检索结果-内蒙古大学图书馆

2011 IEEE Workshop on Applications of computer vision, WACV 2011

作者： Bauer, Sebastian Wasza, Jakob Müller, Kerstin Hornegger, Joachim Pattern Recognition Lab. Department of Computer Science University Erlangen-Nuremberg Germany

ISBN: (纸本)9781424494965

Methods for 2D/3D face recognition typically combine results obtained independently from the 2D and 3D data, respectively. There has not been much emphasis on data fusion at an early stage, even though it is at least potentially more powerful to exploit possible synergies between the two modalities. In this paper, we propose photogeometric features that interpret both the photometric texture and geometric shape information of 2D manifolds in a consistent manner. The 4D features encode the spatial distribution of gradients that are derived generically for any scalar field on arbitrary organized surface meshes. We apply the descriptor for biometric face recognition with a time-of-flight sensor. The method consists of three stages: (i) facial landmark localization with a HOG/SVM sliding window framework, (ii) extraction of photogeometric feature descriptors from time-of-flight data, using the inherent grayscale intensity information of the sensor as the 2D manifold's scalar field, (iii) probe matching against the gallery. recognition based on the photogeometric features achieved 97.5% rank-1 identification rate on a comprehensive time-of-flight dataset (26 subjects, 364 facial images). © 2010 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Interest Points Chain (STIPC) for Activity recognition

Spatio-Temporal Interest Points Chain (STIPC) for Activity R...

引用

1st Asian Conference on pattern recognition (ACPR)

作者： Yuan, Fei Xia, Gui-Song Sahbi, Hichem Prinet, Veronique Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China TELECOM ParisTech LTCI CNRS Paris France

ISBN: (纸本)9781457701214;9781457701221

We present a novel feature, named Spatio-Temporal Interest Points Chain (STIPC), for activity representation and recognition. This new feature consists of a set of trackable spatio-temporal interest points, which correspond to a series of discontinuous motion among a long-term motion of an object or its part. By this chain feature, we can not only capture the discriminative motion information which space-time interest point-like feature try to pursue, but also build the connection between them. Specifically, we first extract the point trajectories from the image sequences, then partition the points on each trajectory into two kinds of different yet close related points: discontinuous motion points and continuous motion points. We extract local space-time features around discontinuous motion points and use a chain model to represent them. Furthermore, we introduce a chain descriptor to encode the temporal relationships between these interdependent local space-time features. The experimental results on challenging datasets show that our STIPC features improves local space-time features and achieve state-of-the-art results.

关键词： Accuracy computer vision Feature extraction Humans pattern recognition Tracking Trajectory

来源：评论

学校读者我要写书评

暂无评论

Are face recognition methods useful for classifying ships?

Are face recognition methods useful for classifying ships?

引用

2011 IEEE Applied Imagery pattern recognition Workshop: Imaging for Decision Making, AIPR 2011

作者： Harguess, Josh Rainey, Katie Computer and Vision Research Center Department of ECE University of Texas at Austin Austin TX United States Space and Naval Warfare Systems Center Pacific San Diego CA United States

ISBN: (纸本)9781467302159

Face recognition research has gained significant interest in recent years which has resulted in the development of many state-of-the-art methods. However, it is not well-known how domain specific these methods are to the problem of face recognition. Could these algorithms be used to classify and identify other objects, such as ships seen from electro-optical satellite imagery? Face recognition research shares many of the same challenges with many other types of classification research, such as illumination, pose and resolution variation. Therefore, a study of this type is warranted. We present a comparison of several classical (e.g. eigenfaces and fisherfaces) as well as recent state-of-the-art face recognition methods (e.g. sparse representation and local binary patterns) using one standard face database and two databases of ship images collected from satellite imagery. An analysis of these results as well as future directions conclude the paper. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Image Analysis and Processing -- ICIAP 2011 2011

引用

丛书名： Lecture Notes in computer Science

2011年

作者： Giuseppe Maino Gian Luca Foresti

ISBN: (数字)9783642240850

ISBN: (纸本)9783642240843

The two-volume set LNCS 6978 + LNCS 6979 constitutes the proceedings of the 16th International Conference on Image Analysis and Processing, ICIAP 2011, held in Ravenna, Italy, in September 2011. The total of 121 papers presented was carefully reviewed and selected from 175 submissions. The papers are divided into 10 oral sessions, comprising 44 papers, and three post sessions, comprising 77 papers. They deal with the following topics: image analysis and representation; image segmentation; pattern analysis and classification; forensics, security and document analysis; video analysis and processing; biometry; shape analysis; low-level color image processing and its applications; medical imaging; image analysis and pattern recognition; image and video analysis and processing and its applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One video is sufficient? Human activity recognition using active video composition

One video is sufficient? Human activity recognition using ac...

引用

2011 IEEE Workshop on Applications of computer vision, WACV 2011

作者： Ryoo, M.S. Yu, Wonpil Electronics and Telecommunications Research Institute Daejeon Korea Republic of

ISBN: (纸本)9781424494965

In this paper, we present a novel human activity recognition approach that only requires a single video example per activity. We introduce the paradigm of active video composition, which enables one-example recognition of complex activities. The idea is to automatically create a large number of semi-artificial training videos called composed videos by manipulating an original human activity video. A methodology to automatically compose activity videos having different backgrounds, translations, scales, actors, and movement structures is described in this paper. Furthermore, an active learning algorithm to model the temporal structure of the human activity has been designed, preventing the generation of composed training videos violating the structural constraints of the activity. The intention is to generate composed videos having correct organizations, and take advantage of them for the training of the recognition system. In contrast to previous passive recognition systems relying only on given training videos, our methodology actively composes necessary training videos that the system is expected to observe in its environment. Experimental results illustrate that a single fully labeled video per activity is sufficient for our methodology to reliably recognize human activities by utilizing composed training videos. © 2010 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Wide-angle micro sensors for vision on a tight budget

Wide-angle micro sensors for vision on a tight budget

引用

作者： Koppal, Sanjeev J. Gkioulekas, Ioannis Zickler, Todd Barrows, Geoffrey L. Harvard University United States Centeye Inc. United States

ISBN: (纸本)9781457703942

Achieving computer vision on micro-scale devices is a challenge. On these platforms, the power and mass constraints are severe enough for even the most common computations (matrix manipulations, convolution, etc.) to be difficult. This paper proposes and analyzes a class of miniature vision sensors that can help overcome these constraints. These sensors reduce power requirements through template-based optical convolution, and they enable a wide field-of-view within a small form through a novel optical design. We describe the trade-offs between the field of view, volume, and mass of these sensors and we provide analytic tools to navigate the design space. We also demonstrate milli-scale prototypes for computer vision tasks such as locating edges, tracking targets, and detecting faces. © 2011 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

On analyzing video with very small motions

On analyzing video with very small motions

引用

作者： Dixon, Michael Abrams, Austin Jacobs, Nathan Pless, Robert Washington University St Louis United States University of Kentucky United States

ISBN: (纸本)9781457703942

We characterize a class of videos consisting of very small but potentially complicated motions. We find that in these scenes, linear appearance variations have a direct relationship to scene motions. We show how to interpret appearance variations captured through a PCA decomposition of the image set as a scene-specific non-parametric motion basis. We propose fast, robust tools for dense flow estimates that are effective in scenes with small motions and potentially large image noise. We show example results in a variety of applications, including motion segmentation and long-term point tracking. © 2011 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PIXHAWK: A System for Autonomous Flight using Onboard computer vision

PIXHAWK: A System for Autonomous Flight using Onboard Comput...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Meier, Lorenz Tanskanen, Petri Fraundorfer, Friedrich Pollefeys, Marc ETH Comp Vis & Geometry Lab CH-8092 Zurich Switzerland

ISBN: (纸本)9781612843858

We provide a novel hardware and software system for micro air vehicles (MAV) that allows high-speed, low-latency onboard image processing. It uses up to four cameras in parallel on a miniature rotary wing platform. The MAV navigates based on onboard processed computer vision in GPS-denied in-and outdoor environments. It can process in parallel images and inertial measurement information from multiple cameras for multiple purposes (localization, pattern recognition, obstacle avoidance) by distributing the images on a central, low-latency image hub. Furthermore the system can utilize low-bandwith radio links for communication and is designed and optimized to scale to swarm use. Experimental results show successful flight with a range of onboard computer vision algorithms, including localization, obstacle avoidance and pattern recognition.

关键词： Cameras computer vision Kalman filters Pipelines Protocols Universal Serial Bus Vehicles

来源：评论

学校读者我要写书评

暂无评论

Binary Confidence Evaluation for a Stereo vision Based Depth Field Processor SoC

Binary Confidence Evaluation for a Stereo Vision Based Depth...

引用

1st Asian Conference on pattern recognition (ACPR)

作者： Motten, Andy Claesen, Luc Pan, Yun Hasselt Univ tUL IBBT Expertise Ctr Digital Media Wetenschapspk 2 B-3590 Diepenbeek Belgium Zhejiang Univ Dept Informat Sci & Elect Engn Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781457701214;9781457701221

This paper presents a methodology to construct a binary confidence value for every pixel of a depth map. We start by constructing 72 different confidence metrics, including the traditional ones and new metrics based on neighborhood information. Construction of the binary confidence value from these metrics is hence viewed as a two-class classification problem where we evaluated three different classifiers, with increasing complexity. Only metrics and classifiers that are suitable for VLSI hardware implementation will be evaluated. Evaluation of the constructed classifiers is performed on an indoor dataset of Stereo Images.

关键词： component computer vision stereo confidence SoC binary adaptable window stereo matching

来源：评论

学校读者我要写书评

暂无评论

Moving-edge detection via heat flow analogy

引用

pattern recognition LETTERS 2011年第2期32卷 270-279页

作者： Direkoglu, Cem Nixon, Mark S. Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England

In this this paper a new and automatic moving-edge detection algorithm is proposed based on using the heat flow analogy This algorithm starts with anisotropic heat diffusion in the spatial domain to remove noise and sharpen region boundaries for the purpose of obtaining high quality edge data Then isotropic and linear heat diffusion is applied in the temporal domain to calculate the total amount of heat flow The moving-edges are represented as the total amount of heat flow out from the reference frame The overall process is completed by non-maxima suppression and hysteresis thresholding to obtain binary moving-edges Evaluation on a variety of data indicates that this approach can handle noise in the temporal domain because of the averaging inherent of isotropic heat flow Results also show that this technique can detect moving-edges in image sequences without background Image subtraction (C) 2010 Elsevier B V All rights reserved

关键词： Moving edges Feature extraction Image processing computer vision Heat flow

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：