检索结果-内蒙古大学图书馆

An automated seamless mosaicing system of multi-charge coupled devices of panchromatic data

Journal of the Indian Society of Remote Sensing 2004年第1期32卷 103-111页

作者： Ramakrishnan, R. Manthira Moorthi, S. Padmanabhan, N. Gupta, P. Data Products Software Division Signal and Image Processing Group Space Applications Centre (ISRO) Ahmedabad-380 015 India Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur 208 016 India

Panchromatic data of pixel resolution 5.8 m obtained from IRS-IC and IRS-ID satellites proved to be very useful for mapping purposes. One of the popular data product is the 70 km swath mosaic which is covered by a combination of 3 CCD line sensors, each with 4096 pixels. Each CCD-line sensor with different imaging times causes geometric problems of mosaicing three strips data together. In this paper, we propose the details of the design elements of system that caters to the need for accurate and automatic multi strip image registration without any second resampling of the data. The systematic geometric correction grid mapping is improved to facilitate accurate mosaicing by automatic image registration task that makes use of the overlap data within image strips and image registration is achieved up to sub-pixel level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning for location recognition from wearable video

Semi-supervised learning for location recognition from weara...

引用

International Workshop on Content-Based Multimedia Indexing, CBMI

作者： Vladislavs Dovgalecs Rémi Megret Hazem Wannous Yannick Berthoumieu Signal and Image Processing Group IMS Laboratory University of Bordeaux 1 France

ISBN: (纸本)9781424480289;9781424480272

This paper tackles the problem of image-based indoor location recognition. The context of the present work is activity monitoring using a wearable video camera data. Because application constraints necessitate weak supervision, a semi-supervised approach has been adopted which leverages the large amount of unlabeled images. The proposed method is based on the Bag of Features approach for image description followed by spectral dimensionality reduction in a transductive setup. Additional information from geometrical verification constraints are also considered which allowed to reach higher performance levels. The considered algorithms are compared experimentally on the data acquired in the wearable camera setup.

关键词： Semisupervised learning image recognition Biomedical monitoring Cameras Histograms image databases Extraterrestrial phenomena Principal component analysis Linear discriminant analysis signal processing

来源：评论

学校读者我要写书评

暂无评论

The generalized sidelobe decorrelator

The generalized sidelobe decorrelator

引用

IEEE Workshop on Applications of signal processing to Audio and Acoustics

作者： C. Fancourt L. Parra Adaptive Image & Signal Processing Group Sarnoff Corporation Princeton NJ USA

We introduce a new hybrid algorithm called the generalized sidelobe decorrelator (GSD) that combines elements of geometric beamforming and blind source separation. On the one hand, it is an extension of the generalized sidelobe canceller (GSC), also known as the Griffiths-Jim beamformer, from the standard criteria of power minimization to a decorrelation criteria. On the other hand, it can be seen as an extension of a particular blind source separation (BSS) algorithm for non-stationary signals to include prior information about the location of one of the sources. However, unlike GSC, performance does not degrade with leakage of the source outside the primary beam and, unlike BSS, it performs well independent of whether the sources are simultaneously active. This makes it ideal for noise reduction in a continuously running on-line operation. We demonstrate its superior performance in a real-room audio experiment.

关键词： Decorrelation Source separation Array signal processing Blind source separation Finite impulse response filter signal processing algorithms Sensor arrays Information geometry Adaptive signal processing Degradation

来源：评论

学校读者我要写书评

暂无评论

Is supervised learning with adversarial features provably better than sole supervision?

arXiv

引用

arXiv 2019年

作者： Rout, Litu Optical Data Processing Division Signal and Image Processing Group SAC ISRO Ahmedabad380015 India

Generative Adversarial Networks (GAN) have shown promising results on a wide variety of complex tasks. Recent experiments show adversarial training provides useful gradients to the generator that helps attain better performance. In this paper, we intend to theoretically analyze whether supervised learning with adversarial features can outperform sole supervision, or not. First, we show that supervised learning without adversarial features suffer from vanishing gradient issue in near optimal region. Second, we analyze how adversarial learning augmented with supervised signal mitigates this vanishing gradient issue. Finally, we prove our main result that shows supervised learning with adversarial features can be better than sole supervision (under some mild assumptions). We support our main result on two fronts (i) expected empirical risk and (ii) rate of convergence. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

The coherence function in blind source separation of convolutive mixtures of non-stationary signals

The coherence function in blind source separation of convolu...

引用

IEEE Workshop on Neural Networks for signal processing

作者： C.L. Fancourt L. Parra Adaptive Image & Signal Processing Group Sarnoff Corporation Princeton NJ USA

We propose a novel performance criteria and update mechanism for the blind decorrelation of an array of sensor measurements into independent sources, assuming each sensor measures a different convolutive mixture of statistically independent non-stationary sources. Specifically, the criteria is the sum of the magnitude squared coherence functions between all possible distinct pairs of outputs produced by a matrix of adaptable filters operating on the sensor measurements in the frequency domain. We then derive an efficient overlap-save online update equation based on stochastic gradient descent and recursive estimation of the coherence functions. We demonstrate separation within fractions of a second and convergence within a few seconds on real room recordings. We attribute this speed to the normalization and recursive estimates of the coherence functions.

关键词： Blind source separation Sensor arrays Recursive estimation Decorrelation Filters Sensor phenomena and characterization Frequency measurement Frequency domain analysis Equations Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Accelerated streak line computation using adaptive refinement

Accelerated streak line computation using adaptive refinemen...

引用

18th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2010

作者： Wiebel, Alexander Wang, Qin Schneider, Dominic Scheuermann, Gerik Max Planck Institute for Human Cognitive and Brain Sciences Stephanstraße 1A 04103 Leipzig Germany Image and Signal Processing Group University of Leipzig PF 100920 04009 Leipzig Germany

ISBN: (纸本)9788086943886

We introduce an improved algorithm for streak line approximation in 2D and 3D time-dependent vector fields. The algorithm is mainly based on iterative refinement of an initial coarse approximation of the streak line. The refinement process is steered by a predicate indicating the local approximation quality. We apply the algorithm to several real-world data sets to prove its applicability and robustness. An error analysis and a comparison show that the algorithm produces more accurate streak lines in shorter time compared to previous approaches. Finally we show how the new algorithm can help to improve the construction of streak surfaces.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A high resolution scintillator based SPECT detector with digital pulse processing (SPECTatress)

A high resolution scintillator based SPECT detector with dig...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Karel Deprez Roel Van Holen Steven Staelens Stefaan Vandenberghe Medical Image and Signal Processing group Ghent University IBBT Ghent Belgium

SPECT scanners using multi-pinhole collimators benefit from modular detectors having a high spatial resolution. Such detectors can be placed closer to the collimator and perpendicular to the pinhole axis (thereby limiting DOI spatial resolution degradation). Current clinical gamma ray cameras have a large area and a poor spatial resolution. This proceeding describes the architecture of SPECTatress, a modular high resolution gamma camera. A brief summary of the electronics and results obtained with the center-of-gravity positioning algorithm have been presented previously (Imaging 2010 conference, Stockholm). Here we present a detailed overview of the pre-amplifiers and the algorithms used in the FPGA. Results using a GPU accelerated MLE algorithm are shown. This measurement indicates a spatial resolution of 1.1mm FWHM in the center of the detector and an energy resolution of 9% FWHM.

关键词： Detectors Spatial resolution Maximum likelihood estimation Cameras Energy resolution Calibration Collimators

来源：评论

学校读者我要写书评

暂无评论

Geometric source separation: merging convolutive source separation with geometric beamforming

Geometric source separation: merging convolutive source sepa...

引用

IEEE Workshop on Neural Networks for signal processing

作者： L. Parra C. Alvino Adaptive Image & Signal Processing Group Sarnoff Corporation Princeton NJ USA

Blind source separation of broad band signals in a multi-path environment remains a difficult problem. Robustness has been limited due to frequency permutation ambiguities. Increasing the number of sensors allows improved performance but introduces degrees of freedom in the separating filters that are not determined by separation criteria. We propose to further shape the filters and improve the robustness of blind separation by including geometric information such as sensor positions and localized source assumption. This allows us to combine blind source separation with adaptive and geometric beamforming leading to a number of novel algorithms collectively termed "geometric source separation". Performance comparisons on real room recordings for 2 and 3 simultaneous sources are presented.

关键词： Source separation Merging Array signal processing Blind source separation Robustness Frequency Microphones Adaptive signal processing signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing image Resolution: A Simulation Study and Sensitivity Analysis of System Parameters for Resourcesat-3S/3SA

arXiv

引用

arXiv 2024年

作者： Garg, Ankur Sarkar, Meenakshi Moorthi, S.M. Dhar, Debajyoti Optical Data Processing Group Signal and Image Processing Area Space Applications Centre Ahmedabad India

Resourcesat-3S/3SA, an upcoming Indian satellite, is designed with Aft andFore payloads capturing stereo images at look angles of -5deg and 26deg,respectively. Operating at 632.6 km altitude, it features a panchromatic (PAN)band offering a Ground Sampling Distance (GSD) of 1.25 meters and a 60 kmswath. To balance swath width and resolution, an Instantaneous Geometric Fieldof View (IGFOV) of 2.5 meters is maintained while ensuring a 1.25-meter GSDboth along and across track. Along-track sampling is achieved through precisetiming, while across-track accuracy is ensured by using two staggered pixelarrays. signal-to-Noise Ratio (SNR) is enhanced through Time Delay andIntegration (TDI), employing two five-stage subarrays spaced 80 {\\mu}m apartalong the track, with a 4 {\\mu}m (0.5 pixel) stagger in the across-trackdirection to achieve 1.25-meter resolution. To further boost resolution, thesatellite employs super-resolution (SR), combining multiple low-resolutioncaptures using sub-pixel shifts to produce high-resolution images. Thistechnique, effective when images contain aliased high-frequency details,reconstructs full-resolution imagery using phase information from multipleobservations, and has been successfully applied in remote sensing missions likeSPOT-5, SkySat, and DubaiSat-1. A Monte Carlo simulation explores the factorsinfluencing the resolution in Resourcesat-3S/3SA, with sensitivity analysishighlighting key impacts. The simulation methodology is broadly applicable toother remote sensing missions, optimizing SR for enhanced image clarity andresolution in future satellite systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Classification of large and heterogeneous LiDAR data sets

Classification of large and heterogeneous LiDAR data sets

引用

2023 Designing Futures: Zukunfte gestalten, INFORMATIK 2023 - 2023 Designing Futures: Shaping the Future, INFORMATIK 2023

作者： Kaubukowski, Kenn Nsonga, Baldwin Kretzschmar, Vanessa Annanias, Yves Wiegreffe, Daniel Hlawitschka, Mario LeipzigUniversity of Applied Sciences Chair of Computer Graphics Karl-Liebknecht-Straße 132 Leipzig04277 Germany Leipzig University Image and Signal Processing Group Augustusplatz 10 Leipzig04109 Germany

ISBN: (纸本)9783885797319

In the context of the renaturation of discontinued open-cast mines, the interactive visualization analysis of three-dimensional LiDAR provides a comprehensive overview for planning the subsequent use of these areas. When analyzing the measured point clouds, it is beneficial to classify the points, enabling the user to filter objects such as vehicles and buildings. Most current classification techniques for LiDAR data rely on good ground truth and work on specific types of measurements and resolutions. In this work, we present a semantic classification workflow for LiDAR data with highly heterogeneous acquisition and storage parameters. We apply the workflow to a freely available LiDAR data set and showcase the resulting classification. Our method is shown to reliably classify not only large-scale objects, such as buildings, but also small-scale objects, such as power lines and street lights. © 2023 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Classification (of information)

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：