检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Eberle, Andreas Computer Vision for Human-Computer Interaction Research Group Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology

Person re-identification (re-id) is the task of recognizing and matching persons at different locations recorded by cameras with non-overlapping views. One of the main challenges of re-id is the large variance in person poses and camera angles since neither of them can be influenced by the re-id system. In this work, an effective approach to integrate coarse camera view information as well as fine-grained pose information into a convolutional neural network (CNN) model for learning discriminative re-id embeddings is introduced. In most recent work pose information is either explicitly modeled within the re-id system or explicitly used for pre-processing, for example by pose-normalizing person images. In contrast, the proposed approach shows that a direct use of camera view as well as the detected body joint locations into a standard CNN can be used to significantly improve the robustness of learned re-id embeddings. On four challenging surveillance and video re-id datasets significant improvements over the current state of the art have been achieved. Furthermore, a novel reordering of the MARS dataset, called X-MARS is introduced to allow cross-validation of models trained for single-image re-id on tracklet data. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

SOS: Segment Object System for Open-World Instance Segmentation With Object Priors

arXiv

引用

arXiv 2024年

作者： Wilms, Christian Rolff, Tim Hillemann, Maris Johanson, Robert Frintrop, Simone Computer Vision Group University of Hamburg Germany Human-Computer Interaction Group University of Hamburg Germany

We propose an approach for Open-World Instance Segmentation (OWIS), a task that aims to segment arbitrary unknown objects in images by generalizing from a limited set of annotated object classes during training. Our Segment Object System (SOS) explicitly addresses the generalization ability and the low precision of state-of-the-art systems, which often generate background detections. To this end, we generate high-quality pseudo annotations based on the foundation model SAM [27]. We thoroughly study various object priors to generate prompts for SAM, explicitly focusing the foundation model on objects. The strongest object priors were obtained by self-attention maps from self-supervised vision Transformers, which we utilize for prompting SAM. Finally, the post-processed segments from SAM are used as pseudo annotations to train a standard instance segmentation system. Our approach shows strong generalization capabilities on COCO, LVIS, and ADE20k datasets and improves on the precision by up to 81.6% compared to the state-of-the-art. Source code is available at: https: //***/chwilms/SOS Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

KINECT UNBIASED

KINECT UNBIASED

引用

IEEE International Conference on Image Processing

作者： Manuel Martinez Rainer Stiefelhagen Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics (IAR) Computer Vision for Human-Computer Interaction Lab

ISBN: (纸本)9781479957521

Since its release, Kinect has been the de facto standard for low-cost RGB-D sensors. An infrared laser ray shot through an holographic diffraction grating projects a fixed dot pattern which is captured using an infrared camera. The pseudo-random pattern ensures that a simple block matching algorithm suffices to provide reliable depth estimates, allowing a cost-effective implementation. In this paper, we analyze the software limitations of Kinect's method, which allows us to propose algorithms that provide better precision. First, we analyze the dot pattern: we measure its pincushion distortion and its effect on the dot density, which is smaller towards the edges of the image. Then, we analyze the behavior of Block Matching algorithms, we show how Kinect's Block Matching implementation is;in general;limited by the dot density of the pattern, and a significant spatial bias is introduced as a result. We propose an efficient approach to estimate the disparity of each dot, allowing us to produce a point cloud with better spatial resolution than Block Matching algorithms.

关键词： Kinect RGB-D Pattern Bias

来源：评论

学校读者我要写书评

暂无评论

Trans4Trans: Efficient transformer for transparent object and semantic scene segmentation in real-world navigation assistance

arXiv

引用

arXiv 2021年

作者： Zhang, Jiaming Yang, Kailun Constantinescu, Angela Peng, Kunyu Müller, Karin Stiefelhagen, Rainer Computer Vision for Human-Computer Interaction Lab Center for Digital Accessibility and Assistive Technology Karlsruhe Institute of Technology Germany

Transparent objects, such as glass walls and doors, constitute architectural obstacles hindering the mobility of people with low vision or blindness. For instance, the open space behind glass doors is inaccessible, unless it is correctly perceived and interacted with. However, traditional assistive technologies rarely cover the segmentation of these safety-critical transparent objects. In this paper, we build a wearable system with a novel dualhead Transformer for Transparency (Trans4Trans) perception model, which can segment general- and transparent objects. The two dense segmentation results are further combined with depth information in the system to help users navigate safely and assist them to negotiate transparent *** propose a lightweight Transformer Parsing Module (TPM) to perform multi-scale feature interpretation in the transformer-based decoder. Benefiting from TPM, the double decoders can perform joint learning from corresponding datasets to pursue robustness, meanwhile maintain efficiency on a portable GPU, with negligible calculation increase. The entire Trans4Trans model is constructed in a symmetrical encoder-decoder architecture, which outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets, obtaining mIoU of 45:13% and 75:14%, respectively. Through a user study and various pre-tests conducted in indoor and outdoor scenes, the usability and reliability of our assistive system have been extensively verified. Meanwhile, the Tran4Trans model has outstanding performances on driving scene datasets. On Cityscapes, ACDC, and DADA-seg datasets corresponding to common environments, adverse weather, and traffic accident scenarios, mIoU scores of 81:5%, 76:3%, and 39:2% are obtained, demonstrating its high efficiency and robustness for real-world transportation applications. Copyright © 2021, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Improving marker-based tracking for augmented reality in underwater environments

Improving marker-based tracking for augmented reality in und...

引用

2018 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2018

作者： Cejka, Jan Marek, U. Agrafiotis, Panagiotis Skarlatos, Dimitrios Bruno, Fabio Liarokapis, Fotis Human Computer Interaction Laboratory Faculty of Informatics Masaryk University Czech Republic Photogrammetric Vision Laboratory Department of Civil Engineering and Geomatics Cyprus University of Technology Cyprus Cyprus Research S.r.l. - University of Calabria Italy

ISBN: (纸本)9783038680574

Underwater sites are a challenging environment for augmented reality. Images taken under water are degraded in several ways, most importantly they are affected by unbalanced colors due to uneven absorption of light in each color channel, blurring and desaturation caused by turbidity, or noise due to the presence of larger organisms, plants, or bubbles. In this paper, we introduce a new method based on white balancing that enhances underwater images to improve the results of detection of markers. We compare this method with several image enhancement methods, and evaluate their performance when applied to the problem of detecting markers under water. Our results show that our method improves the detection in underwater environments while keeping the computation time low. © 2018 GCH 2018 - Eurographics Workshop on Graphics and Cultural Heritage. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

RealityGit: Cross Reality Version Control of R&D Optical Workbench

RealityGit: Cross Reality Version Control of R&D Optical Wor...

引用

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

作者： Ke Li Tim Rolff Reinhard Bacher Frank Steinicke Deutsches Elektronen-Synchrotron DESY Germany Department of Informatics Human-Computer Interaction Universität Hamburg Department of Informatics Computer Vision Universität Hamburg

Multi-user collaboration at research and development (R&D) workbenches in advanced optics laboratories involves updating and documenting the status of hundreds of components. Although there are abundant mixed reality (MR) systems to support the collaboration of spatially co-located users, limited methods are available to facilitate cooperation in the spatial-temporal domain. Inspired by the version control workflow used in software development, we propose RealityGit, a novel cross-reality (CR) system design that leverages the recent advancements of neural radiance fields (NeRF). We illustrate how the NeRF model can be used to channel users with different extended reality (XR) experiences by providing an accurate immersive visual documentation of the historical states of a complex R&D workbench. We demonstrate the feasibility of such a system through an implementation where users could contribute to the version control workflows by integrating historical NeRF scans into their MR devices or providing status reviews by annotating or editing a NeRF model in virtual reality (VR).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bringing Instant Neural Graphics Primitives to Immersive Virtual Reality

Bringing Instant Neural Graphics Primitives to Immersive Vir...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Ke Li Tim Rolff Susanne Schmidt Reinhard Bacher Simone Frintrop Wim Leemans Frank Steinicke Department of Informatics Human-Computer Interaction Group Universität Hamburg Deutsches Elektronen-Synchrotron DESY Germany Department of Informatics Computer Vision Group Universität Hamburg

Neural radiance field (NeRF), in particular, its extension by instant neural graphics primitives is a novel rendering method for view synthesis that uses real-world images to build photo-realistic immersive virtual scenes. Despite its enormous potential for virtual reality (VR) applications, there is currently little robust integration of NeRF into typical VR systems available for research and benchmarking in the VR community. In this poster paper, we present an extension to instant neural graphics primitives and bring stereoscopic, high-resolution, low-latency, 6-DoF NeRF rendering to the Unity game engine for immersive VR applications. 1 1 Link to the repository: https://***/uhhhci/immersive-ngp

关键词： Three-dimensional displays Stereo image processing Conferences Virtual reality Games User interfaces Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Independent component analysis in a facial local residue space

Independent component analysis in a facial local residue spa...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Tae-Kyun Kim Hyunwoo Kim Wonjun Hwang Seok-Cheol Kee J. Kittler Centre for Vision Speech and Signal Processing University of Surrey UK Human Computer Interaction Laboratory Samsung Advanced Institute of Technology South Korea

In this paper, we propose an ICA (Independent Component Analysis) based face recognition algorithm, which is robust to illumination and pose variation. Generally, it is well known that the first few eigenfaces represent illumination variation rather than identity. Most PCA (Principal Component Analysis)-based methods have overcome illumination variation by discarding the projection to a few leading eigenfaces. The space spanned after removing a few leading eigenfaces is called the "residual face space". We found that ICA in the residual face space provides more efficient encoding in terms of redundancy reduction and robustness to pose variation as well as illumination variation, owing to its ability to represent non-Gaussian statistics. Moreover, a face image is separated into several facial components, local spaces, and each local space is represented by the ICA bases (independent components) of its corresponding residual space. The statistical models of face images in local spaces are relatively simple and facilitate classification by a linear encoding. Various experimental results show that the accuracy of face recognition is significantly improved by the proposed method under large illumination and pose variations.

关键词： Independent component analysis Principal component analysis Face recognition Lighting Statistics Image databases Face detection Space technology Speech analysis Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Immersive Neural Graphics Primitives

arXiv

引用

arXiv 2022年

作者： Li, Ke Rolff, Tim Schmidt, Susanne Bacher, Reinhard Frintrop, Simone Leemans, Wim Steinicke, Frank Human-Computer Interaction Group Department of Informatics Universität Hamburg Germany Computer Vision Group Department of Informatics Universität Hamburg Germany Deutsches Elektronen-Synchrotron DESY Germany

Neural radiance field (NeRF), in particular its extension by instant neural graphics primitives, is a novel rendering method for view synthesis that uses real-world images to build photo-realistic immersive virtual scenes. Despite its potential, research on the combination of NeRF and virtual reality (VR) remains sparse. Currently, there is no integration into typical VR systems available, and the performance and suitability of NeRF implementations for VR have not been evaluated, for instance, for different scene complexities or screen resolutions. In this paper, we present and evaluate a NeRF-based framework that is capable of rendering scenes in immersive VR allowing users to freely move their heads to explore complex real-world scenes. We evaluate our framework by benchmarking three different NeRF scenes concerning their rendering performance at different scene complexities and resolutions. Utilizing super-resolution, our approach can yield a frame rate of 30 frames per second with a resolution of 1280×720 pixels per eye. We discuss potential applications of our framework and provide an open source implementation online.1 Copyright © 2022, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

From Lenses to Living Rooms: A Policy Brief on Eye Tracking in XR Before the Impending Boom 6

From Lenses to Living Rooms: A Policy Brief on Eye Tracking ...

引用

6th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024

作者： Byrne, Sean Anthony Castner, Nora Bozkir, Efe Niehorster, Diederick C. Kasneci, Enkelejda Imt School for Advanced Studies Lucca MoMiLab Lucca Italy Carl Zeiss Vision International GmbH Tübingen Germany Technical University of Munich Human-Centered Technologies for Learning Munich Germany University of Tübingen Human-Computer Interaction Tübingen Germany Lund University Humanities Lab & Lund University Dept. of Psychology Lund Sweden

ISBN: (纸本)9798350372021

As tech giants such as Apple and Meta invest heavily in Virtual and Augmented Reality (VR/AR) technologies, often collectively termed Extended Reality (XR) devices, a significant societal concern emerges: The use of eye-tracking technology within these devices. Gaze data holds immense value, revealing insights into user attention, health, and cognitive states. This raises substantial concerns over privacy and fairness, with potential risks of targeted ads, unauthorized surveillance, and data re-purposing. As the impact of eye tracking is due to transition from the lab to the broader public, this paper underscores these pivotal issues in a digestible manner to the general audience. To this end, we first outline the eye-tracking data collection process and its potential for user insights. Second, we introduce perspectives from the domain of privacy, emphasizing its significance as a pivotal measure to guard against the improper use of eye-tracking data. Third, we provide a set of guidelines created by researchers actively working within this space. These recommendations are designed to guide policymakers and the general public toward establishing informed, equitable, and privacy-centric standards surrounding these devices. © 2024 IEEE.

关键词： Eye tracking

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：