检索结果-内蒙古大学图书馆

Effective algorithm for detecting various wipe patterns and discriminating wipe from object and camera motion

IET image processing 2010年第6期4卷 429-442页

作者： Warhade, K. K. Merchant, S. N. Desai, U. B. Indian Inst Technol Dept Elect Engn SPANN Lab Bombay 400076 Maharashtra India

Wipe transition detection in video segmentation is more difficult to detect than abrupt and other gradual transitions, because of diversity in patterns, and difficulty in distinguishing wipe from camera and object motion. In this study, the authors propose an algorithm for wipe transition detection. In the proposed algorithm, first the moving strip due to wipe is obtained, which eliminate most of the edges due to object boundaries and retain true wipe boundaries, and then Hough transform is applied on these moving lines to detect and categorise various wipe types. In order to decrease the computational load of the proposed algorithm, the authors propose a preprocessing step as a first stage of the algorithm. The preprocessing step consists of calculation of statistical image difference between the consecutive frames to obtain the potential wipe frames, which are input to their proposed algorithm. The proposed algorithm detects and identifies various types of wipes and also distinguishes wipes from object and camera motion. The performance comparison of the proposed algorithm, with and without preprocessing, with other existing techniques clearly exhibit its effectiveness in terms of better recall, precision, F1 measure and detection rate.

关键词： wipe pattern detection wipe transition detection image segmentation camera motion statistical analysis image sensors computer vision and image processing techniques statistical image difference calculation true wipe boundary object detection Other topics in statistics Video signal processing Optical, image and video signal processing image motion analysis object motion video segmentation cameras

来源：评论

学校读者我要写书评

暂无评论

Aspect coherence for graph-based semantic image labelling

引用

IET computer vision 2010年第3期4卷 183-194页

作者： Passino, G. Patras, I. Izquierdo, E. Univ London London E1 4NS England

In image semantic segmentation a semantic category label is associated to each image pixel. This classification problem is characterised by pixel dependencies at different scales. On a small-scale pixel correlation is related to object instance sharing, whereas on a middle-and large scale to category co-presence and relative location constraints. The contribution of this study is two-fold. First, the authors present a framework that jointly learns category appearances and pixel dependencies at different scales. Small-scale dependencies are accounted by clustering pixels into larger patches via image oversegmentation. To tackle middle-scale dependencies a conditional random field (CRF) is built over the patches. A novel strategy to exploit local patch aspect coherence is used to impose an optimised structure in the graph to have exact and efficient inference. The second contribution is a method to account for full patch neighbourhoods without introducing loops in the graphical structures. 'Weak neighbours' are introduced, which are patches connected in the image but not in the inference graph. They are pre-classified according to their visual appearance and their category distribution probability is then used in the CRF inference step. Experimental evidence of the validity of the method shows improvements in comparison to other works in the field.

关键词： clustering pixels inference graph local patch aspect coherence Other topics in statistics image pixel pattern clustering graphical structures feature extraction image semantic segmentation semantic category label pixel dependency computer vision and image processing techniques probability conditional random field semantic image labelling category distribution probability Optical, image and video signal processing image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast colour space transformations using minimax approximations

引用

IET image processing 2010年第2期4卷 70-80页

作者： Celebi, M. Emre Kingravi, H. A. Celiker, F. Louisiana State Univ Dept Comp Sci Shreveport LA 71105 USA Georgia Inst Technol Dept Comp Sci Atlanta GA 30332 USA Wayne State Univ Dept Math Detroit MI 48202 USA

Colour space transformations are frequently used in image processing, graphics and visualisation applications. In many cases, these transformations are complex non-linear functions, which prohibit their use in time-critical applications. A new approach called minimax approximations for colour space transformations (MACT) is presented. The authors demonstrate MACT on three commonly used colour space transformations. Extensive experiments on a large and diverse image set and comparisons with well-known multidimensional look-up table interpolation methods show that MACT achieves an excellent balance among four criteria: ease of implementation, memory usage, accuracy and computational speed.

关键词： minimax approximations memory usage computer vision and image processing techniques image processing approximation theory image colour analysis multidimensional look-up table interpolation methods Interpolation and function approximation (numerical analysis) Optical, image and video signal processing complex nonlinear functions colour space transformations interpolation

来源：评论

学校读者我要写书评

暂无评论

Efficient eye detection method based on grey intensity variance and independent components analysis

引用

IET computer vision 2010年第4期4卷 261-271页

作者： Hassaballah, M. Kanazawa, T. Ido, S. Ido, S. Ehime Univ Dept Elect & Elect Engn & Comp Sci Matsuyama Ehime 7908577 Japan S Valley Univ Fac Sci Dept Math Qena Egypt eCompute Corp Matsuyama Ehime 7918042 Japan

Detection of facial features such as eye, nose and mouth in the human face images is important for many applications like face identification or recognition systems. Independent components analysis (ICA) is an unsupervised learning method which decorrelates the higher-order statistics in addition to the second-order moments. Recently, it is used as a technique for face recognition. In this study, ICA applied on a patch image is used as a method to extract the eye which is the most salient and stable feature among all the facial features. The variance of grey intensity in the eye region and ICA are combined together to detect rough eye window. The ICA basis images are computed using the FastICA algorithm;that computes independent components by maximising non-Gaussianity of the whitened data distribution using a kurtosis maximisation process. After detecting rough eye window, intensity information is used to localise eye centre point. The proposed method is evaluated on different databases XM2VTS, BioID and FERET and experimental results demonstrate improved performance over the existing methods. In addition, a high detection rate of 93.3% can be achieved on 600 images with glasses. A comparison between the proposed method and the most recent published methods which focus on eye window detection is also reported.

关键词： Optimisation techniques kurtosis maximisation Other topics in statistics human face images FastICA algorithm XM2VTS image recognition second-order moments eye detection independent component analysis face identification grey intensity variance face recognition whitened data distribution FERET facial feature detection unsupervised learning computer vision and image processing techniques feature extraction nonGaussianity maximisation BioID optimisation higher order statistics higher-order statistics patch image

来源：评论

学校读者我要写书评

暂无评论

Environment classification and hierarchical lane detection for structured and unstructured roads

引用

IET computer vision 2010年第1期4卷 37-49页

作者： Cheng, H. -Y. Yu, C. -C. Tseng, C. -C. Fan, K. -C. Hwang, J. -N. Jeng, B. -S. Natl Cent Univ Dept Comp Sci & Informat Engn Chungli 32054 Taiwan Vanung Univ Dept Comp Sci & Informat Engn Chungli Taiwan Natl Kaohsiung First Univ Sci & Technol Dept Comp & Commun Engn Kaohsiung Taiwan Univ Washington Dept Elect Engn Seattle WA 98195 USA Yuan Ze Univ Dept Commun Engn Commun Res Ctr Chungli Taiwan

This study presents a hierarchical lane detection system with the ability to deal with both structured and unstructured roads. The proposed system classifies the environment first before applying suitable algorithms for different types of roads. Instead of dealing with all situations with one complicated algorithm, this hierarchical architecture makes it possible to achieve high accuracy with relatively simple and efficient lane detection algorithms. For environment classification, pixels with lane-marking colours are extracted as feature points. Eigenvalue decomposition regularised discriminant analysis is utilised in model selection and maximum likelihood estimation of Gaussian parameters in high-dimensional feature space. For structured roads, the extracted feature points are reused for lane detection. Moving vehicles that have the same colours as the lane markings are eliminated from the feature points before the authors perform angles of inclination and turning points searching to locate the lane boundaries. For unstructured roads, mean-shift segmentation is applied to divide the scene into regions. Possible candidate pairs for road boundaries are elected from the region boundaries, and Bayes rule is used to choose the most probable candidate pairs as the lane boundaries. The experimental results have shown that the classification mechanism can effectively choose the correct lane detection algorithm according to the current environment setting, and the system is able to robustly find the lane boundaries on different types of roads in various weather conditions.

关键词： lane-marking colours Other topics in statistics roads hierarchical lane detection algorithm image resolution image segmentation eigenvalue decomposition regularised discriminant analysis model selection high-dimensional feature space unstructured roads Bayes methods structured roads feature points extraction eigenvalues and eigenfunctions maximum likelihood estimation object detection Optical, image and video signal processing image classification computer vision and image processing techniques feature extraction image colour analysis mean-shift segmentation Gaussian parameters automated highways Bayes rule environment classification

来源：评论

学校读者我要写书评

暂无评论

Tensor-based projection using ridge regression and its application to action classification

引用

IET image processing 2010年第6期4卷 486-493页

作者： Wu, X. Lai, J. Sun Yat Sen Univ Sch Informat Sci & Technol Guangzhou 510006 Guangdong Peoples R China

In this study, the authors encode video sequence by a third-order tensor instead of matrices or vectors and present a novel framework of action classification via tensor-based projection using ridge regression (TPRR). The main contributions of this framework include: (i) Classification can be directly achieved by projecting the tensor samples into their binary class label through ridge regression technique. (ii) TPRR algorithm is further generalised from binary classification to solve multi-category classification problem by incorporating the error correcting concept. Experiments of action classification on a small or medium training set demonstrate that this approach outperforms previous tensor embedding methods and other state-of-the-art techniques, whereas on large training set, it is also able to achieve very satisfactory results. The proposed approach is further proven to be considerably robust to viewpoint, partial occlusion and irregularities in motion styles.

关键词： Algebra binary classification label image sequences video coding computer vision and image processing techniques image classification image and video coding action classification TPRR algorithm video sequence encoding regression analysis Video signal processing tensors tensor-based projection ridge regression technique Other topics in statistics multicategory classification problem third-order tensor

来源：评论

学校读者我要写书评

暂无评论

Using diffusion equations for improving performance of wavelet-based image denoising techniques

引用

IET image processing 2010年第6期4卷 452-462页

作者： Nikpour, M. Hassanpour, H. Babol Univ Technol Dept Comp & Elect Engn Babol Sar Iran Shahrood Univ Technol Shahrood Iran

A new method based on anisotropic diffusion and wavelet transform is presented for image noise reduction. In the existing wavelet thresholding methods, the final noise reduced image has limited improvement. It is due to keeping the approximate coefficients of the image unchanged. These coefficients have the main information of the image. Since noise affects both the approximate and detail coefficients, in this research, the anisotropic diffusion technique for noise reduction is applied on the approximation band to alleviate the deficiency of the existing wavelet thresholding methods. The proposed method was applied on several standard noisy images and the results indicate superiority of the proposed method over the existing wavelet-based image denoising, anisotropic diffusion, fourth-order anisotropic diffusion and median filtering techniques.

关键词： wavelet thresholding methods image denoising wavelet-based image denoising techniques wavelet transform computer vision and image processing techniques wavelet transforms fourth-order anisotropic diffusion Integral transforms median filtering techniques diffusion equations Optical, image and video signal processing image noise reduction

来源：评论

学校读者我要写书评

暂无评论

Graphical route information panel for the urban freeway network in Shanghai, China

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2010年第3期4卷 212-220页

作者： Gan, H. Univ Shanghai Sci & Technol Sch Business Ctr Transport Res Shanghai Peoples R China

The concept of using graphical route information panel (GRIP) to improve the dynamic traffic management efficiency is becoming increasingly popular recently. Colour-coded level-of-service (LOS) map and route travel time are important information displayed by GRIP. This study addresses the graphical information provision issue and the travel time prediction issue, based on research and development of Shanghai urban freeway GRIPs. It first presents function and location of Shanghai GRIP, philosophy of GRIP panel layout and basic principle of LOS display method. Then it focuses on segmentation of LOS map and proposes three segmentation approaches: the detector-based approach, the ramp-based approach and the hybrid approach. Opinions and lessons learned regarding advantages and disadvantages of different segmentation approaches are given. Next, it proposes a macroscopic traffic flow model-based travel time prediction approach for GRIP. The traffic flow model incorporated in the prediction approach is a validated high-order continuum model. The preliminary performance test of the approach is conducted using real-traffic data of a three-lane urban freeway section of Yan-An elevated road in Shanghai. The results reveal that the travel time prediction approach performs well both under free-flowing conditions and under congested conditions. Last, it gives concluding remarks.

关键词： Traffic engineering computing continuum model colour coded level-of-service map traffic information systems ramp based map segmentation China traffic management urban freeway network automated highways computer vision and image processing techniques graphical route information panel detector based map segmentation road traffic macroscopic traffic flow model route travel time image segmentation Shanghai

来源：评论

学校读者我要写书评

暂无评论

Texture classification using invariant features of local textures

引用

IET image processing 2010年第3期4卷 158-171页

作者： Janney, P. Geers, G. Univ New S Wales Sch Engn & Comp Sci Sydney NSW 2032 Australia NICTA Sydney NSW 2032 Australia

In this paper, the authors present a texture descriptor algorithm called invariant features of local textures (IFLT). IFLT generates scale, rotation and (essentially) illumination invariant descriptors from a small neighbourhood of pixels around a centre pixel or a texture patch. Texture classification experiments were carried out on the Brodatz, Outex and KTH-TIPS2 databases. Demonstrated texture classification accuracy exceeds the previously published state of the art at a significantly lower computational cost. Experiments also suggests that IFLT descriptors are in a sense intuitive texture descriptors.

关键词： image resolution texture patch computer vision and image processing techniques image classification invariant features of local textures feature extraction texture descriptor algorithm texture classification image texture Optical, image and video signal processing illumination invariant descriptors KTH-TIPS2 databases

来源：评论

学校读者我要写书评

暂无评论

Statistical motion learning for improved transform domain Wyner-Ziv video coding

引用

IET image processing 2010年第1期4卷 28-41页

作者： Martins, R. Brites, C. Ascenso, J. Pereira, F. Univ Tecn Lisboa Inst Telecomunicacoes Inst Super Tecn P-1049001 Lisbon Portugal Inst Super Engn Lisboa Inst Telecomunicacoes P-1959007 Lisbon Portugal

Wyner - Ziv (WZ) video coding is a particular case of distributed video coding (DVC), the recent video coding paradigm based on the Slepian - Wolf and Wyner - Ziv theorems which exploits the source temporal correlation at the decoder and not at the encoder as in predictive video coding. Although some progress has been made in the last years, WZ video coding is still far from the compression performance of predictive video coding, especially for high and complex motion contents. The WZ video codec adopted in this study is based on a transform domain WZ video coding architecture with feedback channel-driven rate control, whose modules have been improved with some recent coding tools. This study proposes a novel motion learning approach to successively improve the rate-distortion (RD) performance of the WZ video codec as the decoding proceeds, making use of the already decoded transform bands to improve the decoding process for the remaining transform bands. The results obtained reveal gains up to 2.3 dB in the RD curves against the performance for the same codec without the proposed motion learning approach for high motion sequences and long group of pictures (GOP) sizes.

关键词： improved transform domain Wyner-Ziv video coding Wyner-Ziv theorem discrete cosine transforms Slepian-Wolf theorem rate-distortion performance image motion analysis motion sequences computer vision and image processing techniques image and video coding statistical motion learning group of pictures sizes video coding image sequences Video signal processing Integral transforms in numerical analysis rate distortion theory discrete cosine transform WZ video codec feedback channel-driven rate control

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：