检索结果-内蒙古大学图书馆

作者： Kropatsch, Walter G. Haxhimusa, Yll Pizlo, Zygmunt Langs, Georg Inst. of Computer Aided Automation Pattern Recog. Image Proc. G. Vienna University of Technology Favoritenstrasse 9 A-1040 Vienna Austria Department of Psychological Sciences Sch. of Elec. and Comp. Engineering Purdue University West Lafayette IN 47907-1364 United States Inst. for Comp. Graphics and Vision Graz University of Technology Inffeldgasse 16 2.OG A-8010 Graz Austria

In irregular pyramids, their vertical structure is not determined beforehand as in regular pyramids. We present three methods, all based on maximal independent sets from graph theory, with the aim to simulate the major sampling properties of the regular counterparts: good coverage of the higher resolution level, not too large sampling gaps and, most importantly, the resulting height, e.g. the number of levels to reach the apex. We show both theoretically and experimentally that the number of vertices can be reduced by a factor of 2.0 at each level. The plausibility of log (diameter) pyramids is supported by psychological and psychophysical considerations. Their technical relevance is demonstrated by enhancing appearance-based object recognition. An irregular pyramid hypothesis generation for robust PCA through top-down attention mechanisms achieves higher speed and quality than regular pyramids and non-pyramidal approaches. © 2004 Elsevier B.V. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Fast data association algorithm of passive sensor tracking

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2000年第12期28卷 45-47+44页

作者： Wang, Ming-Hui You, Zhi-Sheng Zhao, Rong-Chun Zhang, Jian-Zhou Feng, Zi-Liang 1105 of the Dept. of Comp. Sci. Northwestern Polytech. Univ. Xi'an 710071 China Inst. of Image and Graphics Sichuan Univ. Chengdu 610064 China

A fast data association algorithm based on the attribute intensity of space intersection for the static association problem is presented in this paper. All of sensors are passive sensors, which obtained the angle only, in presence of clutter, missed detection, false alarm, and an unknown number and location of targets. comp.rison of our method to the classical algorithm demonstrates that our algorithm is superior to the classical approach in terms of comp.tational comp.exity and association accuracy via several simulations.

关键词： Sensors

来源：评论

学校读者我要写书评

暂无评论

Augmented-reality-based liver-surgical planning system

引用

European Surgery - Acta Chirurgica Austriaca 2004年第5期36卷 270-274页

作者： Werkgartner, G. Lemmerer, M. Hauser, H. Sorantin, E. Beichel, R. Reitinger, B. Bornik, A. Leberl, F. Mischinger, H.J. Division of General Surgery Department of Surgery Medical University of Graz Graz Austria Department of Radiology Medical University of Graz Graz Austria Inst. for Comp. Graphics and Vision Graz University of Technology Graz Austria Division of General Surgery Department of Surgery Medical University of Graz 8036 Graz Auenbruggerplatz 29 Austria

Background: The preoperative planning of liver resections is commonly based on two-dimensional imaging techniques such as sonography, comp.ted tomography (CT), and magnetic resonance imaging. The operability of liver tumors depends on the three-dimensional relation of the parenchyma to be resected to the intrahepatic vascular structures which define the autonomously functioning liver segments. Our aim was to establish a liver surgery planning system (LSPS) for major liver resections by augmented-reality (AR) techniques for the accurate evaluation of operability. Methods: The system provides methods for the processing and preparation of the input CT data, three-dimensional visualization, and resection planning. The output consists of quantitative indices (e.g., volume of liver tumors or segments) and an elaborated plan for the surgical procedure including information like the number of liver segments subject to resection and their spatial arrangement or the volume of the remaining or the removed liver tissue. Basically, the LSPS comp.ises two main comp.nents, a medical image analysis and an AR system. The medical image analysis part is responsible for the segmentation of the liver, the vascular structures, and the tumors and for liver segment approximation. The AR system is utilized for visualization and various kinds of user interaction. Results: Experiments with anonymized CT data sets demonstrated the ability of surgeons to deal with different tasks in resection planning after a brief introduction. This led also to a high acceptance by colleagues who wanted to get information for their surgical strategy as quickly as possible. Conclusions: Quantitative measurements are of major importance for the planning of liver resections, for which precise measurements of distances and volumes are required. On the basis of the patient's CT dataset, the LSPS supports an effective way to find the optimal surgical strategy for each patient. The flexible design of this system allo

关键词： Image processing Liver resection planning Medical imaging Three-dimensional visualization

来源：评论

学校读者我要写书评

暂无评论

Robust occupancy detection from stereo images

Robust occupancy detection from stereo images

引用

Proceedings - 7th International IEEE Conference on Intelligent Transportation Systems, ITSC 2004

作者： Alefs, Bram Clabian, Markus Bischof, Horst Kropatsch, Walter Khairallah, Farid Adv. Comp. Vision GmbH ACV Vienna Donau-City-Strasse 1 A-1220 Vienna Austria Advanced Computer Vision GmbH ACV Farmington Hills MI 48335 United States Inst. for Comp. Graphics and Vision Graz University of Technology Inffeldgasse 16 2. OG A-8010 Graz Austria Computer Science Department Inst. of Computer Aided Automation Vienna University of Technology Favoritenstrasse 9/1832 A-1040 Vienna Austria TRW Automotive 24175 Research Drive Farmington Hills MI 48335 United States

Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This paper presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Knowledge discovery in patent databases

Knowledge discovery in patent databases

引用

Proceedings of the Eleventh International Conference on Information and Knowledge Management (CIKM 2002)

作者： Markellos, Konstantinos Markellou, Penelope Mayritsakis, George Perdikuri, Katerina Sirmakessis, Spiros Tsakalidis, Athanasios Multimedia Graphics and GIS Lab. Computer Eng. and Info. Dept. University of Patras 26500 Patras Greece Research Acad. Comp. Technol. Inst. Internet Multimedia Technol Res Unit 61 Riga Feraiou Str. 26221 Patras Greece

In our days the business, scientific and personal databases are growing in an exponential rate. However, what is truly valuable is the knowledge that can be extracted from the stored data. Knowledge Discovery in patent databases was traditionally based on manual analysis carried out from statistical experts. Nowadays the increasing interest of many actors have led to the development of new tools for discovering and exploiting information related to technological activities and innovation, "hidden" in patent databases. In this paper we present a system that combines efficient and innovative methodologies and tools for the analysis of patent data stored in international databases and the production of scientific and technological indicators.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Dynamic approach to skeletonization

引用

Ruan Jian Xue Bao/Journal of Software 2003年第4期14卷 818-823页

作者： Che, Wu-Jun Yang, Xun-Nian Wang, Guo-Zhao Inst. of Comp. Graphics Dept. of Math. Zhejiang Univ. Hangzhou 310027 China

The skeleton is an effective representation of object shapes. Methods based on distance transformation can generate skeletons with accurate position, but connectivity of the skeleton branches must be carefully checked. It is difficult to check the connectivity when the structures of the skeleton are very comp.icated. A dynamic skeleton algorithm for binary images is presented by combining with thinning method and Snake model technique. First, we comp.te the initial skeleton based on thinning technology in which the connectivity and the topology of the skeleton can be kept well. Then the initial skeleton can be led to its accurate locations in distance field based on Snake model technique. The skeletons generated by this method are not only locating at accurate positions, but also with correct connectivity and topology.

关键词： comp.ter graphics

来源：评论

学校读者我要写书评

暂无评论

Image segmentation and its algorithm based on fuzzy connectedness

引用

Ruan Jian Xue Bao/Journal of Software 2005年第1期16卷 67-76页

作者： Pan, Jian-Jiang Yang, Xun-Nian Wang, Guo-Zhao Dept. of Math. Inst. of Comp. Graphics Zhejiang Univ. Hangzhou 310027 China

A modification to the fuzzy connectedness image segmentation is presented. Through checking the property affinity between the seed pixel and the pixel along the optimal path which has the largest fuzzy connectedness from the pixel to seed pixel, good results can be achieved, especially for those objects with blurred boundary. Additionally, an image-scanning mechanism algorithm for detecting optimal paths is proposed to calculate the fuzzy connectedness between pixels and the seed pixel one by one. This algorithm can make full use of the properties of fuzzy connectedness and property affinity, and detect the optimal path between two pixels effectively. Experimental examples show that the new method is simple, fast, and works well for some images.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Layered surfaces reconstruction algorithm from large volumetric datasets

引用

Ruan Jian Xue Bao/Journal of Software 2003年第8期14卷 1448-1455页

作者： Lu, Sheng-Min Yang, Xun-Nian Wang, Guo-Zhao Inst. of Comp. Graphics Dept. of Math. Zhejiang Univ. Hangzhou 310027 China

Surfaces reconstruction from serial section images is a mature research in visualization of medical imaging. Traditional methods always adopt the process that starts on mesh reconstruction or isosurfaces extraction, then data simplification. Since the volumetric datasets are huge and segmented. Most of the existing algorithms that use large in-core data structures might be too large to off-load to disk. An algorithm is presented that is designed to reconstruct 3D surfaces from huge and segmented volumetric datasets. Approximate mesh can be reconstructed and simplified layer by layer. And user can control mesh comp.exity by parameters. Because memories are used rationally, some surfaces reconstruction from large datasets can work on PC using the algorithm.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Object recognition and video indexing for media analysis

OGAI Journal (Oesterreichische Gesellschaft fuer Artificial ...

引用

OGAI Journal (Oesterreichische Gesellschaft fuer Artificial Intelligence) 2005年第1期24卷 4-10页

作者： Ober, Sandra Neuschmied, Helmut Bischof, Horst Wessely, Christian Inst. for Comp. Graphics and Vision TU Graz Inffeldgasse 16/2 8010 Graz Austria Joanneum Research Graz Steyrergasse 17 8010 Graz Austria Institute for Fundamental Theology KFU Graz Attemsgasse 8/4 8010 Graz Austria

This contribution presents a video analysis system which provides automatic content analysis and enables manual and semi-automatic annotation. In particular, we focus on object recognition and visual video indexing. We briefly review the current state of the art based on interest point extraction (e.g. Harris points, Maximally Stable Extremal Regions) and calculation of invariant descriptors around these points (e.g. SIFT, differential invariants). The main challenge for recognition from videos is the efficiency due to the huge size of the database. We will illustrate these concepts on the recently started project, TheoMedia (joint work between TU Graz, Joanneum Research and inst.tute for Fundamental Theology at KFU Graz) where we use recognition and indexing technology for analyzing films in order to find religious symbols. The goal of the project is to use all the available information retrieval technology to substantially speed up the analysis process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QSPR analysis of the partitioning of vaporous chemicals in a water-gas phase system and the water solubility of liquid and solid chemicals on the basis of fragment and physicochemical similarity and hybot descriptors

QSPR analysis of the partitioning of vaporous chemicals in a...

引用

作者： Raevsky, O. Andreeva, E. Raevskaja, O. Skvortsov, V. Schaper, K. Dept. of Comp.-Aided Molec. Design Inst. Physiologically Active Compds. Russian Academy of Sciences Severnii proezd 1 Chernogolovka Moscow Region 142432 Russia Lab. Molec. Graphics and Drug Des. Inst. Biomedicinal Chem. Russ. M. Pogodina Str. 10 Moscow 109018 Russia Division of Structural Biochemistry Research Center Borstel Leibniz Ctr. for Med. and Biosci. Parkallee 1-40 D-23845 Borstel Germany

QSPR analyses of the solubility in water of 558 vapors, 786 liquids and 2045 solid organic neutral chemicals and drugs are presented. Simultaneous consideration of H-bond acceptor and donor factors leads to a good description of the solubility of vapors and liquids. A volume-related term was found to have an essential negative contribution to the solubility of liquids. Consideration of polarizability, H-bond acceptor and donor factors and indicators for a few functional groups, as well as the experimental solubility values of structurally nearest neighbors yielded good correlations for liquids. The application of Yalkowsky's "General Solubility Equation" to 1063 solid chemicals and drugs resulted in a correlation of experimental vs calculated log S values with only modest statistical criteria. Two approaches to derive predictive models for solubility of solid chemicals and drugs were tested. The first approach was based on the QSPR for liquids together with indicator variables for different functional groups. Furthermore, a calculation of enthalpies for intermolecular comp.exes in crystal lattices, based on new H-bond potentials, was carried out for the better consideration of essential solubility-decreasing effects in the solid state, as comp.red with the liquid state. The second approach was based on a combination of similarity considerations and traditional QSPR. Both approaches lead to high quality predictions with average absolute errors on the level of experimental log S determination. © 2005 Taylor & Francis Ltd.

关键词： Solubility

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：