the proposed model, it is compared with some classical pansharpening approaches with two data sets captured by the GeoEye-1 and Pléiades satellite imagery sensors. The experimental results show the proposed retina-inspired pansharpening method acts well in injecting the spatial information along with reducing the spectral distortion. © 2020 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Anomaly Detection based on Frequency analysis of Repeated Spatial Patterns 1

Hyperspectral Anomaly Detection based on Frequency Analysis ...

引用

1st International Conference on Machine Vision and image processing, MVIP 2020

作者： Taghipour, Ashkan Ghassemian, Hassan Tarbiat Modares University Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9781728168326

Hyperspectral anomaly detection has brought significant attention to researchers during the last decade. In the remote sensing domain, it has lots of applications like environmental monitoring, mine source detection, human safety and, etc. Different methods have been proposed to overcome the challenges of anomaly detection, which mainly are a highly accurate detection rate and also having low false alarm rates. Background complexity of the hyperspectral data causes false detection of pixels as anomalies, and several statistical and sparse based methods try to solve it. However, the computation burden of the statistical and sparse based methods make them unpractical. Also, they often do not utilize the spatial information of hyperspectral data for increasing the detection accuracy. In this paper, we proposed a frequency analysis based approach that suppresses the repeatable patterns of the scene which mainly represent the background and considers the remainder regions as anomalies. Owe to the Fourier analysis advantage, it fast and accurate detects anomalous regions. Two well-known data sets have been chosen to challenge the potency of the proposed method, and the results are compared with some state-of-the-art methods. The visual and quantitative results confirm the supremacy of the proposed method to competitors in computation complexity and detection accuracy point of view. © 2020 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A New Spectral-Spatial Network for Feature Fusion and Classification of Hyperspectral images

A New Spectral-Spatial Network for Feature Fusion and Classi...

引用

International Conference of Signal processing and Intelligent Systems (ICSPIS)

作者： Mohamad Ebrahim Aghili Hassan Ghassemian Maryam Imani Image processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (纸本)9781665409391

Hyperspectral image (HSI) classification is one of the most important applications among all types of classification fields. Proper classification of spectral data leads to discovery of important land covers. In recent years, many methods have been introduced to increase the HSI classification accuracy. Methods based on neural networks show superior results compared to other methods. Among them, the two-dimensional convolutional neural networks (2D-CNNs) inspired by the human eye retina have achieved higher accuracy in classification. In most cases, HSI classifiers use only spectral features. In this paper, the spectral-spatial feature fusion and HSI classification using 2D-CNN are focused. For this purpose, the first 2D-convolutional layer of CNN is substituted by two combined 2D-Gabor-Shapelet filter banks. This layer extracts contextual information and provides valuable joint spectral-spatial features. The experimental results on real HSI (including the urban and agricultural areas and their mixture) show that the proposed method improves the overall classification performance. Compared to several famous HSI classification based on neural networks, the proposed method has higher speed and classification accuracy.

关键词： Training Neural networks Signal processing Feature extraction Retina Convolutional neural networks Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 297-308页

作者： Zhang, Chongsheng Tao, Yuefeng Du, Kai Ding, Weiping Wang, Bin Liu, Ji Wang, Wei Henan Provincial Key Laboratory of Big Data Analysis and Processing Laboratory of the Yellow River Cultural Heritage Henan University Kaifeng475001 China School of Information Science and Technology Nantong University Nantong226019 China School of Electrical Engineering Zhejiang University Hangzhou310058 China Big Data Lab Baidu Inc. Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Urban scenes are full of street entities with sign boards. Therefore, in autonomous driving, street view text spotting techniques will play a significant role in the precise understanding of surrounding scenes during driving, because texts contained in the images usually provide important clues for accurate image understanding, while it is often ambiguous for existing computer vision algorithms to understand scene images without texts. In this work, we propose a Multi-Segmentation network for character-level scene Text Detection (MSTD). The MSTD introduces a densely connected atrous spatial pyramid pooling module to enlarge the receptive field of the feature extraction layer, so as to localize long as well as large-sized text instances. Moreover, it devises a double segmentation subnetwork to utilize two independent but inherently complementary losses to co-optimize the network and increase the reliability of the confidence scores in predicting the text/nontext areas. With the character instances detected by the MSTD, one can easily perform scene text spotting with classic object recognition networks such as ResNet and DenseNet. We carried out extensive experiments on nine scene text datasets to demonstrate the outstanding performance of the MSTD on character-level and line-level text instance localization and scene text recognition, where the MSTD significantly outperforms the state-of-the-art scene text detection methods and the sequence-to-sequence-learning-based scene text recognizers. © 2020 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Pansharpening Methods Based on a Redundant Contourlet Transform

Pansharpening Methods Based on a Redundant Contourlet Transf...

引用

Earth Observation and Geo-Spatial information (ICEOGI), International Conference on

作者： Soumeya Ourabia Nadia Baaziz Youcef Smara Departement of Electronics University Center of Tipaza -Morsli Abdelah-Institut of Sciences Laboratory of Image Processing and Radiation -USTHB Tipaza Algeria Department of Computer Science and Engineering Research Laboratory in Multimedia Information University of Quebec in Outaouais - UQO Gatineau Québec Canada Laboratory of Image Processing and Radiation Faculty of electrical engineering University of Sciences and Technology Houari Boumediene -USTHB Algiers Algeria

The pansharpening of high-resolution panchromatic (Pan) image and low-resolution multispectral (MS) images represents an important task in the remote sensing field. It allows the joint exploitation of the information derived from both types of images. However, this may cause a distortion of spectral information or a lack in details and structures. The multiresolution analysis using wavelet transforms has proved its efficiency in the pansharpening domain, due to the representation of the image content over different resolution levels. In image fusion applications, we always need more detail information to be incorporated in the pansharpening procedure in order to produce enhanced results. However, the limitation of the wavelet transform to three types of oriented detail coefficients prevents this need from being met. To overcome this limitation, we propose to use the redundant contourlet transform (RCT) which extracts a richer multiscale directional information from the image. For this purpose, two RCT-based pansharpening methods are introduced and suitable data fusion procedures are described. We conducted several experiments on two different datasets acquired respectively by ALSAT-2A and IKONOS satellites. The visual results as well as quantitative results from evaluation metrics demonstrate the performance of the proposed methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Anomaly Detection based on Frequency analysis of Repeated Spatial Patterns

Hyperspectral Anomaly Detection based on Frequency Analysis ...

引用

Iranian Machine Vision and image processing (MVIP)

作者： Ashkan Taghipour Hassan Ghassemian Image Processing and Information Analysis Lab Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (数字)9781728168326

ISBN: (纸本)9781728168333

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Retina-Inspired Multiresolution analysis Framework for Pansharpening

A Retina-Inspired Multiresolution Analysis Framework for Pan...

引用

Iranian Machine Vision and image processing (MVIP)

作者： Mehran Maneshi Hassan Ghassemian Ghassem Khademi Maryam Imani Image Processing and Information Analysis Lab. Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (数字)9781728168326

ISBN: (纸本)9781728168333

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Representation of Injected Details for MRA-Based Pansharpening

Sparse Representation of Injected Details for MRA-Based Pans...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Mehran Maneshi Hassan Ghassemian Maryam Imani Image Processing and Information Analysis Lab. Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (数字)9781728131146

ISBN: (纸本)9781728131153

Pansharpening is a notable remote sensing topic in which high spatial resolution panchromatic image and low spatial resolution multi-spectral image are being fused in order to receive the high spatial resolution multi-spectral image. This paper presents a hybrid pansharpening method based on MRA framework and the sparse representation of injected details. To add spatial details of the panchromatic image into the multispectral image more effectively, the injection gains are computed through an iterative full-scale model in which the gains are updated at each iteration relying on its previous iteration's fusion product. The proposed method is compared with five pansharpening approaches to investigate the effectiveness. Experiments have been implemented on two data sets from the Pleiades and GeoEye-1 satellites both at reduced and full scale. In terms of visual and quantity assessment, the high-resolution MS image produced by the proposed method is more acceptable than those images fused by other rival approaches.

关键词： Visualization Satellites Computational modeling Pansharpening Sensors Spatial resolution Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Hyperspectral Target Detection Using Spectral Residual of Deep Autoencoder Networks 4

Unsupervised Hyperspectral Target Detection Using Spectral R...

引用

4th International Conference on Pattern Recognition and image analysis, IPRIA 2019

作者： Taghipour, Ashkan Ghassemian, Hassan Image Processing and Information Analysis Lab. Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (纸本)9781728116211

Unsupervised hyperspectral target detection has attracted considerable attention in different applicable fields like environmental protection, agriculture monitoring, human rescue and etc. Due to the complexity of the background of hyperspectral images, accurate detection of target pixels using background estimation are faces lots of challenges which cause low accurate detection rates and high false alarm rates. In this paper we proposed an approach to estimate the background using a deep autoencoder neural networks architecture, then spectral residual error between the original hyperspectral image and the estimated one is considered for target detection using an exponential function. For evaluating the effectiveness and potency of the proposed method, several experiments are carried out on the well-known and challenging Hyperion dataset and the results are compared with some state-of-the-art methods. The visual and quantitative assessments show how spectral residual point of view using autoencoder networks can make high detection rates and low false alarms simultaneously. © 2019 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

A Variational Pansharpening Algorithm Based on Total Variation and Primal-Dual Optimization 4

A Variational Pansharpening Algorithm Based on Total Variati...

引用

4th International Conference on Pattern Recognition and image analysis, IPRIA 2019

作者： Khademi, Ghassem Ghassemian, Hassan Image Processing and Information Analysis Lab. Faculty of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran

ISBN: (纸本)9781728116211

This paper proposes a variational framework to estimate the high-resolution (HR) multispectral (MS) image from the low-resolution (LR) MS image and the panchromatic (Pan) image. The LR MS image is modeled as a decimation of the HR MS image. Furthermore, the Pan image is considered as a linear combination of the HR MS bands. A super-resolution (SR) model is defined in accordance with the image observation model and the total variation (TV) regularization. The SR reconstruction problem is modeled as a minimization problem, which is solved by an efficient primal-dual algorithm in a Euclidean setting. The result of comparing the proposed method with some recent classical and variational pansharpening methods proves the superiority of the proposed variational pansharpening algorithm. © 2019 IEEE.

关键词： Remote sensing

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：