检索结果-内蒙古大学图书馆

15th International Conference on System Theory, Control and Computing, ICSTCC 2011

作者： Smochina, Cristian Manta, Vasile Kropatsch, Walter Department of Computer Science and Engineering Gheorghe Asachi Technical University of Iasi Romania Pattern Recognition and Image Processing Group Institute of Computer Graphics and Algorithms Vienna University of Technology Austria

ISBN: (纸本)9781457711732

The objective of semantic segmentation in microscopic images is to extract the cellular, nuclear or tissue components. This problem is challenging due to the large variations of these components features (size, shape, orientation or texture). In this paper we improve the technique presented in [17] used to identify the epithelial nuclei (crypt) against interstitial nuclei in microscopic images taken from colon tissues. In the proposed enhanced approach, the crypt inner boundary is detected using the closing morphological pyramid instead of morphological hierarchy. The outer crypt border is determined by the epithelial nuclei, overlapped by the maximal isoline of the inner boundary. The use of sampling in building the pyramid offers computational efficiency, reduces the amount of used memory, increase the robustness and preserve the quality results. An analysis of the two approaches is performed considering the number of pixels processed to create each level. Also the relation between the levels of the hierarchical structures is established. © 2011 Faculty of Auto Control.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Variable Neighborhood Search for a prize collecting capacity constrained connected facility location problem

Variable Neighborhood Search for a prize collecting capacity...

引用

2008 International Symposium on Applications and the Internet, SAINT 2008

作者： Leitnef, Markus Raidl, Günther R. Carinthia University of Applied Sciences School of Telematics Network Engineering Klagenfurt Austria Vienna University of Technology Institute of Computer Graphics and Algorithms Vienna Austria

ISBN: (纸本)9780769532974

We present a Variable Neighborhood Search approach for a network design problem occurring in real world when the bandwidth of an existing network shall be enhanced. Using two different neighborhood structures we show that a carefully designed combination of a metaheuristic and an exact method based on integer linear programming is able to improve solution quality compared to using heuristic methods only. © 2008 IEEE.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Comparing different teaching models in a first year computer aided design course

Comparing different teaching models in a first year computer...

引用

2005 ASEE Annual Conference and Exposition: The Changing Landscape of engineering and Technology Education in a Global World

作者： Baxter, Douglas H. Mandigo, Andrew CAD/CAM/CAE United States Engineering Graphics and Computer Aided Design Course School of Engineering Rensselaer Polytechnic Institute United States CAD/CAM/CAE School of Engineering Rensselaer Polytechnic Institute United States

The comparison of different teaching models in a first year CAD course is presented. The course, engineering graphics and computer Aided Design (EG&CAD) teaches the skills of using a solid modeling system to create parts, small assemblies, and documentation. EG&CAD is taught with a series of twelve one hour lectures over a fourteen week semester. The new model of using assembly for the entire semester is proving successful. Moreover, quizzes will no longer be drawn from the final project instead, from other sources.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking 32

DRT: Detection Refinement for Multiple Object Tracking

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Focal region-based volume rendering

Focal region-based volume rendering

引用

作者： Zhou, Jianlong Wang, Zhiyan Tönnies, Klaus D. School of Computer Science and Engineering South China University of Technology Guangzhou 510640 China Institute for Simulation and Graphics University of Magdeburg D-39106 Magdeburg Germany

In this paper, a new approach named focal region-based volume rendering for visualizing internal structures of volumetric data is presented. This approach presents volumetric information through integrating context information as the structure analysis of the data set with a lens-like focal region rendering to show more detailed information. This feature-based approach contains three main components: (i) A feature extraction model using 3D image processing techniques to explore the structure of objects to provide contextual information;(ii) An efficient ray-bounded volume ray casting rendering to provide the detailed information of the volume of interest in the focal region;(iii) The tools used to manipulate focal regions to make this approach more flexible. The approach provides a powerful framework for producing detailed information from volumetric data. Providing contextual information and focal region renditions at the same time has the advantages of easy to understand and comprehend volume information for the scientist. The interaction techniques provided in this approach make the focal region-based volume rendering more flexible and easy to use. © World Scientific Publishing Company.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the thermal processes and simulation methods for additive manufacturing based on the geometry voxel representation

引用

Key engineering Materials 2018年第1期771卷 91-96页

作者： Ripetskiy, Andrey Zelenov, Sergey Kuznetsova, Ekaterina Rabinskiy, Lev Department of Engineering and Computer Graphics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Department of Engineering Graphics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Faculty of Applied Mechanics Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia Department of Advanced Materials and Technologies for Aerospace Application Moscow Aviation Institute National Research University 4 Volokolamskoe highway Moscow125993 Russia

Currently, the technological and hardware base additive production technologies are actively developing. The emergence of new developments in the field of materials science and their possibilities for the creation of products using layer-by-layer method promotes the development of innovative solutions that increase the efficiency of complex technical parts and improves their quality. This paper describes simulation methods based on the Model Voxel Representation part discretization allowing evaluating thermal processes during 3D printing process. The simulation model was extended taking into consideration the following criteria: heat conduction coefficient as a constant;temperature in the center of the elementary volume equals to the temperature at the volume border;temperature of the powder surrounding the item taken as a constant. It was determined that the convergence is affected by numerous factors: temperature in the machine chamber, material properties, heat exchange and the processes running into the chamber of the certain machines. © 2018 Trans Tech Publications, Switzerland.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Ecological adaptive cruise control for Urban environments using SPaT information 17

Ecological adaptive cruise control for Urban environments us...

引用

17th IEEE Vehicle Power and Propulsion Conference, VPPC 2020

作者： Chada, Sai Krishna Purbai, Ankith Gorges, Daniel Ebert, Achim Teutsch, Roman University of Kaiserslautern Electromobility Research Group Germany Computer Graphics and HCI Group University of Kaiserslautern Germany Institute for Mechanical and Automotive Engineering University of Kaiserslautern Germany

ISBN: (纸本)9781728189598

This paper proposes an ecological adaptive cruise control (EACC) strategy to minimize the energy consumption of an electric vehicle using two linear model predictive controllers (MPCs). In the absence of a preceding vehicle, the first MPC uses the upcoming traffic light signal phase and timing (SPaT) information to track an optimal green-wave velocity to reach the next traffic light signal during green phase. For the preceding vehicle in range scenario, the second MPC follows the leading vehicle by maintaining a desired inter-vehicle distance and strictly adheres to road speed limits. If the upcoming traffic light signal phase is changing to red, the controller uses the SPaT information to plan an energy-efficient stop near the traffic light signal. To evaluate the performance of the proposed strategy, both controllers are tested in a realistic scenario against a baseline controller and furthermore their energy saving benefits are explored. Finally, investigations on computation time reveal that the proposed strategy is capable for online implementation. © 2020 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Improving the visualization of electron-microscopy data through optical flow interpolation

Improving the visualization of electron-microscopy data thro...

引用

27th Spring Conference on computer graphics, SCCG 2011

作者： Carata, Lucian Shao, Dan Hadwiger, Markus Groeller, Eduard Faculty of Automatic Control and Computer Engineering Gh. Asachi Technical University of Iasi Romania Institute of Computer Graphics and Algorithms Vienna University of Technology Austria Division of Mathematical and Computer Sciences and Engineering King Abdullah University of Science and Technology Saudi Arabia

ISBN: (纸本)9781450319782

Technical developments in neurobiology have reached a point where the acquisition of high resolution images representing individual neurons and synapses becomes possible. For this, the brain tissue samples are sliced using a diamond knife and imaged with electron-microscopy (EM). However, the technique achieves a low resolution in the cutting direction, due to limitations of the mechanical process, making a direct visualization of a dataset difficult. We aim to increase the depth resolution of the volume by adding new image slices interpolated from the existing ones, without requiring modifications to the EM image-capturing method. As classical interpolation methods do not provide satisfactory results on this type of data, the current paper proposes a re-framing of the problem in terms of motion volumes, considering the depth axis as a temporal axis. An optical flow method is adapted to estimate the motion vectors of pixels in the EM images, and this information is used to compute and insert multiple new images at certain depths in the volume. We evaluate the visualization results in comparison with interpolation methods currently used on EM data, transforming the highly anisotropic original dataset into a dataset with a larger depth resolution. The interpolation based on optical flow better reveals neurite structures with realistic undistorted shapes, and helps to easier map neuronal connections. © 2011 ACM.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Research on the effect of visual conventions on perception and inference 6th

Research on the effect of visual conventions on perception a...

引用

6th International Conference on Design, User Experience, and Usability, DUXU 2017, held as part of the 19th International Conference on Human-computer Interaction, HCI 2017

作者： Peng, Ningyue Xue, Chengqi Wang, Haiyan Niu, Yafeng Chen, Yingjie Victor School of Mechanical Engineering Southeast University Nanjing China Institute of Product Design and Reliability Engineering Southeast University Nanjing China Department of Computer Graphics Technology in Purdue Polytechnic Institute Purdue University IN United States

ISBN: (纸本)9783319586335

Visual conventions are perceptually efficient graphic agreements with common-sense like referents and are commonly used in what we interact with in daily life. It becomes a studying-worthy issue on whether such conventions can enhance performances and reduce cognitive load when we perceive and reason about new knowledge. Furthermore, whether the visual conventions can affect experts, who have prior knowledge and design experience about different visual encoding principles the same degree as novice who have no background knowledge in this area, is another research focus in this study. Our research is carried out according to action features when we read visualizations. Four task features are extracted, based on which behavioral and eye-tracking measurement were conducted, that is data localization, simple and complex data comparison, and knowledge inference. Both expert and novice participants were enrolled in our experiment. The result indicates that conventional elements in visualizations can hugely improve performances in more complex tasks involving higher-level cognition, like making comparisons and reasoning about new knowledge. The performance improvement can be seen from shorter response time on achieving conclusions and higher accuracy rates. Meanwhile, cognitive load, which can be measured from shorter total fixation duration and fewer fixation counts in AOIs, is reduced through applying visually conventional features. No statistically significant difference is found in comparing perceptual and inferential outputs of expert and novice group. We draw conclusions that visual conventions in visualizations can better performance in relatively complex activities, and it can be equally perceived and acquired regardless of the user’s knowledge background is. What we conclude in this study can be extended to areas of dynamic data visualization and layout design in the digital interface domain. © Springer International Publishing AG 2017.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Robust active appearance model matching

Robust active appearance model matching

引用

19th International Conference on Information Processing in Medical Imaging, IPMI 2005

作者： Beichel, Reinhard Bischof, Horst Leberl, Franz Sonka, Milan Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/2 A-8010 Graz Austria Department of Electrical and Computer Engineering University of Iowa Iowa City IA 52242 United States

A novel robust active appearance model (AAM) matching algorithm is presented. The method consists of two main stages. First, initial residuals are clustered by a non parametric mean shift mode detection step. Second, modes without gross outliers are selected using an objective function. Robustness of the matching procedure is demonstrated on a variety of examples with different noise conditions. The proposed algorithm outperformed the conventional AAM matching on images with gross disturbances and can tolerate up to 40% of disturbed data. © Springer Verlag Berlin Heidelberg 2005.

关键词： Algorithms

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：