检索结果-内蒙古大学图书馆

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Cheng, Ming-Ming Zhang, Guo-Xin Mitra, Niloy J. Huang, Xiaolei Hu, Shi-Min Tsinghua Univ TNList Beijing Peoples R China UCL Dept Comp Sci London WC1E 6BT England Lehigh Univ Dept Comp Sci & Engn Bethlehem PA 18015 USA Univ Oxford Oxford OX1 2JD England Tsinghua Univ Dept Comp Sci & Technol TNList Beijing Peoples R China

ISBN: (纸本)9781457703935

Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields full resolution saliency maps. Our algorithm consistently outperformed existing saliency detection methods, yielding higher precision and better recall rates, when evaluated using one of the largest publicly available data sets. We also demonstrate how the extracted saliency map can be used to create high quality segmentation masks for subsequent image processing.

关键词： images Image processing computer vision based maps Spatial coherence inspection methods

来源：评论

学校读者我要写书评

暂无评论

Predicate Logic Based Image Grammars for Complex pattern recognition

引用

INTERNATIONAL JOURNAL OF computer vision 2011年第2期93卷 141-161页

作者： Shet, Vinay Singh, Maneesh Bahlmann, Claus Ramesh, Visvanathan Neumann, Jan Davis, Larry Siemens Corp Res Princeton NJ 08540 USA Streamsage Comcast Washington DC 20005 USA Univ Maryland Dept Comp Sci College Pk MD 20742 USA

Predicate logic based reasoning approaches provide a means of formally specifying domain knowledge and manipulating symbolic information to explicitly reason about different concepts of interest. Extension of traditional binary predicate logics with the bilattice formalism permits the handling of uncertainty in reasoning, thereby facilitating their application to computer vision problems. In this paper, we propose using first order predicate logics, extended with a bilattice based uncertainty handling formalism, as a means of formally encoding pattern grammars, to parse a set of image features, and detect the presence of different patterns of interest. Detections from low level feature detectors are treated as logical facts and, in conjunction with logical rules, used to drive the reasoning. Positive and negative information from different sources, as well as uncertainties from detections, are integrated within the bilattice framework. We show that this approach can also generate proofs or justifications (in the form of parse trees) for each hypothesis it proposes thus permitting direct analysis of the final solution in linguistic form. Automated logical rule weight learning is an important aspect of the application of such systems in the computer vision domain. We propose a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, interprets rule uncertainties as link weights in the network, and applies a constrained, back-propagation algorithm to converge upon a set of rule weights that give optimal performance within the bilattice framework. Finally, we evaluate the proposed predicate logic based pattern grammar formulation via application to the problems of (a) detecting the presence of humans under partial occlusions and (b) detecting large complex man made structures as viewed in satellite imagery. We also evaluate the optimization approach on real as well as simulated data and show favorable results.

关键词： Stochastic image grammars Logical reasoning Human detection Object detection and classification Bilattice Back propagation Aerial image analysis

来源：评论

学校读者我要写书评

暂无评论

Aggregating Gradient Distributions into Intensity Orders: A Novel Local Image Descriptor

Aggregating Gradient Distributions into Intensity Orders: A ...

引用

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Fan, Bin Wu, Fuchao Hu, Zhanyi Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing 100190 Peoples R China

ISBN: (纸本)9781457703935

A novel local image descriptor is proposed in this paper, which combines intensity orders and gradient distributions in multiple support regions. The novelty lies in three aspects: 1) The gradient is calculated in a rotation invariant way in a given support region;2) The rotation invariant gradients are adaptively pooled spatially based on intensity orders in order to encode spatial information;3) Multiple support regions are used for constructing descriptor which further improves its discriminative ability. Therefore, the proposed descriptor encodes not only gradient information but also information about relative relationship of intensities as well as spatial information. In addition, it is truly rotation invariant in theory without the need of computing a dominant orientation which is a major error source of most existing methods, such as SIFT. Results on the standard Oxford dataset and 3D objects have shown a significant improvement over the state-of-the-art methods under various image transformations.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Optimization of threshold value for segmenting objects with known shapes

引用

pattern recognition and Image Analysis 2011年第2期21卷 231-232页

作者： Astafyev, I.A. ul. Modorova 4 Vladimir 600017 Russia

This paper suggests a method of selection of threshold value for segmenting objects with a priori known shapes. The problem is formulated in the form of an optimization task. This approach is implemented by the example of segmenting the human pupil (first stage of segmenting the eye's iris in recognition). © 2011 Pleiades Publishing, Ltd.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

recognition of human actions using texture descriptors

引用

MACHINE vision AND APPLICATIONS 2011年第5期22卷 767-780页

作者： Kellokumpu, Vili Zhao, Guoying Pietikainen, Matti Univ Oulu Machine Vis Grp Oulu Finland

Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. Two methods are proposed. The first one uses temporal templates to capture movement dynamics and then uses texture features to characterize the observed movements. We then extend this idea into a spatiotemporal space and describe human movements with dynamic texture features. Following recent trends in computer vision, the method is designed to work with image data rather than silhouettes. The proposed methods are computationally simple and suitable for various applications. We verify the performance of our methods on the popular Weizmann and KTH datasets, achieving high accuracy.

关键词： Action recognition Local binary pattern Dynamic textures Temporal templates Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Projection defocus correction using adaptive kernel sampling and geometric correction in dual-planar environments

Projection defocus correction using adaptive kernel sampling...

引用

2011 IEEE computer Society Conference on computer vision and pattern recognition Workshops, CVPRW 2011

作者： Ladha, Shamsuddin Smith-Miles, Kate Chandran, Sharat IITB Monash Research Academy Indian Institute of Technology Bombay India School of Mathematical Sciences Monash University Australia Department of Computer Science and Engineering Indian Institute of Technology Bombay India

ISBN: (纸本)9781457705298

Defocus blur correction for projectors using a camera is useful when the projector is used in ad hoc environments. However, past literature has not explicitly considered the common situation when the projection surface includes a corner made up of two planar surfaces that abut each other, such as the ubiquitous office cubicle. In this paper, we advance the state of the art by demonstrating defocus correction in a non-parametric setting. Our method differs from prior methods in that (a) the luminance and chrominance channels are independently considered, and (b) a sparse sampling of the surface is used to discover the spatially varying defocus kernel. © 2011 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Is there a connection between face symmetry and face recognition?

Is there a connection between face symmetry and face recogni...

引用

2011 IEEE computer Society Conference on computer vision and pattern recognition Workshops, CVPRW 2011

作者： Harguess, Josh Aggarwal, J.K. Computer and Vision Research Center Department of ECE University of Texas Austin United States

ISBN: (纸本)9781457705298

Recent research in the area of automatic machine recognition of human faces has shown that there may be an advantage in utilizing face symmetry to improve recognition accuracy. While promising, this work has led to several open questions. What is a good feature description or score of the symmetry of the face? Is there a statistical significance between face symmetry and face recognition? We present new symmetry scores of the face and use the scores to compare the symmetry in several subgroups of a face database. A 3D face database is used to remove the effects of illumination which should improve the reliability of the symmetry score. We find a significant difference in face symmetry between the men and women subjects in the database. The database is then partitioned into most symmetric and least symmetric subjects based on the symmetry scores. The average-half-face is utilized in our face recognition experiments to take into account the symmetry of the face. Face recognition with eigenfaces using the average-half-face is significantly higher than using the full face in all subgroups regardless of symmetry score. However, face recognition using the full face does depend on the symmetry score and generally favors the least symmetric subjects. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Fast Cost-Volume Filtering for Visual Correspondence and Beyond

Fast Cost-Volume Filtering for Visual Correspondence and Bey...

引用

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Rhemann, Christoph Hosni, Asmaa Bleyer, Michael Rother, Carsten Gelautz, Margrit Vienna Univ Technol A-1040 Vienna Austria Vienna Univ Technol Inst Software Technol & Interact Sys Interact Media Sys Grp A-1040 Vienna Austria Microsoft Res Cambridge Cambridge England

ISBN: (纸本)9781457703935

Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge preserving filter. In this paper we propose a generic and simple framework comprising three steps: (i) constructing a cost volume (ii) fast cost volume filtering and (iii) winner-take-all label selection. Our main contribution is to show that with such a simple framework state-of-the-art results can be achieved for several computer vision applications. In particular, we achieve (i) disparity maps in real-time, whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and (ii) optical flow fields with very fine structures as well as large displacements. To demonstrate robustness, the few parameters of our framework are set to nearly identical values for both applications. Also, competitive results for interactive image segmentation are presented. With this work, we hope to inspire other researchers to leverage this framework to other application areas.

关键词： images computer vision Frameworks image segmentation Fasting Filtration program area

来源：评论

学校读者我要写书评

暂无评论

Embedded neuromorphic vision for humanoid robots

Embedded neuromorphic vision for humanoid robots

引用

2011 IEEE computer Society Conference on computer vision and pattern recognition Workshops, CVPRW 2011

作者： Bartolozzi, Chiara Rea, Francesco Clercq, Charles Fasnacht, Daniel B. Indiveri, Giacomo Hofstätter, Michael Metta, Giorgio Italian Institute of Technology via Morego 30 Genova Italy Austrian Institute of Technology Donau-city Strae 1 Wien Austria University of Zurich ETH Zurich Winterthurerstr. 190 Zürich Switzerland Università Degli Studi di Genova Viale F. Causa 13 Genova Italy

ISBN: (纸本)9781457705298

We are developing an embedded vision system for the humanoid robot iCub, inspired by the biology of the mammalian visual system, including concepts such as stimulus-driven, asynchronous signal sensing and processing. It comprises stimulus-driven sensors, a dedicated embedded processor and an event-based software infrastructure for processing visual stimuli. These components are integrated with the existing standard machine vision modules currently implemented on the robot, in a configuration that exploits the best features of both: the high resolution, color, frame-based vision and the neuromorphic low redundancy, wide dynamic range and high temporal resolution event-based sensors. This approach seeks to combine various styles of vision hardware with sensorimotor systems to complement and extend the current state-of-the art. © 2011 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Resolving occlusion in multiframe reconstruction of deformable surfaces

Resolving occlusion in multiframe reconstruction of deformab...

引用

2011 IEEE computer Society Conference on computer vision and pattern recognition Workshops, CVPRW 2011

作者： Shaji, Appu Varol, Aydin Fua, Pascal Yashoteja Jain, Ankush Chandran, Sharat Computer Vision Laboratory EPFL Switzerland Indian Institute of Technology Bombay India

ISBN: (纸本)9781457705298

Occlusion is troublesome for almost all computer vision algorithms. To a certain extent, the difficulty is alleviated when multiple frames are given. On the other hand, when we consider the recovery of shapes of moving deformable objects, observed using a monocular camera, the problem appears difficult again. In this paper, we show a method that outperforms previous approaches to reconstruction when feature data is unavailable, perhaps due to occlusion. Our key intuition is that portions of the surface that are visible in some frame can be reliably reconstructed in that frame;further, the reliable portions can be stitched together to find even missing portions, much the way a human eye would hallucinate. Our techniques are based on optimization in Riemannian shape spaces, and is demonstrated on isometric surfaces without involving any kind of machine learning methods. © 2011 IEEE.

关键词： Learning systems

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：