检索结果-内蒙古大学图书馆

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

作者： Wendel, Andreas Irschara, Arnold Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria

ISBN: (纸本)9781457705298

We present a novel technique for the automatic alignment of Structure from Motion (SfM) models, acquired at ground level or by micro aerial vehicles, to an overhead Digital Surface Model (DSM) using GPS information. An additional refinement step based on the correlation of the DSM height map with the model height map corrects for the GPS localization uncertainties and results in precisely aligned models. Our approach successfully handles cases where previous methods had problems, including objects on the ground, unoccupied space, and models covering a small area. We conclude our work by presenting several applications of our approach, namely the fusion of detailed SfM model information into the original DSM, season-invariant matching using aligned models, and alignment for providing context in visualization. © 2011 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Microscopic shape from focus with optimal illumination

Microscopic shape from focus with optimal illumination

引用

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

作者： Lenz, Martin Ruther, Matthias Bischof, Horst Graz University of Technology Institute for Computer Graphics and Vision Inffeldgasse 16 8010 Graz Austria

ISBN: (纸本)9781457705298

We present a novel method for compensating illumination artifacts in shape from focus reconstruction that does not require additional measurement time. Frequently applied in optical microscopy, shape from focus requires rich surface texture over the whole scene. This prerequisite is violated in saturated image regions. To overcome this limitation, we automatically compensate for the scene reflectance by means of a projector-camera system on a per-image basis. We iteratively adapt illumination in the first image and consecutively track the compensation pattern through the image stack to reduce measurement time. Despite the low measurement time, our experiments show that our method outperforms the standard shape from focus approach and is also superior to competing methods like high dynamic range imaging in terms of measurement time and accuracy. © 2011 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Fast, recurrent, attentional modulation improves saliency representation and scene recognition

Fast, recurrent, attentional modulation improves saliency re...

引用

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

作者： Shi, Xun Bruce, Neil D. B. Tsotsos, John K. Department of Computer Science and Engineering Centre for Vision Research York University Toronto ON Canada

ISBN: (纸本)9781457705298

The human brain uses visual attention to facilitate object recognition. Traditional theories and models envision this attentional mechanism either in a pure feedforward fashion for selection of regions of interest or in a top-down task-priming fashion. To these well-known attentional mechanisms, we add here an additional novel one. The approach is inspired by studies of biological vision pertaining to the asynchronous timing of feedforward signals among different early visual areas and the role of recurrent connections from short latency areas to facilitate object recognition [7]. It is suggested that recurrence elicited from these short latency dorsal areas improves the slower feedforward processing in the early ventral areas. We therefore propose a computational model that simulates this process. To test this model, we add such fast recurrent processes to a well-known model of feedforward saliency, AIM [6] and show that those recurrent signals can modulate the output of AIM to improve its utility in recognition by later stages. We further add the proposed model to a back-propagation neural network for the task of scene recognition. Experimental results on standard video sequences show that the discriminating power of the modulated representation is significantly improved, and the implementation consistently outperforms existing work including a benchmark system that does not include recurrent refinement. © 2011 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

NeuFlow: A runtime reconfigurable dataflow processor for vision

NeuFlow: A runtime reconfigurable dataflow processor for vis...

引用

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

作者： Farabet, Clément Martini, Berin Corda, Benoit Akselrod, Polina Culurciello, Eugenio Lecun, Yann Courant Institute of Mathematical Sciences New York University New York NY United States Electrical Engineering Department Yale University New Haven CT United States

ISBN: (纸本)9781457705298

In this paper we present a scalable dataflow hardware architecture optimized for the computation of general-purpose vision algorithms neuFlow and a dataflow compiler luaFlow that transforms high-level flow-graph representations of these algorithms into machine code for neuFlow. This system was designed with the goal of providing real-time detection, categorization and localization of objects in complex scenes, while consuming 10 Watts when implemented on a Xilinx Virtex 6 FPGA platform, or about ten times less than a laptop computer, and producing speedups of up to 100 times in real-world applications. We present an application of the system on street scene analysis, segmenting 20 categories on 500 × 375 frames at 12 frames per second on our custom hardware neuFlow. © 2011 IEEE.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

Invited paper: Accelerating neuromorphic vision on FPGAs

Invited paper: Accelerating neuromorphic vision on FPGAs

引用

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

作者： Park, Sungho Kestur, Srinidhi Irick, Kevin M. Narayanan, Vijaykrishnan Department of Computer Science and Engineering Pennsylvania State University University Park PA 16802 United States

ISBN: (纸本)9781457705298

Reconfigurable hardware such as FPGAs are being increasingly employed for application acceleration due to their high degree of parallelism, flexibility and power efficiency factors which are key in the rapidly evolving field of embedded real-time vision. While recent advances in technology have increased the capacity of FPGAs, lack of standard models for developing custom accelerators creates issues with scalability and compatibility. In this paper, we describe a model for designing streaming hardware accelerators with run-time configurability. This model provides a generic interface for each hardware module, a modular and hierarchical structure for parallelism at multiple levels and a run-time reconfiguration framework for increased flexibility. We present case studies to accelerate sample neu-romorphic vision algorithms which are inspired by models of the mammalian visual cortex. Experimental results show speedups of several factors over comparable CPU implementations and higher performance-per-watt over relevant GPU implementations. © 2011 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

The image ray transform for structural feature detection

引用

pattern recognition LETTERS 2011年第15期32卷 2053-2060页

作者： Cummings, Alastair H. Nixon, Mark S. Carter, John N. Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ Hants England

The use of analogies to physical phenomena is an exciting paradigm in computer vision that allows unorthodox approaches to feature extraction, creating new techniques with unique properties. A technique known as the "image ray transform" has been developed based upon an analogy to the propagation of light as rays. The transform analogises an image to a set of glass blocks with refractive index linked to pixel properties and then casts a large number of rays through the image. The course of these rays is accumulated into an output image. The technique can successfully extract tubular and circular features and we show successful circle detection, ear biometrics and retinal vessel extraction. The transform has also been extended through the use of multiple rays arranged as a beam to increase robustness to noise, and we show quantitative results for fully automatic ear recognition, achieving 95.2% rank one recognition across 63 subjects. (C) 2011 Elsevier B.V. All rights reserved.

关键词： vision Feature extraction Circle detection Biometrics Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Viewpoint invariants from three-dimensional data: The role of reflection in human activity understanding

Viewpoint invariants from three-dimensional data: The role o...

引用

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

作者： Kakarala, Ramakrishna Kaliamoorthi, Prabhu Li, Wanqing Nanyang Technological University Singapore University of Wollongong Australia

ISBN: (纸本)9781457705298

Human activity understanding from three-dimensional data, such as from depth cameras, requires viewpoint-invariant matching. In this paper, we propose a new method of constructing invariants that allows distinction between isometries based on rotation, which preserve handedness, and those that involve reflection, which reverse right and left hands. The state-of-the-art in viewpoint invariants uses either global descriptors such as moments or spherical harmonic magnitudes, or relies on local methods such as feature matching. None of those methods are able to easily distinguish rotations from reflections, which is essential to understand left vs right handed gestures. We show that the distinction between rotation and reflection is contained in the imaginary part of certain weighted inner-products of moment vectors. We show how reflection-sensing viewpoint invariants may be applied to depth-map data for understanding activity data. © 2011 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Scaling up biologically-inspired computer vision: A case study in unconstrained face recognition on facebook

Scaling up biologically-inspired computer vision: A case stu...

引用

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

作者： Pinto, Nicolas Stone, Zak Zickler, Todd Cox, David Rowland Insitute at Harvard Harvard University Cambridge MA 02142 United States McGovern Institute for Brain Research MIT Cambridge MA 02139 United States School of Engineering and Applied Sciences Harvard University Cambridge MA 02138 United States

ISBN: (纸本)9781457705298

Biological visual systems are currently unrivaled by artificial systems in their ability to recognize faces and objects in highly variable and cluttered real-world environments. Biologically-inspired computer vision systems seek to capture key aspects of the computational architecture of the brain, and such approaches have proven successful across a range of standard object and face recognition tasks (e.g. [23, 8, 9, 18]). Here, we explore the effectiveness of these algorithms on a large-scale unconstrained real-world face recognition problem based on images taken from the Face-book social networking website. In particular, we use a family of biologically-inspired models derived from a high-throughput feature search paradigm [19, 15] to tackle a face identification task with up to one hundred individuals (a number that approaches the reasonable size of real-world social networks). We show that these models yield high levels of face-identification performance even when large numbers of individuals are considered;this performance increases steadily as more examples are used, and the models outperform a state-of-the-art commercial face recognition system. Finally, we discuss current limitations and future opportunities associated with datasets such as these, and we argue that careful creation of large sets is an important future direction. © 2011 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Shape recognition using machine learning

Shape recognition using machine learning

引用

6th Colombian Computing Congress (CCC)

作者： Gomez, Sebastian Univ Tecnol Pereira Syst & Comp Engn Pereira Colombia

ISBN: (纸本)9781457702860

computer vision is a growing field of computer science that intends to extract some useful information from images, usually taken from cameras or scanners. The ability to recognize shapes in images is often necessary in computer vision programs. This article describes how to make a program able to recognize basic geometrical figures by using machine learning. This article shows the image processing stages until feature extraction;Giving to the reader an idea of how to apply computer vision for other problems that involve shape recognition.

关键词： Artificial Intelligence Machine learning computer vision pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An optimized vision library approach for embedded systems

An optimized vision library approach for embedded systems

引用

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

作者： Dedeoǧlu, Göksel Kisačanin, Branislav Moore, Darnell Sharma, Vinay Miller, Andrew Texas Instruments Inc. Dallas TX United States

ISBN: (纸本)9781457705298

There is an ever-growing pressure to accelerate computer vision applications on embedded processors for wide-ranging equipment including mobile phones, network cameras, and automotive safety systems. Towards this goal, we propose a software library approach that eases common computational bottlenecks by optimizing over 60 low- and mid-level vision kernels. Optimized for a digital signal processor that is deployed in many embedded image & video processing systems, the library was designed for typical high-performance and low-power requirements. The algorithms are implemented in fixed-point arithmetic and support block-wise partitioning of video frames so that a direct memory access engine can efficiently move data between on-chip and external memory. We highlight the benefits of this library for a baseline video security application, which segments moving foreground objects from a static background. Benchmarks show a ten-fold acceleration over a bit-exact yet unoptimized C language implementation, creating more computational headroom to embed other vision algorithms. © 2011 IEEE.

关键词： Embedded 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：