检索结果-内蒙古大学图书馆

2011 3rd National Conference on computer vision, pattern recognition, Image Processing and Graphics, NCVPRIPG 2011

作者： Patnaik, Renuka Gupta, Raj Mittal, Anurag Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai 600036 India

ISBN: (纸本)9780769545998

Local Binary pattern (LBP) has been the successful feature descriptor used for face recognition. The basic idea in this method is to convert from an intensity space to an order space where the order of neighboring pixels is used to create a monotonic change illumination-invariant code for each point in the image. A drawback for this method, however, is that, in homogenous regions, the order of the pixel with respect to its neighbors is quite noisy. In this paper, we propose to use a third value which indicates if two pixels are similar in value. We also propose to match these patterns using maximum bipartite matching rather than histogram matching. Significant performance boost was found when compared to LBP and other standard methods like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). We present our results on Extended Yale and FERET datasets. © 2011 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Occlusion robust multi-camera face tracking

Occlusion robust multi-camera face tracking

引用

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

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

ISBN: (纸本)9781457705298

This paper presents a novel approach to object tracking by using multiple views to assist with handling occlusion which improves the overall tracking result. The approach is applied to face tracking using a 3D cylinder head model, but any 3D rigid object may be tracked using this approach. All cameras in the system are used to estimate a joint motion model of the face, which is updated at each frame. Self-occlusion is handled by a weighted mask that depends on the pose of the face. Full face occlusion is first detected automatically by measuring and comparing image histograms of the current tracking result and a face template. If an occlusion from a camera is reported, it is not used in the global tracking result of the face from the multi-camera system. Experiments demonstrate that our method succeeds in tracking in both cases of self-occlusion and full face occlusion. Comparisons are made between single camera tracking, multi-camera tracking and occlusion robust multi-camera tracking using results from pose estimation. The performance of the occlusion robust multi-camera face tracking method is shown to produce more accurate estimates of the face pose and is able to estimate the face pose even under severe face occlusion. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Recognizing human-vehicle interactions from aerial video without training

Recognizing human-vehicle interactions from aerial video wit...

引用

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

作者： Lee, Jong Taek Chen, Chia-Chih Aggarwal, J.K. Computer and Vision Research Center Department of ECE University of Texas Austin United States

ISBN: (纸本)9781457705298

We propose a novel framework to recognize human-vehicle interactions from aerial video. In this scenario, the object resolution is low, the visual cues are vague, and the detection and tracking of objects are less reliable as a consequence. Any methods that require the accurate tracking of objects or the exact matching of event definition are better avoided. To address these issues, we present a temporal logic based approach which does not require training from event examples. At the low-level, we employ dynamic programming to perform fast model fitting between the tracked vehicle and the rendered 3-D vehicle models. At the semantic-level, given the localized event region of interest (ROI), we verify the time series of human-vehicle relationships with the pre-specified event definitions in a piecewise fashion. With special interest in recognizing a person getting into and out of a vehicle, we have tested our method on a subset of the VIRAT Aerial Video dataset [11] and achieved superior results. Our framework can be easily extended to recognize other types of human-vehicle interactions. © 2011 IEEE.

关键词： Tracked vehicles

来源：评论

学校读者我要写书评

暂无评论

Rapid reconstruction of small objects on mobile phones

Rapid reconstruction of small objects on mobile phones

引用

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

作者： Hartl, Andreas Gruber, Lukas Arth, Clemens Hauswiesner, Stefan Schmalstieg, Dieter Institute for Computer Graphics and Vision Graz Technical University Inffeldgasse 16/2 8010 Austria

ISBN: (纸本)9781457705298

Augmented Reality (AR) on mobile phones is receiving more and more attention recently, becoming a popular research topic and an important commercial field. In this paper we present a lightweight method to create coarse 3D models of small-scale objects. The goal is to give the users the possibility to create and maintain AR content themselves without the need for expensive tools and complex interaction. Our algorithm is based on shape-from-silhouette using voxel carving and runs on modern smartphone hardware. 3D models of certain object groups can be generated interactively and instantly. The actual result is visualized continuously using image based rendering methods to inform the user about the actual model quality. Given a suitably accurate model it can further be used for any means of AR and can easily be shared with other users. The usability of our approach is evaluated using modern smartphone hardware (see Figure 1). The advantages are demonstrated using a set of models for playing a board game. © 2011 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Hand vein biometry based on geometry and appearance methods

引用

IET computer vision 2011年第6期5卷 398-406页

作者： Yuksel, A. Akarun, L. Sankur, B. Bogazici Univ Dept Comp Engn Istanbul Turkey Bogazici Univ Dept Elect & Elect Engn Istanbul Turkey

Many biometric systems, such as face, fingerprint and iris have been studied extensively for personal verification and identification purposes. Biometric identification with vein patterns is a more recent approach that uses the vast network of blood vessels underneath a person's skin. These patterns in the hands are assumed to be unique to each individual and they do not change over time except in size. As veins are under the skin and have a wealth of differentiating features, an attempt to copy an identity is extremely difficult. These properties of uniqueness, stability and strong immunity to forgery of the vein patterns make it a potentially good biometric trait which offers greater security and reliable features for personal identification. In this study, the authors present a novel hand vein database and a biometric technique based on the statistical processing of the hand vein patterns. The BOSPHORUS hand vein database has been collected under realistic conditions in that subjects had to undergo the procedures of holding a bag, pressing an elastic ball and cooling with ice, all exercises that force changes in the vein patterns. The applied recognition techniques are a combination of geometric and appearance-based techniques and good identification performances have been obtained on the database.

关键词： Spatial and pictorial databases visual databases vein recognition biometric trait biometric identification hand vein biometry BOSPHORUS hand vein database hand vein pattern statistical processing geometric technique appearance methods computer vision and image processing techniques Image recognition blood vessels

来源：评论

学校读者我要写书评

暂无评论

A comparative study of image processing algorithms

引用

pattern recognition and Image Analysis 2011年第2期21卷 148-151页

作者： Koltsov, P.P. Scientific Research Institute for System Studies Russian Academy of Sciences Nakhimovskii pr. 34 Moscow 117218 Russia

We compared the performances of the well-known image processing algorithms run on a set of reference images. For this, the algorithm-distorted images are compared against "ground truth" images. © 2011 P... 详细信息

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Contour Detection and Hierarchical Image Segmentation

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2011年第5期33卷 898-916页

作者： Arbelaez, Pablo Maire, Michael Fowlkes, Charless Malik, Jitendra Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA CALTECH Dept Elect Engn Pasadena CA 91125 USA Univ Calif Irvine Dept Comp Sci Irvine CA 92697 USA

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.

关键词： Contour detection image segmentation computer vision

来源：评论

学校读者我要写书评

暂无评论

Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture

Improved anomaly detection in crowded scenes via cell-based ...

引用

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

作者： Reddy, Vikas Sanderson, Conrad Lovell, Brian C. NICTA PO Box 6020 St Lucia QLD 4067 Australia University of Queensland School of ITEE QLD 4072 Australia

ISBN: (纸本)9781457705298

A robust and efficient anomaly detection technique is proposed, capable of dealing with crowded scenes where traditional tracking based approaches tend to fail. Initial foreground segmentation of the input frames confines the analysis to foreground objects and effectively ignores irrelevant background dynamics. Input frames are split into non-overlapping cells, followed by extracting features based on motion, size and texture from each cell. Each feature type is independently analysed for the presence of an anomaly. Unlike most methods, a refined estimate of object motion is achieved by computing the optical flow of only the foreground pixels. The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets. Texture features are modelled by an adaptively grown code-book, with the number of entries in the codebook selected in an online fashion. Experiments on the recently published UCSD Anomaly Detection dataset show that the proposed method obtains considerably better results than three recent approaches: MPPCA, social force, and mixture of dynamic textures (MDT). The proposed method is also several orders of magnitude faster than MDT, the next best performing method. © 2011 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning of Graph Structure

引用

1st International Workshop on Similarity-Based pattern recognition (SIMBAD)

作者： Torsello, Andrea Rossi, Luca Univ Ca Foscari Venezia Dipartimento Sci Ambientali Informat & Stat Venice Italy

ISBN: (纸本)9783642244704;9783642244711

Graph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure. Despite this, the methodology available for learning structural representations from sets of training examples is relatively limited. In this paper we take a simple yet effective Bayesian approach to attributed graph learning. We present a naive node-observation model, where we make the important assumption that the observation of each node and each edge is independent of the others, then we propose an EM-like approach to learn a mixture of these models and a Minimum Message Length criterion for components selection. Moreover, in order to avoid the bias that could arise with a single estimation of the node correspondences, we decide to estimate the sampling probability over all the possible matches. Finally we show the utility of the proposed approach on popular computer vision tasks such as 2D and 3D shape recognition.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sparsity-based Image Denoising via Dictionary Learning and Structural Clustering

Sparsity-based Image Denoising via Dictionary Learning and S...

引用

IEEE Conference on computer vision and pattern recognition (CVPR)

作者： Dong, Weisheng Li, Xin Zhang, Lei Shi, Guangming Xidian Univ Xian Peoples R China West Virginia Univ Morgantown WV 26506 USA Hong Kong Polytech Univ Hong Kong Peoples R China

ISBN: (纸本)9781457703935

Where does the sparsity in image signals come from? Local and nonlocal image models have supplied complementary views toward the regularity in natural images the former attempts to construct or learn a dictionary of basis functions that promotes the sparsity;while the latter connects the sparsity with the self-similarity of the image source by clustering. In this paper, we present a variational framework for unifying the above two views and propose a new denoising algorithm built upon clustering-based sparse representation (CSR). Inspired by the success of l(1)-optimization, we have formulated a double-header l(1)-optimization problem where the regularization involves both dictionary learning and structural structuring. A surrogate-function based iterative shrinkage solution has been developed to solve the double-header l(1)-optimization problem and a probabilistic interpretation of CSR model is also included. Our experimental results have shown convincing improvements over state-of-the-art denoising technique BM3D on the class of regular texture images. The PSNR performance of CSR denoising is at least comparable and often superior to other competing schemes including BM3D on a collection of 12 generic natural images.

关键词： Dictionaries as Topic image denoising image signal Noise reduction GRAIN pattern images Cluster Analysis

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：