检索结果-内蒙古大学图书馆

Texture classification with kernel principal component analysis

ELECTRONICS LETTERS 2000年第12期36卷 1021-1022页

作者： Kim, KI Jung, K Park, SH Kim, HJ Kyungpook Natl Univ Dept Comp Engn Taegoo South Korea

Kernel principal component analysis (PCA) is presented as a mechanism for extracting textural information. Using the polynomial kernel, higher order correlations of input pixels can be easily used as features for clas... 详细信息

关键词： correlation theory Optical, image and video signal processing neural nets image classification polynomial kernel Neural nets supervised texture classification feature extraction principal component analysis higher order correlations kernel principal component analysis textural information Other topics in statistics image texture input pixels computer vision and image processing techniques image recognition neural network

来源：评论

学校读者我要写书评

暂无评论

Visual Media Production

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 2005年第4期152卷 385-386页

作者： Grau, O Hilton, A Univ Surrey Visual Media Res Grp Guildford GU2 5XH Surrey England

No abstract available

关键词： Graphics techniques Optical, image and video signal processing visual media production image processing computer vision computer graphics computer vision and image processing techniques Video signal processing video signal processing

来源：评论

学校读者我要写书评

暂无评论

THE SADLI PROJECT - SAFETY-CRITICAL SOFTWARE RESEARCH IN THE MEDICAL DIAGNOSTIC DOMAIN

引用

COMPUTING & CONTROL ENGINEERING JOURNAL 1995年第5期6卷 211-215页

作者： CHUDLEIGH, M BERRIDGE, C MAY, R BUTLER, J POOLE, I MRC HUMAN GENET UNITCAMBRIDGE CB2 2QHENGLAND

The overall objective of the SADLI project was to implement a demonstration imaging system in diagnostic microscopy using functional programming under the discipline of a safety-critical methodology in order to determ... 详细信息

关键词： safety critical methodology cervical screening functional programming safety-critical software microscopy medical image processing biomedical equipment diagnostic microscopy demonstration imaging system medical diagnostic domain Patient diagnostic methods and instrumentation Software engineering techniques Optical information, image and video signal processing Biology and medical computing computer vision and image processing techniques SADLI project safety critical software research

来源：评论

学校读者我要写书评

暂无评论

Local characteristic based wavelet shrinkage denoising algorithm

引用

ELECTRONICS LETTERS 2002年第9期38卷 411-412页

作者： Wang, SQ Zhou, YH Zou, DW Shanghai Jiao Tong Univ Inst Image Commun & Informat Proc Shanghai 200030 Peoples R China Jiangxi Normal Univ Sch Phys & Commun Technol Nanchang 330027 Peoples R China

A new wavelet shrinkage denoising algorithm for an image is presented. which is based on the local characteristic of an image, The proposed algorithm efficiently reduces noise and achieves better peak signal-to-noise ... 详细信息

关键词： interference suppression wavelet transforms image processing Optical, image and video signal processing Integral transforms in numerical analysis local image characteristic noise reduction low SNR images wavelet shrinkage image denoising algorithm local characteristic based wavelet shrinkage denoising algorithm peak signal-to-noise ratio optical noise wavelet shrinkage denoising algorithm image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Bidirectional variable size block motion compensation

引用

ELECTRONICS LETTERS 1998年第1期34卷 52-53页

作者： Zhang, JJ Ahmad, MO Swamy, MNS Concordia Univ Dept Elect & Comp Engn Ctr Commun & Signal Proc Quebec City PQ H3G 1M8 Canada

The authors present a neu motion compensation technique for bidirectional predictive video coding, which partitions a frame into variable size blocks according to the local motion contents and yields an optimal rate-distortion performance. Preliminary results show that this method is more efficient than the conventional fixed-size method.

关键词： bidirectional predictive video coding rate distortion theory local motion contents variable size blocks Codes optimal rate-distortion performance Optical information, image and video signal processing block motion compensation Pattern recognition Information theory motion compensation video coding computer vision and image processing techniques block codes

来源：评论

学校读者我要写书评

暂无评论

Gradient-based predictor for diagonal edge pixels in JPEG-LS

引用

ELECTRONICS LETTERS 2001年第22期37卷 1327-1328页

作者： Edirisinghe, EA Bedi, S Loughborough Univ Technol Dept Comp Sci Loughborough LE11 3TU Leics England

JPEG-LS predictors have been optimised for the accurate prediction of pixels in the locality of horizontal/vertical edges. Here a low cost technique that accurately predicts the values of pixels along diagonal edges is proposed. It is shown that the proposed technique outperforms JPEG-LS in terms of predicted mean squared error, by a margin of up to 11.23%.

关键词： image and video coding data compression image coding prediction theory low cost technique diagonal edge pixels edge detection image recognition gradient-based predictor computer vision and image processing techniques image compression JPEG-LS predictors diagonal edge patterns

来源：评论

学校读者我要写书评

暂无评论

Descriptor detecting the most nonuniform subimages in multiresolution texture segmentation procedure

引用

ELECTRONICS LETTERS 2002年第4期38卷 169-170页

作者： Kontaxakis, I Sangriotis, M Martakos, D Univ Athens Dept Informat & Telecommun Athens 15784 Greece

A descriptor, based on histogram central moments, is proposed for picking up only the nonuniform from a series of subimages resulting from the multiresolution analysis of a texture image. This subimage choice speeds up a procedure laid out for texture segmentation of the image while maintaining or even improving the reliability of it.

关键词： Optical, image and video signal processing image recognition nonuniform subimage detection texture image histogram central moments-based descriptor image texture segmentation image segmentation multiresolution analysis multiresolution texture segmentation procedure nonuniform subimages image recognition reliability image resolution image texture computer vision and image processing techniques descriptor subimage series

来源：评论

学校读者我要写书评

暂无评论

Watermark embedded in permuted domain

引用

ELECTRONICS LETTERS 2001年第2期37卷 80-81页

作者： Yen, JC Natl Lien Ho Inst Technol Dept Elect Engn Maioli Taiwan

A scheme is proposed in which a watermark is transformed and then used to modify the third, fourth, or fifth bit of the pixels in a permuted image according to a chaotic binary sequence. The PSNR is larger than 44dB a... 详细信息

关键词： image and video coding chaotic binary sequence data compression permuted domain chaos binary sequences copy protection image coding compression ratio PSNR watermark computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Absolute localisation in confined spaces using deep geometric features

引用

ELECTRONICS LETTERS 2021年第16期57卷 621-623页

作者： Brogaard, Rune Y. Ravn, Ole Boukas, Evangelos Tech Univ Denmark Dept Elect Engn Lyngby Denmark

When operating in dark and confined spaces, the capacity of the robots to localise in an absolute reference frame is of utmost importance. This letter presents an absolute localisation system, using deep 3D landmarks, for known confined spaces. The system estimates the robot's relative localisation using visual inertial odometry. Local deep 3D landmarks are extracted from the robot's view. Similar 3D landmarks are, also, extracted from the prior map which are then registered with the local landmarks to provide absolute localisation via an extended Kalman filter. To the best of knowledge, deep 3D feature registration has not been used before for absolute localisation. The proposed localisation system is tested within a representative application area-i.e. a structured, confined space-and the results indicate greater accuracy and lower processing time when compared to mainstream 3D registration approaches.

关键词： Optical, image and video signal processing Filtering methods in signal processing Mobile robots computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Autonomous trail-following unmanned aerial vehicle system based on resource partitioning of single hardware platform

引用

ELECTRONICS LETTERS 2021年第6期57卷 245-248页

作者： Lim, Yoojin Kim, Kyungil Shin, Jinah Lim, Chaedeok Elect & Telecommun Res Inst Daejeon South Korea

As deep neural networks are spreading to almost all fields, flight systems in the unmanned aerial vehicle (UAV) domain are undergoing various transitions to intelligent systems. Among these transitions-in a bid to reduce flight risk-is the active research domain of autonomous navigation for intelligent UAVs. The autonomous trail-following flight system that this letter introduces can safely consolidate flight control and mission control within the latest commercial hardware platform. The resource usage and degradation of pass-through delay in vision-based convolutional neural network workloads show that virtualisation overhead is not significantly negative, and the overall performance of the introduced system is acceptable. Real-time cooperation is also verified as achievable-in that the workloads incur minimal communication delay-between the controls. Finally, the actual field test analysis demonstrates the applicability of our autonomous UAV system, whereby our system controls the UAV to follow the centre of a set trail.

关键词： Optical, image and video signal processing Aerospace control Mobile robots Telerobotics computer vision and image processing techniques Control engineering computing Aerospace engineering computing Neural nets

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：