检索结果-内蒙古大学图书馆

SAR image De-noising Based on Generalized Non-local Means in Non-subsample Shearlet Domain 1

4th International conference on Communications, Signal processing, and systems (CSPS)

作者： Liu Shuaiqi Geng Peng Shi Mingzhu Fang Jing Hu Shaohai Hebei Univ Coll Elect & Informat Engn Baoding Hebei Peoples R China Key Lab Digital Med Engn Hebei Prov Baoding Hebei Peoples R China Shijiazhuang Tiedao Univ Sch Informat Sci & Technol Shijiazhuang Hebei Peoples R China Tianjin Normal Univ Coll Elect & Commun Engn Tianjin Peoples R China Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China

ISBN: (数字)9783662498316

ISBN: (纸本)9783662498316;9783662498293

How to suppress and remove the speckle of SAR image has been a hot research issue. Combining the advantages of non-subsample Shearlet transform (NSST) with the generalized non-local means de-noising algorithm, we proposed a new SAR image de-noising algorithm in this paper. This algorithm is appropriate for the characteristics of the speckle noise, so it can improve the quality of de-noised image. Meanwhile, the algorithm holds the characteristics of translational invariance, which can suppress Gibbs phenomenon effectively.

关键词： image denoising algorithms Radar polarimetry Rescue Synthetic aperture radar Specific absorption rate SAFETY ANALYSIS REPORTS Gibbs phenomenon speckle noise Speckle image noise

来源：评论

学校读者我要写书评

暂无评论

EFFECT OF AFT ROTOR ON THE INTER-ROTOR FLOW OF AN OPEN ROTOR PROPULSION SYSTEM

引用

ASME Turbo Expo: Turbine Technical conference and Exposition

作者： Slaboch, Paul E. Stephens, David B. Van Zante, Dale E. St Martins Univ Lacey WA 98503 USA NASA Glenn Res Ctr Cleveland OH USA

ISBN: (纸本)9780791849682

The effects of the aft rotor on the inter-rotor flow field of an open rotor propulsion rig were examined. A Particle image Velocimetry (PIV) dataset that was acquired phase locked to the front rotor position has been phase averaged based on the relative phase angle between the forward and aft rotors. The aft rotor phase was determined by feature tracking in raw PIV images through an image processing algorithm. The effects of the aft rotor potential field on the inter-rotor flow were analyzed and shown to be in reasonably good agreement with Computational Fluid Dynamics (CFD) simulations. The aft rotor position was shown to have a significant upstream effect, with implications for front rotor interaction noise. It was found that the aft rotor had no substantial effect on the position of the forward rotor tip vortex but did have a small effect on the circulation strength of the vortex when the rotors were highly loaded.

关键词： Rotors Propulsion systems Flow (Dynamics) image processing Engineering simulation Propulsion Simulation Particulate matter Noise (Sound) Computational fluid dynamics algorithms Vortices Wake turbulence

来源：评论

学校读者我要写书评

暂无评论

Deep Belief Network Based Part-of-Speech Tagger for Telugu Language 2nd

Deep Belief Network Based Part-of-Speech Tagger for Telugu L...

引用

2nd International conference on Computer and Communication Technologies

作者： Jagadeesh, M. Kumar, M. Anand Soman, K. P. Atlas Healthcare Software India Pvt Coimbatore Tamil Nadu India Amrita Vishwa Vidyapeetham Ctr Excellence Computat Engn & Networking Coimbatore Tamil Nadu India

ISBN: (纸本)9788132225263;9788132225256

Indian languages have very less linguistic resources, though they have a large speaker base. They are very rich in morphology, making it very difficult to do sequential tagging or any type of language analysis. In natural language processing, parts-of-speech (POS) tagging is the basic tool with which it is possible to extract terminology using linguistic patterns. The main aim of this research is to do sequential tagging for Indian languages based on the unsupervised features and distributional information of a word with its neighboring words. The results of the machine learning algorithms depend on the data representation. Not all the data contribute to creation of the model, leading a few in vain and it depends on the descriptive factors of data disparity. Data representations are designed by using domain-specific knowledge but the aim of Artificial Intelligence is to reduce these domain-dependent representations, so that it can be applied to the domains which are new to one. Recently, deep learning algorithms have acquired a substantial interest in reducing the dimension of features or extracting the latent features. Recent development and applications of deep learning algorithms are giving impressive results in several areas mostly in image and text applications.

关键词： Natural language processing Deep belief networks Restricted Boltzmann machine Neural networks POS tagging

来源：评论

学校读者我要写书评

暂无评论

AprilTag 2: Efficient and robust fiducial detection

AprilTag 2: Efficient and robust fiducial detection

引用

IEEE/RSJ International conference on Intelligent Robots and systems (IROS)

作者： Wang, John Olson, Edwin Univ Michigan Dept Comp Sci & Engn Ann Arbor MI 48109 USA

ISBN: (纸本)9781509037629

AprilTags and other passive fiducial markers require specialized algorithms to detect markers among other features in a natural scene. The vision processing steps generally dominate the computation time of a tag detection pipeline, so even small improvements in marker detection can translate to a faster tag detection system. We incorporated lessons learned from implementing and supporting the AprilTag system into this improved system. This work describes AprilTag 2, a completely redesigned tag detector that improves robustness and efficiency compared to the original AprilTag system. The tag coding scheme is unchanged, retaining the same robustness to false positives inherent to the coding system. The new detector improves performance with higher detection rates, fewer false positives, and lower computational time. Improved performance on small images allows the use of decimated input images, resulting in dramatic gains in detection speed.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Polynomial feature engineering for classification of textural images

引用

Journal of Physics: conference Series 2018年第1期1096卷

作者： A V Gaidel Samara National Research University Moskovskoe Shosse 34 Samara Russia 443086 Image Processing Systems Institute - Branch of the Federal Scientific Research Centre 'Crystallography and Photonics' of Russian Academy of Sciences Molodogvardeyskaya str. 151 Samara Russia 443001

I consider a number of methods of automatic quadratic features adjustment for digital textural images of biological tissues in order to improve the quality of classification. The proposed approaches are based on optimization procedures that use various quality criteria of a feature space as target functions. I investigate the methods based on random search, genetic algorithm, simulation of annealing, as well as the original hybrid algorithm. I presented results of experimental studies of the proposed algorithms on sets of real X-ray images of bone tissue and the lung CT images. We show that the hybrid algorithm provides more stable results regardless of the chosen quality criterion of the feature space, which is expressed in decreasing of the average percentage of incorrectly recognized images in comparison with the use of the specific optimization methods individually.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Visibility Enhancement of Foggy images

An Improved Method for Visibility Enhancement of Foggy Image...

引用

International conference on Emerging Trends in Electrical Electronics & Sustainable Energy systems (ICETEESES)

作者： Pal, Narendra Singh Lal, Shyam Shinghal, Kshitij Moradabad Inst Technol Dept E&C Engn Moradabad UP India Dr APJ Abdul Kalam Tech Univ Lucknow Uttar Pradesh India Natl Inst Technol Karnataka Dept E&C Engn Mangaluru KA India

ISBN: (纸本)9781509021185

An improved method for visibility enhancement of foggy based degraded images is presented. Proposed technique consists of two phases: firstly applied the visibility enhancement algorithm and then automatic color enhancement algorithm. Quantitative metric and qualitative result of proposed technique is evaluated and compared with other existing visibility restoration algorithms. In this paper quantitative results are presented in terms of measure of enhancement and measure of enhancement factor. Simulation results on foggy images from database demonstrates that proposed technique provides better visibility enhancement results as compared to the others existing visibility enhancement algorithms. A result reveals that proposed technique is an efficient method for visibility enhancement of foggy based degraded images.

关键词： Visibility Enhancement Color Enhancement image processing Enhancement Factor

来源：评论

学校读者我要写书评

暂无评论

Local motion compensation in image sequences degraded by atmospheric turbulence: a comparative analysis of optical flow vs. block matching methods 19

Local motion compensation in image sequences degraded by atm...

引用

conference on Optics in Atmospheric Propagation and Adaptive systems XIX

作者： Huebner, Claudia S. Fraunhofer IOSB Gutleuthausstr 1 D-76275 Ettlingen Germany

ISBN: (数字)9781510604094

ISBN: (纸本)9781510604087;9781510604094

As a consequence of fluctuations in the index of refraction of the air, atmospheric turbulence causes scintillation, spatial and temporal blurring as well as global and local image motion creating geometric distortions. To mitigate these effects many different methods have been proposed. Global as well as local motion compensation in some form or other constitutes an integral part of many software-based approaches. For the estimation of motion vectors between consecutive frames simple methods like block matching are preferable to more complex algorithms like optical flow, at least when challenged with near real-time requirements. However, the processing power of commercially available computers continues to increase rapidly and the more powerful optical flow methods have the potential to outperform standard block matching methods. Therefore, in this paper three standard optical flow algorithms, namely Horn-Schunck (HS), Lucas-Kanade (LK) and Farneback (FB), are tested for their suitability to be employed for local motion compensation as part of a turbulence mitigation system. Their qualitative performance is evaluated and compared with that of three standard block matching methods, namely Exhaustive Search (ES), Adaptive Rood Pattern Search (ARPS) and Correlation based Search (CS).

关键词： atmospheric turbulence turbulence mitigation optical flow block matching motion estimation local motion compensation image restoration

来源：评论

学校读者我要写书评

暂无评论

Planet detection down to a few λ/D: an RSDI/TLOCI approach to PSF subtraction 5

Planet detection down to a few λ/D: an RSDI/TLOCI approach ...

引用

conference on Adaptive Optics systems V

作者： Gerard, Benjamin L. Marois, Christian Univ Victoria Dept Phys & Astron 3800 Finnerty Rd Victoria BC V8P 5C2 Canada Natl Res Council Canada 5071 West Saanich Rd Victoria BC V9E 2E7 Canada

ISBN: (纸本)9781510601987

Most current high contrast imaging point spread function (PSF) subtraction algorithms use some form of a least-squares noise minimization to find exoplanets that are, before post-processing, often hidden below the instrumental speckle noise. In the current standard PSF subtraction algorithms, a set of reference images is derived from the target image sequence to subtract each target image, using Angular and/or Simultaneous Spectral Differential Imaging (ADI, SSDI, respectively). However, to avoid excessive exoplanet self-subtraction, ADI and SSDI (in the absence of a strong spectral feature) severely limit the available number of reference images at small separations. This limits the performance of the least-squares algorithm, resulting in lower sensitivity to exoplanets at small angular separations. Possible solutions are to use additional reference images by acquiring longer sequences, use SSDI if the exoplanet is expected to show strong spectral features, or use images acquired on other targets. The latter option, known as Reference Star Differential Imaging (RSDI), which relies on the use of reference images that are highly correlated to the target image, has been ineffective in previous ground-based high contrast imaging surveys. The now >200 target reference library from the Gemini Planet imager Exoplanet Survey (GPIES) allows for a detailed RSDI analysis to possibly improve contrast performance near the focal plane mask, at similar to 2-7 lambda/D separations. We present the results of work to optimize PSF subtraction with the GPIES reference library using a least-squares algorithm designed to minimize speckle noise and maximize planet throughput, thus maximizing the planet signal to noise ratio (SNR). Using December 2014 51 Eri GPI data in the inner 100 mas to 300 mas annulus, we find no apparent improvement in SNR when using RSDI and/or our optimization scheme. This result, while still being investigated, seems to show that current algorithms on ADI+SSDI da

关键词： high contrast imaging PSF subtraction image processing

来源：评论

学校读者我要写书评

暂无评论

Design and Manufacturing of a Low-Cost 2-DOF Autonomous Sentry Gun 2

Design and Manufacturing of a Low-Cost 2-DOF Autonomous Sent...

引用

2nd International conference on Robotics and Artificial Intelligence (ICRAI)

作者： Ahmad, Husnain Ali, Syed Mohsin Sheikh, Usman Ayub Murtaza, Zain Rizwan, Muhammad Natl Univ Sci & Technol Dept Robot & Artificial Intelligence Sect H-12 Islamabad 44000 Pakistan Harbin Inst Technol Automat Test & Control Inst Elect & Automat Dept Harbin Peoples R China

ISBN: (纸本)9781509040599

In this paper, design and development of a selfsufficient sentry robotic gun is presented. Professional robotic assemblies which are generally developed for security purposes are targeted toward high efficiency and are based on extensive control algorithms. This makes them quite expensive and infeasible for low budget applications. One important component of such systems is that of motion detection. Motion detection also plays a key role in security applications installed at banks, offices and vulnerable areas. An efficient motion detection system has been developed using embedded micro-controller and MATLAB interface. The proposed system can also be set into an autonomous mode of operation, in which the system tracks and engages targets without any human intervention. Aside from autonomous mode, there is also a manual over-ride mode. The hardware employed in the proposed system is based on easily accessible materials. Motion detection and image processing was implemented using MATLAB image processing toolbox and periodic background estimation subtraction was used for the detection of motion.

关键词： periodic background estimation subtraction security solution 2-DOF sentry manipulator MATLAB image processing tool box

来源：评论

学校读者我要写书评

暂无评论

Innovative methodology for the integration of range-data and image-based systems

Innovative methodology for the integration of range-data and...

引用

IMEKO International conference on Metrology for Archeology and Cultural Heritage, MetroArcheo 2016

作者： Angelini, Andrea Portarena, Damiano Consiglio Nazionale delle Ricerche Istituto per le Tecnologie Applicate ai Beni Culturali Roma Italy Università degli studi di Roma Tor Vergata Italy

ISBN: (纸本)9781510849754

Most of the survey techniques used in archaeology and architecture are currently focused on range-data (laser scanning) and image-based systems (digital photogrammetry/photoscanning). The paper aims to highlight a different methodological approach in the procedures of acquisition and processing of numerical data. The proposed methodology suggests an alternative integration between point clouds from laser scanner and image-based system, exploiting the properties of the ICP algorithms. Three different experimentations were performed at different level in order to achieve the suitable procedure. Some graphics show the comparison between the classic approach and the new procedure. The results are very interesting for what concerns the elaboration of the numerical models. The correct position of the points in space contributes the next step of the surface reconstruction (meshing process) and the final 2D representation. © 2016 IMEKO-International Measurement Federation Secretariat. All rights reserved.

关键词： Data handling

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：