检索结果-内蒙古大学图书馆

37th sibgrapi Conference on graphics, Patterns and images (sibgrapi)

作者： Pinto, Antonio Andrade, Felipe Suarez, Carlos Santos, Luiz Fernando Miranda, Frederico Michelon, Diogo Ribeiro, Roberto Ivson, Paulo Pontifical Catholic Univ Rio de Janeiro Tecgraf Inst Rio De Janeiro Brazil ENEVA SA Rio De Janeiro Brazil Pontifical Catholic Univ Rio de Janeiro Dept Informat Rio De Janeiro Brazil

ISBN: (纸本)9798350376043;9798350376036

In the quest for efficient hydrocarbon exploration, seismic reflection plays a pivotal role. However, the inherent ambiguity in geological features within seismic poses significant interpretation challenges, often necessitating costly analysis. We introduce a novel self-supervised approach utilizing Self Supervised Long Short-Term Memory (LSTM) networks. Our method significantly reduces the reliance on extensive annotated data, a common bottleneck in deep learning applications. We demonstrate that our sequence reconstruction task, employed as a pre-training method, leads to a marked improvement in model performance. Notably, our results exhibit a 5%-10% increase in mean Intersection over Union (mIoU) and an 8%-15% enhancement in mean precision compared to existing models. Our method demonstrates the potential of self-supervised techniques for advancing seismic data interpretation, leading to cost-effective and accurate geological mapping.

关键词： Auto-encoders LSTM Neural Networks Seismic image Segmentation

来源：评论

学校读者我要写书评

暂无评论

brazilian symposium of computer Graphic and image processing

Brazilian Symposium of Computer Graphic and Image Processing

引用

15th brazilian symposium on computer graphics and image processing, sibgrapi 2002

ISBN: (纸本)076951846X

the proceedings contain 87 papers. the topics discussed include: a semi-automatic surface reconstruction framework based on T-surfaces and isosurface extraction methods;DSVOL II - a distributed visualization and sonification application communicating via an XML-based protocol;visualizing inner structures in multimodal volume data;evaluating an adaptive windowing scheme in speckle noise MAP filtering;multispectral image data fusion using projections onto convex sets techniques;texture feature neural classifier for remote sensing image retrieval systems;filtering sparse data with 3D tensorial structuring elements;combining approximate geometry with view-dependent texture mapping - a hybrid approach to 3D video teleconferencing;improvement and invariance analysis of Zernike moments using as a region-based shape descriptor;automatic method for assessment of Telangiectasia degreeing by mathematical morphology;and approximating parametric curves with strip trees using affine arithmetic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel DSP architecture for reconstruction of tomographic images using wavelets techniques. 14

Parallel DSP architecture for reconstruction of tomographic ...

引用

14th brazilian symposium on computer graphics and image processing

作者： Pereira, MFL Koenigkan, LV Cruvinel, PE UFSCar Dept Comp BR-13565905 Sao Carlos SP Brazil

ISBN: (纸本)0769513301

this poster describes a technique for reconstructing tomographic images generated by a minitomograph scanner for soil science developed by Embrapa Agricultural Instrumentation using a parallel DSP architecture with an HEPC2E board from Hunt Engineering with two TMS320C40 processors from Texas Instruments. the software designed for visualization of bi-and tri-dimensional images uses Code Composer tool combined with Parallel C from 3L and Borland Builder C++. Reconstruction and interpolation tasks were distributed throughout the platform processors, using parallel algorithms in order to improve speed and processing power. the work resulted in an increase of about 15% in the system speed when compared with that reached using a classical platform at 200 MHz.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Viscosity solutions of a level-set method for anisotropic geometric diffusion in image processing

引用

JOURNAL OF MAthEMATICAL IMAGING AND VISION 2007年第2-3期29卷 205-217页

作者： Preusser, Tobias Univ Bremen Ctr Comp Syst & Visualizat CeVis D-28359 Bremen Germany

We discuss the existence of viscosity solutions for a class of anisotropic level-set methods which can be seen as an extension of the mean-curvature motion with a nonlinear anisotropic diffusion tensor. In an earlier work (Mikula et al. in Comput. Vis. Sci. 6(4):197-209, [2004];Preusser and Rumpf in SIAM J. Appl. Math. 62(5):1772-1793, [2002]) we have applied such methods for the denoising and enhancement of static images and image sequences. the models are characterized by the fact that-unlike the mean-curvature motion-they are capable of retaining important geometric structures like edges and corners of the level-sets. the article reviews the definition of the model and discusses its geometric behavior. the proof of the existence of viscosity solutions for these models is based on a fixed point argument which utilizes a compactness property of the diffusion tensor. For the application to image processing suitable regularizations of the diffusion tensor are presented for which the compactness assumptions of the existence proof hold. Finally, we consider the half relaxed limits of the solutions of auxiliary problems to show the compactness of the solution operator and thus the existence of a solution to the original problem.

关键词： image processing anisotropic diffusion level set method viscosity solution half relaxed limits

来源：评论

学校读者我要写书评

暂无评论

Viscosity solutions of a level-set method for anisotropic geometric diffusion in image processing

Viscosity solutions of a level-set method for anisotropic ge...

引用

19th brazilian symposium on computer graphics and image processing (sibgrapi 2006)

作者： Preusser, Tobias Univ Bremen Ctr Comp Syst & Visualizat CeVis D-28359 Bremen Germany

关键词： image processing anisotropic diffusion level set method viscosity solution half relaxed limits

来源：评论

学校读者我要写书评

暂无评论

Corresponding geometric distorted images using an uncertainty inference method

Corresponding geometric distorted images using an uncertaint...

引用

brazilian symposium on computer graphics and image processing (sibgrapi)

作者： J.D.S. da Silva P.O. Simoni UBS-Universidade Braz Cubas Sao Paulo Brazil INPE-Instituto Nacional de Pesquisas Espaciais Sao Paulo Brazil

We present further results of the application of Dempster-Shafer theory for uncertainty reasoning in corresponding distorted images in computer vision. In a previous work (J.D.S. Silva et al., 2002), the model was applied to correspond radiometrically distorted images, that is, images with differences in brightness and contrast, as an extension of the work developed by J.D.S. Silva et al. (2001). the results showed the model is robust when dealing with pairs of nonequalized images and encouraged us to try to correspond geometric distorted images, that is, pairs of images in which one is rotated in relation to the other. In the conducted experiments, the right image was rotated by different angles to simulate the desired geometric distortions. the model was applied to a pair of rotated images and it successfully established the correspondence of a pair of points. As in previous works, the correspondence evidences are based on the contextual and structural features of the points, and their combination is performed by Dempster-Shafer's rule of combination for uncertainty reasoning. A search process maximizes the belief on the combined evidences.

关键词： Uncertainty computer graphics image processing

来源：评论

学校读者我要写书评

暂无评论

Point set compression through BSP quantization

Point set compression through BSP quantization

引用

brazilian symposium on computer graphics and image processing (sibgrapi)

作者： Alex Bordignon thomas Lewiner Helio Lopes Geovan Tavares Rener Castro Departamento de Matemática-Matmídia Project PUC-Rio Rio de Janeiro Brazil

this work introduces a new compression scheme for point sets. this scheme relies on an adaptive binary space partition (BSP) which takes into account the geometric structure of the point set. this choice introduces geometrical rather than combinatorial information in the compression scheme. In order to effectively improve the final compression ratio, this partition is encoded in a progressive manner, decreasing the number of bits used for the quantisation at each subdivision. this strategy distributes the extra cost of the geometry encoding onto the maximal number of points, compressing in average 15% more than previous techniques

关键词： Quantization image coding Geometry Costs Encoding Solid modeling Collaborative work image reconstruction Tree graphs Data mining

来源：评论

学校读者我要写书评

暂无评论

Video Segmentation by Supervised Learning

Video Segmentation by Supervised Learning

引用

brazilian symposium on computer graphics and image processing (sibgrapi)

作者： G. Camara Chavez M. Cord F. Precioso S. Philipp-Foliguet Arnaldo De A. Araujo Federal University of Minas Gerais Computer Science Department Av. Antônio Carlos MG Brazil Equipe Traitment des Images et du Signal-ENSEA Cergy-Pontoise France Equipe Traitment des Images et du Signal-ENSEA France Federal University of Minas Gerais

In most of video shot boundary detection algorithms, proposed in the literature, several parameters and thresholds have to be set in order to achieve good results. In this paper, to get rid of parameters and thresholds, we explore a supervised classification method for video shot segmentation. We transform the temporal segmentation into a class categorization issue. Our approach defines a uniform framework for combining different kinds of features extracted from the video. Our method does not require any pre-processing step to compensate motion or post-processing filtering to eliminate false detected transitions. the experiments, following strictly the TRECVID 2002 competition protocol, provide very good results dealing with a large amount of features thanks to our kernel-based SVM classification method

关键词： Supervised learning Support vector machines Support vector machine classification Histograms Feature extraction Gunshot detection systems Statistical learning Machine learning Detection algorithms Motion detection

来源：评论

学校读者我要写书评

暂无评论

A Sketch-Based Modeling Framework Based on Adaptive Meshes

A Sketch-Based Modeling Framework Based on Adaptive Meshes

引用

brazilian symposium on computer graphics and image processing (sibgrapi)

作者： Emilio Vital Brazil Ronan Amorim Mario Costa Sousa Luiz Velho Luiz Henrique De Figueiredo Department of Computer Science University Of Calgary Canada IMPA Instituto Nacional de Matemática Pura e Aplicada Brazil IMPA Inst. Nac. de Mat. Pura e Aplic. Brazil

ISBN: (纸本)9781479942572

In the last 15 years many systems for sketch-based modeling have been developed. Much of this work has focused on the final results and describes the solutions from a technical and practical point of view. In this paper we take a more theoretical approach to the problem of sketch-based surface modeling (SBSM) and introduce a framework for SBSM systems based on adaptive meshes. the main advantage of this approach is to split the modeling operators and the final representation, allowing the creation of SBSM systems suitable for specific domains with different demands. In addition, we present two systems built on top of this framework, one with the capability to control local and global changes to the model and one that follows domain constraints.

关键词： Adaptation models Topology Geometry Computational modeling Surface treatment Solid modeling Approximation methods

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：