检索结果-内蒙古大学图书馆

IEEE Conference on computer vision and pattern recognition

作者： Escalera, Sergio Radeva, Petia Pujol, Oriol UAB Comp Vis Ctr Edif O Bellaterra 08193 Spain Univ Barcelona CVC Dept Matemat Aplicada E-08007 Barcelona Spain

ISBN: (纸本)9781424411795

The goal of interest point detectors is to find in an unsupervised way, keypoints easy to extract and the same timerobust to image transformation. We present a novel set of saliency features based on image singularities that takes into account the region content in terms of intensity and local structure. The region complexity is estimated by means of the entropy of the grey-level information shape information is obtained by measuring the entropy of significant orientations. The regions are located in their representative scale and catergorized by their complexity level. Thus the regions are highly discriminable and less sensitive to confusion and false alarm than raditional approaches. We compare the novel complex salient regions with the state of the art keypoint detectors. The presented interest points show robusthness to a wide set of image transformations and high respecability as well as allows matching from different camera point of view. Besides we show the temporal robusiness of the novel salient regions in real video sequences being potentially useful for matching image retriveal and object categorization problems.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Recognizing human activities from silhouettes: Motion subspace and factorial discriminative graphical model

Recognizing human activities from silhouettes: Motion subspa...

引用

IEEE Conference on computer vision and pattern recognition

作者： Wang, Liang Suter, David Monash Univ Dept Elect & Comp Syst Engn Clayton Vic 3800 Australia

ISBN: (纸本)9781424411795

We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel principal component analysis (KPCA) based feature extraction and factorial conditional random field (FCRF) based motion modeling. Silhouette data is represented more compactly by nonlinear dimensionality reduction that explores the underlying structure of the articulated action space and preserves explicit temporal orders in projection trajectories of motions. FCRF models temporal sequences in multiple interacting ways, thus increasing joint accuracy by information sharing, with the ideal advantages of discriminative models over generative ones (e.g., relaxing independence assumption between observations and the ability to effectively incorporate both overlapping features and long-range dependencies). The experimental results on two recent datasets have shown that the proposed framework can not only accurately recognize human activities with temporal, intra- and inter-person variations, but also is considerably robust to noise and other factors such as partial occlusion and irregularities in motion styles.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Kernel-based tracking from a probabilistic viewpoint

Kernel-based tracking from a probabilistic viewpoint

引用

IEEE Conference on computer vision and pattern recognition

作者： Nguyen, Quang Anh Robles-Kelly, Antonio Shen, Chunhua Australian Natl Univ RSISE Bldg 115 Canberra ACT 0200 Australia Natl ICT Australia Canberra ACT 2601 Australia

ISBN: (纸本)9781424411795

In this paper, we present a probabilistic formulation of kernel-based tracking methods based upon maximum likelihood estimation. To this end, we view the coordinates for the pixels in both, the target model and its candidate as random variables and make use of a generative model so as to cast the tracking task into a maximum likelihood framework. This, in turn, permits the use of the EM-algorithm to estimate a set of latent variables that can be used to update the target-center position. Once the latent variables have been estimated, we use the Kullback-Leibler divergence so as to minimise the mutual information between the target model and candidate distributions in order to develop a target-center update rule and a kernel bandwidth adjustment scheme. The method is very general in nature. We illustrate the utility of our approach for purposes of tracking on real-world video sequences using two alternative kernel functions.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Incorporating on-demand stereo for real time recognition

Incorporating on-demand stereo for real time recognition

引用

IEEE Conference on computer vision and pattern recognition

作者： Deselaers, T. Criminisi, A. Winn, J. Agarwal, A. Microsoft Res Ltd Cambridge England Rhein Westfal TH Aachen Human Language Technol & Pattern Recognit Aachen Germany

ISBN: (纸本)9781424411795

A new method for localising and recognising hand poses and objects in real-time is presented. This problem is important in vision-driven applications where it is natural for a user to combine hand gestures and real objects when interacting with a machine. Examples include using a real eraser to remove words from a document displayed on an electronic surface. In this paper the task of simultaneously recognising object classes, hand gestures and detecting touch events is cast as a single classification problem. A random forest algorithm is employed which adaptively selects and combines a minimal set of appearance, shape and stereo features to achieve maximum class discrimination for a given image. This minimal set leads to both efficiency at run time and good generalisation. Unlike previous stereo works which explicitly construct disparity maps, here the stereo matching costs are used directly as visual cue and only computed on-demand, i.e. only for pixels where they are necessary for recognition. This leads to improved efficiency. The proposed method is assessed on a database of a variety of objects and hand poses selected for interacting on a flat surface in an office environment.

关键词： image classification image matching stereo image processing disparity maps hand gestures on-demand stereo random forest algorithm real eraser real objects real time recognition stereo matching vision-driven applications

来源：评论

学校读者我要写书评

暂无评论

Super-resolved all-refocused image with a plenoptic camera 9

Super-resolved all-refocused image with a plenoptic camera

引用

9th International Symposium on Multispectral Image Processing and pattern recognition (mippr) - pattern recognition and computer vision

作者： Wang, Xiang Li, Lin Hou, Guangqi Beijing Inst Technol Sch Optoelect 5 Zhongguancun South St Beijing 100081 Peoples R China Chinese Acad Sci Inst Automat Ctr Res Intelligent Percept & Comp Natl Lab Pattern Recognit Beijing 100190 Peoples R China

ISBN: (纸本)9781510600546

This paper proposes an approach to produce the super-resolution all-refocused images with the plenoptic camera. The plenoptic camera can be produced by putting a micro-lens array between the lens and the sensor in a conventional camera. This kind of camera captures both the angular and spatial information of the scene in one single shot. A sequence of digital refocused images, which are refocused at different depth, can be produced after processing the 4D light field captured by the plenoptic camera. The number of the pixels in the refocused image is the same as that of the micro-lens in the micro-lens array. Limited number of the micro-lens will result in poor low resolution refocused images. Therefore, not enough details will exist in these images. Such lost details, which are often high frequency information, are important for the in-focus part in the refocused image. We decide to super-resolve these in-focus parts. The result of image segmentation method based on random walks, which works on the depth map produced from the 4D light field data, is used to separate the foreground and background in the refocused image. And focusing evaluation function is employed to determine which refocused image owns the clearest foreground part and which one owns the clearest background part. Subsequently, we employ single image super-resolution method based on sparse signal representation to process the focusing parts in these selected refocused images. Eventually, we can obtain the super-resolved all-focus image through merging the focusing background part and the focusing foreground part in the way of digital signal processing. And more spatial details will be kept in these output images. Our method will enhance the resolution of the refocused image, and just the refocused images owning the clearest foreground and background need to be super-resolved.

关键词： Light field super resolution digital refocusing all-refocused

来源：评论

学校读者我要写书评

暂无评论

Local structure detection with orientation-invariant radial configuration

Local structure detection with orientation-invariant radial ...

引用

IEEE Conference on computer vision and pattern recognition

作者： Szumilas, Lech Donner, Rene Langs, Georg Hanbury, Allan Vienna Univ Technol Pattern Recognit & Image Proc Grp Favoritenstr 9-1832 A-1040 Vienna Austria Graz Univ Technol Inst Comp Graph & Vis A-8010 Graz Austria

ISBN: (纸本)9781424411795

Local image descriptors have proved themselves as useful tools for many computer vision tasks such as matching points between multiple images of a scene and object recognition. Current descriptors, such as SIFT, are designed to match image features with unique local neighborhoods. However, the interest point detectors used with SIFT often fail to select perceptible local structures in the image, and the SIFT descriptor does not directly encode the local neighborhood shape. In this paper we propose a symmetry based interest point detector and radial local structure descriptor which consistently captures the majority of basic local image structures and provides a geometrical description of the structure boundaries. This approach concentrates on the extraction of shape properties in image patches, which are an intuitive way to represent local appearance for matching and classification. We explore the specificity and sensitivity of this local descriptor in the context of classification of natural patterns. The implications of the performance comparison with standard approaches like SIFT are discussed.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

The role of context in object recognition

引用

TRENDS IN COGNITIVE SCIENCES 2007年第12期11卷 520-527页

作者： Oliva, Aude Torralba, Antonio MIT Dept Brain & Cognit Sci Cambridge MA 02139 USA Comp Sci & Artificial Intelligence Lab Cambridge MA 02139 USA

In the real world, objects never occur in isolation;they co-vary with other objects and particular environments, providing a rich source of contextual associations to be exploited by the visual system. A natural way of representing the context of an object is in terms of its relationship to other objects. Alternately, recent work has shown that a statistical summary of the scene provides a complementary and effective source of information for contextual inference, which enables humans to quickly guide their attention and eyes to regions of interest in natural scenes. A better understanding of how humans build such scene representations, and of the mechanisms of contextual analysis, will lead to a new generation of computer vision systems.

关键词： computer vision pattern recognition systems EYE INTEREST (Psychology) IMAGE processing

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC LEAF STRUCTURE BIOMETRY: computer vision TECHNIQUES AND THEIR APPLICATIONS IN PLANT TAXONOMY

引用

INTERNATIONAL JOURNAL OF pattern recognition AND ARTIFICIAL INTELLIGENCE 2009年第2期23卷 247-262页

作者： Plotze, Rodrigo De Oliveira Bruno, Odemir Martinez USP ICMC Dept Ciencias Comp BR-1356090 Sao Carlos SP Brazil USP ICMC Grp Comp Interdisciplinar BR-13560090 Sao Carlos SP Brazil

This paper proposes a new methodology to extract biometric features of plant leaf structures. Combining computer vision techniques and plant taxonomy protocols, these methods are capable of identifying plant species. The biometric measurements are concentrated in leaf internal forms, specifically in the veination system. The methodology was validated with real cases of plant taxonomy, and eleven species of passion fruit of the genus Passiflora were used. The features extracted from the leaves were applied to the neural network system to perform the classification of species. The results showed to be very accurate in correctly differentiating among species with 97% of success. The computer vision methods developed can be used to assist taxonomists to perform biometric measurements in plant leaf structures.

关键词： Image analysis biometry plant taxonomy morphometry computer vision

来源：评论

学校读者我要写书评

暂无评论

Kernel-based 3D tracking

Kernel-based 3D tracking

引用

IEEE Conference on computer vision and pattern recognition

作者： Tyagi, Ambrish Keck, Mark Davis, James W. Potamianos, Gerasimos Ohio State Univ Dept Comp Sci & Engn Columbus OH 43210 USA IBM Corp TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)9781424411795

We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstrapped by constructing 3D point clouds. These points clouds are then clustered and used to initialize the trackers and validate their performance. The framework describes a complete tracking system that fuses appearance features from all available camera sensors and is capable of automatic initialization and drift detection. Its elegance resides in its inherent ability to handle problems encountered by various 2D trackers, including scale selection, occlusion, view-dependence, and correspondence across views. Tracking results for an indoor smart room and a multi-camera outdoor surveillance scenario are presented We demonstrate the effectiveness of this unified approach by comparing its performance to a baseline 3D tracker that fuses results of independent 2D trackers, as well as comparing the re- initialization results to known ground truth.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A comparison of PMD-Cameras and stereo-vision for the task of surface reconstruction using patchlets

A comparison of PMD-Cameras and stereo-vision for the task o...

引用

IEEE Conference on computer vision and pattern recognition

作者： Beder, Christian Bartczak, Bogumil Koch, Reinhard Univ Kiel Dept Comp Sci Hermann Rodewald Str 3 D-24118 Kiel Germany

ISBN: (纸本)9781424411795

Recently real-time active 3D range cameras based on time-of-flight technology (PMD) have become available. Those cameras can be considered as a competing technique for stereo-vision based surface reconstruction. Since those systems directly yield accurate 3d measurements, they can be used for benchmarking vision based approaches, especially in highly dynamic environments. Therefore, a comparative study of the two approaches is relevant. In this work the achievable accuracy of the two techniques, PMD and stereo, is compared on the basis of patchlet estimation. As patchlet we define an oriented small planar 3d patch with associated surface normal. Least-squares estimation schemes for estimating patchlets from PMD range images as well as from a pair of stereo images are derived It is shown, how the achivable accuracy can be estimated for both systems. Experiments under optimal conditions for both systems are performed and the achievable accuracies are compared It has been found that the PMD system outperformed the stereo system in terms of achievable accuracy for distance measurements, while the estimation of normal direction is comparable for both systems.

关键词： Surface reconstruction

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：