检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Bogensperger, Lea Narnhofer, Dominik Falk, Alexander Schindler, Konrad Pock, Thomas Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Photogrammetry and Remote Sensing ETH Zurich Zurich Switzerland Institute of Computer Graphics and Vision Graz University of Technology Austria Photogrammetry and Remote Sensing ETH Zurich Switzerland

Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation masks that are closely related to the respective structures. In this work we introduce FlowSDF, an image-guided conditional flow matching framework, designed to represent the signed distance function (SDF), and, in turn, to represent an implicit distribution of segmentation masks. The advantage of leveraging the SDF is a more natural distortion when compared to that of binary masks. Through the learning of a vector field associated with the probability path of conditional SDF distributions, our framework enables accurate sampling of segmentation masks and the computation of relevant statistical measures. This probabilistic approach also facilitates the generation of uncertainty maps represented by the variance, thereby supporting enhanced robustness in prediction and further analysis. We qualitatively and quantitatively illustrate competitive performance of the proposed method on a public nuclei and gland segmentation data set, highlighting its utility in medical image segmentation applications. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hotspot Prediction of Severe Traffic Accidents in the Federal District of Brazil

arXiv

引用

arXiv 2023年

作者： Lima, Vinicius Byrd, Vetria Computer Graphics Technology Criminalistics Institute Purdue University Federal District Civil Police West LafayetteIN United States Computer Graphics Technology Criminalistics Institute Purdue University Federal District Civil Police DF Brasilia Brazil Computer Graphics Technology Purdue University West LafayetteIN United States

Traffic accidents are one of the biggest challenges in a society where commuting is so important. What triggers an accident can be dependent on several subjective parameters and varies within each region, city, or country. In the same way, it is important to understand those parameters in order to provide a knowledge basis to support decisions regarding future cases prevention. The literature presents several works where machine learning algorithms are used for prediction of accidents or severity of accidents, in which city-level datasets were used as evaluation studies. This work attempts to add to the diversity of research, by focusing mainly on concentration of accidents and how machine learning can be used to predict hotspots. This approach demonstrated to be a useful technique for authorities to understand nuances of accident concentration behavior. For the first time, data from the Federal District of Brazil collected from forensic traffic accident analysts were used and combined with data from local weather conditions to predict hotspots of collisions. Out of the five algorithms we considered, two had good performance: Multi-layer Perceptron and Random Forest, with the latter being the best one at 98% accuracy. As a result, we identify that weather parameters are not as important as the accident location, demonstrating that local intervention is important to reduce the number of accidents. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Learned Discretization Schemes for the Second-Order Total Generalized Variation 9th

Learned Discretization Schemes for the Second-Order Total ...

引用

9th International Conference on Scale Space and Variational Methods in computer Vision, SSVM 2023

作者： Bogensperger, Lea Chambolle, Antonin Effland, Alexander Pock, Thomas Institute of Computer Graphics and Vision Graz University of Technology Graz Austria CEREMADE CNRS & Université Paris-Dauphine PSL Paris France Institute for Applied Mathematics University of Bonn Bonn Germany

ISBN: (纸本)9783031319747

The total generalized variation extends the total variation by incorporating higher-order smoothness. Thus, it can also suffer from similar discretization issues related to isotropy. Inspired by the success of novel discretization schemes of the total variation, there has been recent work to improve the second-order total generalized variation discretization, based on the same design idea. In this work, we propose to extend this to a general discretization scheme based on interpolation filters, for which we prove variational consistency. We then describe how to learn these interpolation filters to optimize the discretization for various imaging applications. We illustrate the performance of the method on a synthetic data set as well as for natural image denoising. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Optimizing Artificial Neural Networks Trough Weight Adjustments

引用

Procedia computer Science 2024年 246卷 2158-2165页

作者： Syed Muhammad Abrar Akber Agnieszka Szczesna Sadia Nishat Kazmi Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice 44-100 Poland Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice 44-100 Poland

Longer training times pose a significant challenge in Artificial neural networks (ANNs) as it may leads to increasing the computational costs and decreasing the effectiveness of the model. Therefore, it is imperative to reduce training times in ANNs to enhance the computational efficiency. The initialization of the weights between the layers in ANN plays a vital role in reducing training times. Appropriate weight initialization can help the network converge faster during the training by providing an optimum starting point for the network. Therefore, weight initialization techniques are essential for efficient training of ANNs. This paper revisits and implements different popular weight initialization techniques in ANNs and analyzes their impact on training time. Specifically, this paper implements Gaussian-based, Kaming-based, and Xavier-based weight initiation atop a popular DNN-based network. The experiments are conducted by employing a well-known dataset. The results show that the scenario when no weight initiation is applied consumed the highest training time, whereas different weight initiation techniques contribute in reducing the training times for the network.

关键词： Artificial neural network Deep neural network weight initiation

来源：评论

学校读者我要写书评

暂无评论

A Research Platform for Studying Mixed-Presence Collaboration

A Research Platform for Studying Mixed-Presence Collaboratio...

引用

IEEE International Symposium on Mixed and Augmented Reality Workshops (ISMARW)

作者： Wolfgang Büschel Katja Krug Marc Satkowski Stefan Gumhold Raimund Dachselt Interactive Media Lab Dresden TUD Dresden University of Technology Chair of Computer Graphics and Visualization TUD Dresden University of Technology

ISBN: (数字)9798331506919

ISBN: (纸本)9798331506926

In this paper, we present a research platform to support studying collaboration in hybrid and co-located scenarios. Mixed-presence collaboration includes various novel and exciting use cases, such as situated and immersive data analysis by multiple users. However, research in this emerging field is hindered by the technical complexity of the setups and often requires re-implementation of common features. We address this issue by contributing a toolkit and research platform for mixed-presence collaboration that serves as an extensible baseline implementation and enables fast prototyping for user studies in collaborative mixed reality. Furthermore, our platform provides adjustable parameters, such as types of avatars, audio source placement, or the amount of simulated network latency. This way, developers are supported in making design choices regarding typical, re-occurring technical challenges.

关键词： Three-dimensional displays Data analysis Avatars Spatial audio Decision making Collaboration Mixed reality Complexity theory Synchronization Augmented reality

来源：评论

学校读者我要写书评

暂无评论

InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization 43rd

InfoSeg: Unsupervised Semantic Image Segmentation with Mutua...

引用

43rd DAGM German Conference on Pattern Recognition, DAGM GCPR 2021

作者： Harb, Robert Knöbelreiter, Patrick Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

ISBN: (纸本)9783030926588

We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features. The core idea of our work is to leverage recent progress in self-supervised image representation learning. Representation learning methods compute a single high-level feature capturing an entire image. In contrast, we compute multiple high-level features, each capturing image segments of one particular semantic class. To this end, we propose a novel two-step learning procedure comprising a segmentation and a mutual information maximization step. In the first step, we segment images based on local and global features. In the second step, we maximize the mutual information between local features and high-level features of their respective class. For training, we provide solely unlabeled images and start from random network initialization. For quantitative and qualitative evaluation, we use established benchmarks, and COCO-Persons, whereby we introduce the latter in this paper as a challenging novel benchmark. InfoSeg significantly outperforms the current state-of-the-art, e.g., we achieve a relative increase of 26 % in the Pixel Accuracy metric on the COCO-Stuff dataset. © 2021, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Single Image LDR to HDR Conversion Using Conditional Diffusion

Single Image LDR to HDR Conversion Using Conditional Diffusi...

引用

IEEE International Conference on Image Processing

作者： Dwip Dalal Gautam Vashishtha Prajwal Singh Shanmuganathan Raman Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes, resulting in under-/overexposed images. This paper presents a deep learning-based approach for recovering intricate details from shadows and highlights while reconstructing High Dynamic Range (HDR) images. We formulate the problem as an image-to-image (I2I) translation task and propose a conditional Denoising Diffusion Probabilistic Model (DDPM) based framework using classifier-free guidance. We incorporate a deep CNN-based autoencoder in our proposed framework to enhance the quality of the latent representation of the input LDR image used for conditioning. Moreover, we introduce a new loss function for LDR-HDR translation tasks, termed Exposure Loss. This loss helps direct gradients in the opposite direction of the saturation, further improving the results’ quality. By conducting comprehensive quantitative and qualitative experiments, we have effectively demonstrated the proficiency of our proposed method. The results indicate that a simple conditional diffusion-based method can replace the complex camera pipeline-based architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of importance for condition attributes based on quality of decision reducts 26

Evaluation of importance for condition attributes based on q...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Stanczyk, Urszula Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A Gliwice44-100 Poland

Relative or decision reducts belong with mechanisms dedicated to feature selection, and they are embedded in rough set approach to data processing. Algorithms for reduct construction typically aim at dimensionality reduction aspect, searching for smallest reducts, which are considered as the most advantageous from the point of view of knowledge representation. However, classifiers build on reduced data models, based on reducts, can significantly vary in performance. Therefore, to ensure quality of predictions, other characteristics of reducts, apart from their cardinalities, need to be taken into account. The paper presents research in which estimation of reduct quality through their characteristics was reflected in calculation of the proposed weighting factors leading to attribute rankings. These rankings were next employed in the process of filtering decision rules, inferred by classic rough set approach. Constructed rule-based classifiers were applied in the stylometric domain to solve a task of authorship attribution. © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022)

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Towards Large-Scale Video-Based Highway Traffic Monitoring

Towards Large-Scale Video-Based Highway Traffic Monitoring

引用

International Conference on Intelligent Transportation

作者： Johannes Spoecklberger Jakub Micorek Horst Possegger Horst Bischof Faculty of Computer Science Institute of Computer Graphics and Vision (ICG) Graz University of Technology Graz Austria

Traffic safety on highways is supported by a variety of technical measures, including countless camera systems that are often only monitored by human operators. However, due to the sheer amount of data, safety monitoring and accident prevention are limited by human resources. In this paper, we present an efficient system capable of extracting accurate vehicle trajectories from the vast amount of video data generated by modern highway infrastructures. Our proposed system conveniently leverages bird's eye view transformations estimated from aerial data or street marker geometry to generate geo-localized trajectories. Utilizing existing infrastructure, we demonstrate that the central data for video-based highway traffic monitoring can be reliably extracted. Remarkably, this can be achieved solely relying on uncalibrated cameras and noisy video streams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single Image LDR to HDR Conversion using Conditional Diffusion

arXiv

引用

arXiv 2023年

作者： Dalal, Dwip Vashishtha, Gautam Singh, Prajwal Raman, Shanmuganathan Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gandhinagar India

关键词： Cameras

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：