检索结果-内蒙古大学图书馆

2013 26th Conference on graphics, Patterns and images, SIBGRAPI 2013

作者： Martinez, John Jairo Hernandez, Jose Tiberio Rodriguez, Carlos F. Department of Computer Science Universidad de Los Andes Bogota Colombia Department of Mechanical Engineering Universidad de Los Andes Bogota Colombia

ISBN: (纸本)9780769550992

In this paper we propose a visual estimation algorithm to aid the guidance system of an unmanned aerial vehicle (UAV). Specifically, we are considering a glider UAV trying to reach a target zone. Given that the UAV is falling fast, the scale of the images captured by the on-board camera grows. the vehicle dynamics and the control algorithm cause fast changes in the region seen by the camera and in the way it projects to the image plane. We propose an algorithm based on projective transformations to estimate the target coordinate during the flight trajectory. the proposed vision algorithm provides accurate position information allowing the control system to guide the UAV to the target zone. Simulations have shown the accuracy of the vision algorithm and its usefulness in the considered application. © 2013 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Subjective quality evaluation applied to scalable video coding 08

Subjective quality evaluation applied to scalable video codi...

引用

14th brazilian symposium on Multimedia and the Web - WebMedia 2008

作者： Daronco, Leonardo Crauss Roesler, Valter De Lima, José Valdeni UFRGS - Universidade Federal Do Rio Grande Do Sul Av. Bento Gonçalves 9500 Bloco IV CEP 91501-970 POA/RS Brazil

ISBN: (纸本)9781605581705

this paper presents a subjective video quality study of video sequences coded using the scalable extension of the H.264 standard (SVC). A group of experiments was performed to measure, primarily, the effects of transmission instability and the influence of the three scalability methods (spatial, temporal and quality) on the video quality. the definitions were based on a layered transmission system using protocols for adaptability and congestion control. To run the subjective assessment we used the ACR-HRR methodology and recommendations given by ITU-R Rec. BT.500 and ITU-T Rec. P.910. the results show that instability does not causes significant alterations on the overall video subjective quality and that the temporal scalability usually presents far lower subjective quality than spatial and quality scalabilities. Copyright © held by author/owner.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Segmentation of large images with complex networks

Segmentation of large images with complex networks

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Cuadros, Oscar Botelho, Glenda Rodrigues, Francisco Neto, João Batista São Carlos Brazil

ISBN: (纸本)9780769548296

image segmentation is still a challenging issue in pattern recognition. Among the various segmentation approaches are those based on graph partitioning, which present some drawbacks, one being high processing times. With the recent developments on complex networks theory, pattern recognition techniques based on graphs have improved considerably. the identification of cluster of vertices can be considered a process of community identification according to complex networks theory. Since data clustering is related with image segmentation, image segmentation can also be approached via complex networks. However, image segmentation based on complex networks poses a fundamental limitation which is the excessive numbers of nodes in the network. this paper presents a complex network approach for large image segmentation that is both accurate and fast. To that, we incorporate the concept of super pixels, to reduce the number of nodes in the network. We evaluate our method for both synthetic and real images. Results show that our method can outperform other graph-based methods both in accuracy and processing times. © 2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm for fractal analysis of textures

An efficient algorithm for fractal analysis of textures

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Costa, Alceu Ferraz Humpire-Mamani, Gabriel Traina, Agma Juci MacHado Department of Computer Science University of São Paulo USP São Carlos Brazil

ISBN: (纸本)9780769548296

In this paper we propose a new and efficient texture feature extraction method: the Segmentation-based Fractal Texture Analysis, or SFTA. the extraction algorithm consists in decomposing the input image into a set of binary images from which the fractal dimensions of the resulting regions are computed in order to describe segmented texture patterns. the decomposition of the input image is achieved by the Two-threshold Binary Decomposition (TTBD) algorithm, which we also propose in this work. We evaluated SFTA for the tasks of content-based image retrieval (CBIR) and image classification, comparing its performance to that of other widely employed feature extraction methods such as Haralick and Gabor filter banks. SFTA achieved higher precision and accuracy for CBIR and image classification. Additionally, SFTA was at least 3.7 times faster than Gabor and 1.6 times faster than Haralick with respect to feature extraction time. © 2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Automatic image segmentation by tree pruning

引用

JOURNAL OF MAthEMATICAL IMAGING AND VISION 2007年第2-3期29卷 141-162页

作者： Bergo, Felipe P. G. Falcao, Alexandre X. Miranda, Paulo A. V. Rocha, Leonardo M. Univ Estadual Campinas LIV Inst Comp BR-13083970 Campinas SP Brazil Univ Estadual Campinas DECOM FEEC BR-13083970 Campinas SP Brazil

the image Foresting Transform (IFT) is a tool for the design of image processing operators based on connectivity, which reduces image processing problems into an optimum-path forest problem in a graph derived from the image. A new image operator is presented, which solves segmentation by pruning trees of the forest. An IFT is applied to create an optimum-path forest whose roots are seed pixels, selected inside a desired object. In this forest, object and background are connected by optimum paths (leaking paths), which cross the object's boundary through its "most weakly connected" parts (leaking pixels). these leaking pixels are automatically identified and their subtrees are eliminated, such that the remaining forest defines the object. Tree pruning runs in linear time, is extensible to multidimensional images, is free of ad hoc parameters, and requires only internal seeds, with little interference from the heterogeneity of the background. these aspects favor solutions for automatic segmentation. We present a formal definition of the obtained objects, algorithms, sufficient conditions for tree pruning, and two applications involving automatic segmentation: 3D MR-image segmentation of the human brain and image segmentation of license plates. Given that its most competitive approach is the watershed transform by markers, we also include a comparative analysis between them.

关键词： image segmentation graph-search algorithms image foresting transform image processing watershed transform

来源：评论

学校读者我要写书评

暂无评论

A maximum-likelihood approach for multiresolution W-operator design

A maximum-likelihood approach for multiresolution W-operator...

引用

SIBGRAPI 2005: 18th brazilian symposium on computer graphics and image processing - Conference Proceedings

作者： Vaquero, Daniel André Barrera, Junior Hirata Jr., Roberto USP-Universidade de São Paulo IME-Instituto de Matemática e Estatística Cidade Universitária Rua do Matão 1010 CEP: 05508-090 São Paulo SP Brazil

ISBN: (纸本)0769523897

the design of W-operators from a set of input/output examples for large windows is a hard problem. From the statistical standpoint, it is hard because of the large number of examples necessary to obtain a good estimate of the joint distribution. From the computational standpoint, as the number of examples grows memory and time requirements can reach a point where it is not feasible to design the operator. this paper introduces a technique for joint distribution estimation in W-operator design. the distribution is represented by a multiresolution pyramidal structure and the mean conditional entropy is proposed as a criterion to choose between distributions induced by different pyramids. Experimental results are presented for maximum-likelihood classifiers designed for the problem of handwritten digits classification. the analysis shows that the technique is interesting from the theoretical point of view and has potential to be applied in computer vision and image processing problems. © 2005 IEEE.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Comparison of image processing techniques (magnetic resonance imaging, computed tomography scan and ultrasound) for 3D modeling and analysis of the human bones

引用

JOURNAL OF DIGITAL IMAGING 1997年第3期10卷 203-206页

作者： Mehta, BV Rajani, S Sinha, G GEN MOTORS DIMENS CONTROL SYSTDETROITMI LEXEL ENGN TROYMI

Magnetic resonance imaging (MRI), computed tomography scanning (CT scan), and ultrasound imaging techniques {UI} were used for data acquisition to construct/develop a 3D solid model of the human tibia, femur, and skull, CT scan was found to he an acceptable technique for cadavers. CT scans are harmful to the human body in large doses, while MRIs and ultrasound are known to be safe. However, MRIs form a better tool in performing this image generation task for living beings because of its high resolution capacity when compared with images obtained using ultrasound techniques. High resolution poses to be a very important factor, as the consideration of various material properties of the bones was part of the emphasis of this research. MRIs have the capacity of displaying a distinct boundary between the muscles and the bone, in addition to the boundary between the cortical and the cancellous region within the bone. Ultrasound was found to be the cheapest technique and gave reasonably good results for just the outside boundaries of the bone. the models of the human bones were generated on a computer Aided Design (CAD) system, the cross-sections obtained from (MRI, CT, or UI) were scanned into the computer. image processing software was used to detect the boundaries of the bones. A C + + program was used to read the coordinates of the edges and construct a B-spline curve on the CAD system. the curves were converted to a B-rep solid using skinning. the solid models were meshed, constrained, and material properties were assigned to different regions of the models for Finite Element Analysis (FEM). Copyright (C) 1997 by W.B. Saunders Company.

关键词： 3-D modeling FEM biomechanics MRI CT scan ultrasound

来源：评论

学校读者我要写书评

暂无评论

Instanced Rendering of Massive CAD Models Using Shape Matching 27

Instanced Rendering of Massive CAD Models Using Shape Matchi...

引用

27th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Ivson, Paulo Celes, Waldemar Pontifical Catholic Univ Rio de Janeiro PUC Rio Dept Comp Sci Rio De Janeiro Brazil Pontifical Catholic Univ Rio de Janeiro PUC Rio Tecgraf Inst Tech Sci Software Dev Rio De Janeiro Brazil

ISBN: (纸本)9781479942602

We present an efficient approach to greatly reduce memory usage and to achieve high rendering performance for massive 3D CAD models. Our work is based on the observation that these models often contain many instances of the same geometries. Using a shape matching algorithm, we identify these instances and estimate the optimal affine transformation between them. the resulting sets of unique geometries only require a fraction of the memory used by the original 3D model. this compact representation can be rendered efficiently using hardware-accelerated geometry instancing. As another benefit, this allows for interactive rendering of highly dynamic scenes of up to a million moving objects. Our proposal assumes no knowledge about the scene, and thus can be applied to other kinds of massive 3D models with similar properties.

关键词： graphics computer graphics Shape CADCAM

来源：评论

学校读者我要写书评

暂无评论

Detection of unusual motion using computer vision

Detection of unusual motion using computer vision

引用

SIBGRAPI 2006: 19th brazilian symposium on computer graphics and image processing

作者： Jung, Cláudio R. Jacques Jr., Julio C. S. Soldera, John Musse, Soraia R. PIPCA Graduate School on Applied Computing Universidade do Vale do Rio dos Sinos Av. UNISINOS 950 São Leopoldo RS 93022-000 Brazil

ISBN: (纸本)0769526861

In this paper, we propose different criteria for detecting unusual motion in surveillance cameras. Initially, a certain environment is observed within a time interval, and captured trajectories are used as examples of usual trajectories. these trajectories are used to build a Spatial Occupancy Map (SpOM, which is introduced in this paper) of the observed people, as well as main flow directions. In the test period, each new trajectory is classified as normal or unusual with respect to spatial occupancy and trajectory consistency. the spatial occupancy criterion considers the relation of space occupancy between the new tracked trajectory and the observed period. the trajectory consistency criterion considers the agreement of the new trajectory with the main flows extracted in the training period. Experimental results showed that these criteria can be used as an automatic pre-screening of suspect motion in surveillance applications. © 2006 IEEE.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Capture and stylization of human models

Capture and stylization of human models

引用

2013 26th Conference on graphics, Patterns and images, SIBGRAPI 2013

作者： De Aguiar, Edilson Costalonga, Leandro Lesqueves Rigo Jr., Luis Otavio Villaca, Rodolfo Da Silva DCEL CEUNES UFES Sao Mateus ES Brazil

ISBN: (纸本)9780769550992

Capturing and creating models of human subjects is an ongoing effort in computer graphics. In this paper, we present a framework to capture, model, simplify, and stylize an human subject. We use a consumer 3D depth camera that captures the appearance, shape, and pose of the recorded person. We then fit this data with a parametric human model that is based on 3D scans available from the CAESAR database. Once we have a personalized 3D human model, we can apply stylization techniques to create a variety of outputs. We present several results obtained with our framework and verify that these models remain recognizable as their human sources. © 2013 IEEE.

关键词： computer graphics

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：