检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Basirat, Mina Roth, Peter M. Institute of Computer Graphics and Vision Graz University of Technology

Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build on the same architectural decisions. This also applies to the selection of activation functions (AFs), where most approaches build on Rectified Linear Units (ReLUs). In this paper, however, we show that the choice of a proper AF has a significant impact on the classification accuracy, in particular, if fine, subtle details are of relevance. Therefore, we propose to model the degree of absence and the presence of features via the AF by using piece-wise linear functions, which we refer to as L*ReLU. In this way, we can ensure the required properties, while still inheriting the benefits in terms of computational efficiency from ReLUs. We demonstrate our approach for the task of Fine-grained Visual Categorization (FGVC), running experiments on seven different benchmark datasets. The results do not only demonstrate superior results but also that for different tasks, having different characteristics, different AFs are selected. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FuseSeg: LiDAR point cloud segmentation fusing multi-modal data

arXiv

引用

arXiv 2019年

作者： Krispel, Georg Opitz, Michael Waltner, Georg Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology

We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds. Utilizing the dense native range representation of a LiDAR sensor and the setup calibration, we establish point correspondences between the two input modalities. Subsequently, we are able to warp and fuse the features from one domain into the other. Therefore, we can jointly exploit information from both data sources within one single network. To show the merit of our method, we extend SqueezeSeg, a point cloud segmentation network, with an RGB feature branch and fuse it into the original structure. Our extension called FuseSeg leads to an improvement of up to 18% IoU on the KITTI benchmark. In addition to the improved accuracy, we also achieve real-time performance at 50 fps, five times as fast as the KITTI LiDAR data recording speed. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Learned Collaborative Stereo Refinement

arXiv

引用

arXiv 2019年

作者： Pock, Thomas Knöbelreiter, Patrick Institute for Computer Graphics and Vision Graz University of Technology

In this work, we propose a learning-based method to denoise and refine disparity maps of a given stereo method. The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energy defined in a joint disparity, color, and confidence image space. Our method allows to learn a robust collaborative regularizer leveraging the joint statistics of the color image, the confidence map and the disparity map. Due to the variational structure of our method, the individual steps can be easily visualized, thus enabling interpretability of the method. We can therefore provide interesting insights into how our method refines and denoises disparity maps. The efficiency of our method is demonstrated by the publicly available stereo benchmarks Middlebury 2014 and Kitti 2015. Copyright © 2019, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a Cloud Computing System using Queuing Model with Correlated Task Reneging 5

Performance Analysis of a Cloud Computing System using Queui...

引用

5th International Scientific Conference on Information, Control, and Communication Technologies, ICCT 2021

作者： Kumar, Rakesh Soodan, Bhavneet Singh Kuaban, Godlove Suila Czekalski, Piotr Sharma, Sapana School of Mathematics Shri Mata Vaishno Devi University Jammu and Kashmir Katra182320 India Department of Mathematics and Statistics Namibia University of Science and Technology Private Bag 13388 Windhoek Namibia 13 Jackson Kaujeua Street Windhoek Namibia Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44 - 100 Poland Department of Computer Graphics. Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Poland Department of Mathematics Cluster University of Jammu Jammu and Kashmir India

Queuing theory has been extensively used in the modelling and performance analysis of cloud computing systems. The phenomenon of the task (or request) reneging, that is, the dropping of requests from the request queue often occur in cloud computing systems, and it is important to consider it when developing performance evaluations models for cloud computing infrastructures. Majority of studies in the performance evaluation of cloud computing data centres with the use of queuing theory do not consider the fact that the tasks could be removed from queue without being serviced. The removal of tasks from the queue could be due to the user impatience, execution deadline expiration, security reasons, or as an active queue management strategy. The reneging could be correlated in nature, that is, if a request is dropped (or reneged) at any time epoch, and then there is a probability that a request may or may not be dropped at the next time epoch. This kind of dropping (or reneging) of requests is referred to as correlated request reneging. In this paper we have modelled a cloud computing infrastructure with correlated request reneging using queuing theory. An M/M/1/N queuing model with correlated reneging has been used to study the performance analysis of the load balancing server of a cloud computing system. The steady-state as well as the transient performance analyses have been carried out. Important measures of performance like a vera ge queue size, average delay, probability of task blocking, and the probability of no waiting in the queue are studied. Finally, some comparisons are performed which describe the effect of correlated task reneging over simple exponential reneging. © 2021 institute of Physics Publishing. All rights reserved.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Total Variation-Based Image Decomposition and Denoising for Microscopy Images

arXiv

引用

arXiv 2025年

作者： Corrias, Marco Franceschi, Giada Riva, Michele Tampieri, Alberto Föttinger, Karin Diebold, Ulrike Pock, Thomas Franchini, Cesare Faculty of Physics Center for Computational Materials Science University of Vienna Austria Vienna Doctoral School in Physics University of Vienna Austria Institute of Applied Physics TU Wien Austria Institute of Materials Chemistry TU Wien Austria Institute of Computer Graphics and Vision TU Graz Austria Department of Physics and Astronomy University of Bologna Italy

Experimentally acquired microscopy images are unavoidably affected by the presence of noise and other unwanted signals, which degrade their quality and might hide relevant features. With the recent increase in image acquisition rate, modern denoising and restoration solutions become necessary. This study focuses on image decomposition and denoising of microscopy images through a workflow based on total variation (TV), addressing images obtained from various microscopy techniques, including atomic force microscopy (AFM), scanning tunneling microscopy (STM), and scanning electron microscopy (SEM). Our approach consists in restoring an image by extracting its unwanted signal components and subtracting them from the raw one, or by denoising it. We evaluate the performance of TV-L1, Huber-ROF, and TGV-L1 in achieving this goal in distinct study cases. Huber-ROF proved to be the most flexible one, while TGV-L1 is the most suitable for denoising. Our results suggest a wider applicability of this method in microscopy, restricted not only to STM, AFM, and SEM images. The Python code used for this study is publicly available as part of AiSurf. It is designed to be integrated into experimental workflows for image acquisition or can be used to denoise previously acquired images. © 2025, CC BY.

关键词： Atomic force microscopy

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adaptive Filter for Head Tracking in Augmented Reality (AR)-based Flight Simulators

引用

IEEE Transactions on computers 2025年

作者： Nwobodo, Onyeka J. Kuaban, Godlove Suila Nkemeni, Valery Wereszczynski, Kamil Cyran, Krzysztof A. Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Polish Academy of Sciences Institute of Theoretical and Applied Informatics Poland University of Buea Laboratory of Electrical Engineering and Computing Faculty of Engineering and Technology Buea Cameroon

This paper presents a novel approach for head tracking in augmented reality (AR) flight simulators using an adaptive fusion of Kalman and particle filters. This fusion dynamically balances the strengths of both algorithms, leveraging Kalman filters for computational efficiency and particle filters for handling non-linearities based on real-time factors such as sensor noise and head movement patterns. Our method demonstrates superior tracking precision and reduced latency, making it particularly effective for immersive pilot training in AR-based flight simulations. While focused on flight simulation, our approach holds high potential for broader applications in other AR and virtual reality (VR) environments where precise, real-time head tracking is crucial. These results provide actionable design guidance for developers optimizing tracking systems in environments that require fast response times and high accuracy. Future extensions of this research could explore the generalization of our approach across diverse AR applications, including human-computer interaction (HCI), medical simulations, and gaming. © 1968-2012 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

HOnnotate: A Method for 3D Annotation of Hand and Object Poses

HOnnotate: A Method for 3D Annotation of Hand and Object Pos...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Shreyas Hampali Mahdi Rad Markus Oberweger Vincent Lepetit Institute for Computer Graphics and Vision Graz University of Technology Austria LIGM Ecole des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images for this problem, as estimating the 3D poses is challenging, mostly because of the mutual occlusions between the hand and the object. To tackle this challenge, we capture sequences with one or several RGB-D cameras and jointly optimize the 3D hand and object poses over all the frames simultaneously. This method allows us to automatically annotate each frame with accurate estimates of the poses, despite large mutual occlusions. With this method, we created HO-3D, the first markerless dataset of color images with 3D annotations for both the hand and object. This dataset is currently made of 77,558 frames, 68 sequences, 10 persons, and 10 objects. Using our dataset, we develop a single RGB image-based method to predict the hand pose when interacting with objects under severe occlusions and show it generalizes to objects not seen in the dataset.

关键词： Three-dimensional displays Pose estimation Solid modeling Cameras Sensors Training Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Sketch-aided retrieval of incomplete 3D cultural heritage objects 12

Sketch-aided retrieval of incomplete 3D cultural heritage ob...

引用

12th Eurographics Workshop on 3D Object Retrieval, 3DOR 2019, in conjunction with the 40th Annual Conference of the European Association for computer graphics, EG 2019

作者： Lengauer, S. Komar, A. Labrada, A. Karl, S. Trinkl, E. Preiner, R. Bustos, B. Schreck, T. Institute of Computer Graphics and Knowledge Visualisation Graz University of Technology Austria Institute of Archaeology University of Graz Austria Millenium Institute for Foundational Research on Data Department of Computer Science University of Chile Chile

ISBN: (纸本)9783038680772

Due to advances in digitization technology, documentation efforts and digital library systems, increasingly large collections of visual Cultural Heritage (CH) object data becomes available, offering rich opportunities for domain analysis, e.g., for comparing, tracing and studying objects created over time. In principle, existing shape- and image-based similarity search methods can aid such domain analysis tasks. However, in practice, visual object data are given in different modalities, including 2D, 3D, sketches or conventional drawings like profile sections or unwrappings. In addition, collections may be distributed across different publications and repositories, posing a challenge for implementing encompassing search and analysis systems. We introduce a methodology and system for cross-modal visual search in CH object data. Specifically, we propose a new query modality based on 3D views enhanced by user sketches (3D+sketch). This allows for adding new context to the search, which is useful e.g., for searching based on incomplete query objects, or for testing hypotheses on existence of certain shapes in a collection. We present an appropriately designed workflow for constructing query views from incomplete 3D objects enhanced by a user sketch based on shape completion and texture inpainting. Visual cues additionally help users compare retrieved objects with the query. We apply our method on a set of relevant 3D and view-based CH object data, demonstrating the feasibility of our approach and its potential to support analysis of domain experts in Archaeology and the field of CH in general. © 2019 The Author(s)

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Motif-Driven retrieval of greek painted pottery

Motif-Driven retrieval of greek painted pottery

引用

2019 Eurographics Workshop on graphics and Cultural Heritage, GCH 2019

ISBN: (纸本)9783038680826

The analysis of painted pottery is instrumental for understanding ancient Greek society and human behavior of past cultures in Archaeology. A key part of this analysis is the discovery of cross references to establish links and correspondences. However, due to the vast amount of documented images and 3D scans of pottery objects in today's domain repositories, manual search is very time consuming. computer aided retrieval methods are of increasing importance. Mostly, current retrieval systems for this kind of cultural heritage data only allow to search for pottery of similar vessel's shape. However, in many cases important similarity cues are given by motifs painted on these vessels. We present an interactive retrieval system that makes use of this information to allow for a motif-driven search in cultural heritage repositories. We address the problem of unsupervised motif extraction for preprocessing and the shape-based similarity search for Greek painted pottery. Our experimental evaluation on relevant repository data demonstrates effectiveness of our approach on examples of different motifs of interests. © 2019 Eurographics Association.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Minimal Solutions for Relative Pose With a Single Affine Correspondence

Minimal Solutions for Relative Pose With a Single Affine Cor...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Banglei Guan Ji Zhao Zhang Li Fang Sun Friedrich Fraundorfer College of Aerospace Science and Engineering National University of Defense Technology China National University of Defense Technology Changsha China Institute for Computer Graphics and Vision Graz University of Technology Austria Remote Sensing Technology Institute German Aerospace Center Germany

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

In this paper we present four cases of minimal solutions for two-view relative pose estimation by exploiting the affine transformation between feature points and we demonstrate efficient solvers for these cases. It is shown, that under the planar motion assumption or with knowledge of a vertical direction, a single affine correspondence is sufficient to recover the relative camera pose. The four cases considered are two-view planar relative motion for calibrated cameras as a closed-form and a least-squares solution, a closed-form solution for unknown focal length and the case of a known vertical direction. These algorithms can be used efficiently for outlier detection within a RANSAC loop and for initial motion estimation. All the methods are evaluated on both synthetic data and real-world datasets from the KITTI benchmark. The experimental results demonstrate that our methods outperform comparable state-of-the-art methods in accuracy with the benefit of a reduced number of needed RANSAC iterations.

关键词： Cameras Pose estimation Transmission line matrix methods Robot vision systems Simultaneous localization and mapping Motion estimation

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：