检索结果-内蒙古大学图书馆

Overscan Detection in Digitized Analog Films by Precise Sprocket Hole Segmentation 15th

学校读者我要写书评

暂无评论

Overscan Detection in Digitized Analog Films by Precise Spro...

15th International Symposium on visual computing, ISVC 2020

作者： Helm, Daniel Kampel, Martin Institute of Visual Computing and Human-Centered Technology Computer Vision Lab TU Wien Vienna Austria

ISBN: (纸本)9783030645557

Automatic video analysis is explored in order to understand and interpret real-world scenes automatically. For digitized historical analog films, this process is influenced by the video quality, video composition or scan artifacts called overscanning. The main aim of this paper is to find the Sprocket Holes (SH) in digitized analog film frames in order to drop unwanted overscan areas and extract the correct scaled final frame content which includes the most significant frame information. The outcome of this investigation proposes a precise overscan detection pipeline which combines the advantages of supervised segmentation networks such as DeepLabV3 with an unsupervised Gaussian Mixture Model for fine-grained segmentation based on histogram features. Furthermore, this exploration demonstrates the strength of using low-level backbone features in combination with low-cost CNN architectures like SqueezeNet in terms of inference runtime and segmentation performance. Moreover, a pipeline for creating photo-realistic frame samples to build a self-generated dataset is introduced and used in the training and validation phase. This dataset consists of 15000 image-mask pairs including synthetically created and deformed SHs with respect to the exact film reel layout geometry. Finally, the approach is evaluated by using real-world historical film frames including original SHs and deformations such as scratches, cracks or wet splices. The proposed approach reaches a Mean Intersection over Union (mIoU) score of 0.9509 (@threshold: 0.5) as well as a Dice Coefficient of 0.974 (@threshold: 0.5) and outperforms state-of-the-art solutions. Finally, we provide full access to our source code as well as the self-generated dataset in order to promote further research on digitized analog film analysis and fine-grained object segmentation. © 2020, Springer Nature Switzerland AG.

关键词： Sprockets

RSVP for VPSA: A Meta Design Study on Rapid Suggestive visualization Prototyping for visual Parameter Space Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Klaffenboeck, Manfred Gleicher, Michael Sorger, Johannes Wimmer, Michael Möller, Torsten The Institute of Visual Computing and Human Centered Technology TU Wien Austria The Complexity Science Hub Vienna Austria The Department of Computer Sciences The University of Wisconsin - Madison United States The Faculty of Computer Science The University of Vienna The Research Network Data Science Uni Wien Austria

visual Parameter Space Analysis (VPSA) enables domain scientists to explore input-output relationships of computational models. Existing VPSA applications often feature multi-view visualizations designed by visualization experts for a specific scenario, making it hard for domain scientists to adapt them to their problems without professional help. We present RSVP, the Rapid Suggestive visualization Prototyping system encoding VPSA knowledge to enable domain scientists to prototype custom visualization dashboards tailored to their specific needs. The system implements a task-oriented, multi-view visualization recommendation strategy over a visualization design space optimized for VPSA to guide users in meeting their analytical demands. We derived the VPSA knowledge implemented in the system by conducting an extensive meta design study over the body of work on VPSA. We show how this process can be used to perform a data and task abstraction, extract a common visualization design space, and derive a task-oriented VisRec strategy. User studies indicate that the system is user-friendly and can uncover novel insights. © 2024, CC BY.

关键词： visualization

Temporal Alignment of human Motion Data: A Geometric Point of View

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tumpach, Alice Barbora Kán, Peter Institut CNRS Pauli Oskar-Morgenstern-Platz 1 Vienna1090 Austria University of Lille Cité scientifique Villeneuve d'Ascq59650 France Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria

Temporal alignment is an inherent task in most applications dealing with videos: action recognition, motion transfer, virtual trainers, rehabilitation, etc. In this paper we dive into the understanding of this task from a geometric point of view: in particular, we show that the basic properties that are expected from a temporal alignment procedure imply that the set of aligned motions to a template form a slice to a principal fiber bundle for the group of temporal reparameterizations. A temporal alignment procedure provides a reparameterization invariant projection onto this particular slice. This geometric presentation allows to elaborate a consistency check for testing the accuracy of any temporal alignment procedure. We give examples of alignment procedures from the literature applied to motions of tennis players. Most of them use dynamic programming to compute the best correspondence between two motions relative to a given cost function. This step is computationally expensive (of complexity O(NM) where N and M are the numbers of frames). Moreover most methods use features that are invariant by translations and rotations in R3, whereas most actions are only invariant by translation along and rotation around the vertical axis, where the vertical axis is aligned with the gravitational field. The discarded information contained in the vertical direction is crucial for accurate synchronization of motions. We propose to incorporate keyframe correspondences into the dynamic programming algorithm based on coarse information extracted from the vertical variations, in our case from the elevation of the arm holding the racket. The temporal alignment procedures produced are not only more accurate, but also computationally more efficient. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost functions

Deep Vehicle Detection in Satellite Video

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pflugfelder, Roman Weissenfeld, Axel Wagner, Julian The Dynamic Vision and Learning Group Technical University Munich Germany The Center of Digital Safety & Security Austrian Institute of Technology Austria The Institute of Visual Computing & Human-Centered Technology University of Technology Vienna Austria

This work presents a deep learning approach for vehicle detection in satellite video. Vehicle detection is perhaps impossible in single EO satellite images due to the tininess of vehicles (4-10 pixel) and their similarity to the background. Instead, we consider satellite video which overcomes the lack of spatial information by temporal consistency of vehicle movement. A new spatiotemporal model of a compact 3 × 3 convolutional, neural network is proposed which neglects pooling layers and uses leaky ReLUs. Then we use a reformulation of the output heatmap including Non-Maximum-Suppression (NMS) for the final segmentation. Empirical results on two new annotated satellite videos reconfirm the applicability of this approach for vehicle detection. They more importantly indicate that pre-training on WAMI data and then fine-tuning on few annotated video frames for a new video is sufficient. In our experiment only five annotated images yield a F1 score of 0.81 on a new video showing more complex traffic patterns than the Las Vegas video. Our best result on Las Vegas is a F1 score of 0.87 which makes the proposed approach a leading method for this benchmark. Copyright © 2022, The Authors. All rights reserved.

关键词： Satellites

Tolerating Untrustworthy Robots: Studying human Vulnerability Experience within a Privacy Scenario for Trust in Robots

学校读者我要写书评

暂无评论

Tolerating Untrustworthy Robots: Studying Human Vulnerabilit...

IEEE International Workshop on Robot and human Communication (ROMAN)

作者： Glenda Hannibal Anna Dobrosovestnova Astrid Weiss Institute of Artificial Intelligence (xAI Group) Ulm University Ulm Baden-Württemberg Germany Institute of Visual Computing and Human-Centered Technology (HCI Group) TU Wien Austria

ISBN: (数字)9781728188591

ISBN: (纸本)9781665406802

Focusing on human experience of vulnerability in everyday life interaction scenarios is still a novel approach. So far, only a proof-of-concept online study has been conducted, and to extend this work, we present a follow-up online study. We consider in more detail how human experience of vulnerability caused by a trust violation through a privacy breach affects trust ratings in an interaction scenario with the PEPPER robot assisting with clothes shopping. We report the results from 32 survey responses and 11 semi-structured interviews. Our findings reveal the existence of the privacy paradox also for studying trust in HRI, which is a common observation describing a discrepancy between the stated privacy concerns by people and their behavior to safeguard it. Moreover, we reflect that participants considered only the added value of utility and entertainment when deciding whether or not to interact with the robot again, but not the privacy breach. We conclude that people might tolerate an untrustworthy robot even when they are feeling vulnerable in the everyday life situation of clothes shopping.

关键词： Entertainment industry Focusing Robot sensing systems Privacy breach Behavioral sciences Interviews

FISHing in Uncertainty: Synthetic Contrastive Learning for Genetic Aberration Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gutwein, Simon Kampel, Martin Taschner-Mandl, Sabine Licandro, Roxane St. Anna Children’s Cancer Research Institute Vienna Austria TU Wien Institute of Visual Computing and Human-Centered Technology Computer Vision Lab Vienna Austria Medical University of Vienna Department of Biomedical Imaging and Image-guided Therapy Computational Imaging Research ELIA Group Vienna Austria

Detecting genetic aberrations is crucial in cancer diagnosis, typically through fluorescence in situ hybridization (FISH). However, existing FISH image classification methods face challenges due to signal variability, the need for costly manual annotations and fail to adequately address the intrinsic uncertainty. We introduce a novel approach that leverages synthetic images to eliminate the requirement for manual annotations and utilizes a joint contrastive and classification objective for training to account for inter-class variation effectively. We demonstrate the superior generalization capabilities and uncertainty calibration of our method, which is trained on synthetic data, by testing it on a manually annotated dataset of real-world FISH images. Our model offers superior calibration in terms of classification accuracy and uncertainty quantification with a classification accuracy of 96.7% among the 50% most certain cases. The presented end-to-end method reduces the demands on personnel and time and improves the diagnostic workflow due to its accuracy and adaptability. All code and data is publicly accessible at: https://***/SimonBon/FISHing. © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

Fast multi-view rendering for real-time applications

学校读者我要写书评

暂无评论

Fast multi-view rendering for real-time applications

20th Eurographics Symposium on Parallel Graphics and visualization, EGPGV 2020

作者： Unterguggenberger, Johannes Kerbl, Bernhard Steinberger, Markus Schmalstieg, Dieter Wimmer, Michael TU Wien Institute of Visual Computing and Human-Centered Technology Austria Graz University of Technology Austria

ISBN: (纸本)9783038681076

Efficient rendering of multiple views can be a critical performance factor for real-time rendering applications. Generating more than one view multiplies the amount of rendered geometry, which can cause a huge performance impact. Minimizing that impact has been a target of previous research and GPU manufacturers, who have started to equip devices with dedicated acceleration units. However, vendor-specific acceleration is not the only option to increase multi-view rendering (MVR) performance. Available graphics API features, shader stages and optimizations can be exploited for improved MVR performance, while generally offering more versatile pipeline configurations, including the preservation of custom tessellation and geometry shaders. In this paper, we present an exhaustive evaluation of MVR pipelines available on modern GPUs. We provide a detailed analysis of previous techniques, hardware-accelerated MVR and propose a novel method, leading to the creation of an MVR catalogue. Our analyses cover three distinct applications to help gain clarity on overall MVR performance characteristics. Our interpretation of the observed results provides a guideline for selecting the most appropriate one for various use cases on different GPU architectures. © 2020 The Author(s) Eurographics Proceedings © 2020 The Eurographics Association.

关键词：

Head Up visualization of Spatial Sound Sources in Virtual Reality for Deaf and Hard-of-Hearing People

学校读者我要写书评

暂无评论

Head Up Visualization of Spatial Sound Sources in Virtual Re...

IEEE Annual International Symposium Virtual Reality

作者： Mohammadreza Mirzaei Peter Kán Hannes Kaufmann Institute of Visual Computing and Human-Centered Technology Vienna University of Technology Vienna Austria Aarhus University Denmark

This paper presents a novel method for the visualization of 3D spatial sounds in Virtual Reality (VR) for Deaf and Hard-of-Hearing (DHH) people. Our method enhances traditional VR devices with additional haptic and visual feedback, which aids spatial sound localization. The proposed system automatically analyses 3D sound from VR application, and it indicates the direction of sound sources to a user by two Vibro-motors and two Light-Emitting Diodes (LEDs). The benefit of automatic sound analysis is that our method can be used in any VR application without modifying the application itself. We evaluated the proposed method for 3D spatial sound visualization in a user study. Additionally, the conducted user study investigated which condition (corresponding to different senses) leads to faster performance in 3D sound localization task. For this purpose, we compared three conditions: haptic feedback only, LED feedback only, combined haptic and LED feedback. Our study results suggest that DHH participants could complete sound-related VR tasks significantly faster using LED and haptic+LED conditions in comparison to only haptic feedback. The presented method for spatial sound visualization can be directly used to enhance VR applications for use by DHH persons, and the results of our user study can serve as guidelines for the future design of accessible VR systems.

关键词： Location awareness visualization Three-dimensional displays Virtual reality Auditory system User interfaces Light emitting diodes

Multi-modal Spatial Object Localization in Virtual Reality for Deaf and Hard-of-Hearing People

学校读者我要写书评

暂无评论

Multi-modal Spatial Object Localization in Virtual Reality f...

IEEE Annual International Symposium Virtual Reality

作者： Mohammadreza Mirzaei Peter Kán Hannes Kaufmann Institute of Visual Computing and Human-Centered Technology Vienna University of Technology Vienna Austria Aarhus University Denmark

Information visualization techniques play an important role in Virtual Reality (VR) because they improve task performance, support cognitive processes, and eventually increase the feeling of immersion. Deaf and Hard-of-Hearing (DHH) persons have special needs for information presentation because they feel and perceive VR environments differently. Therefore, it is necessary to pay attention to requirements about presenting information in VR for this group of users. Previous research showed that adding special features and using haptic methods helps DHH persons to do VR tasks better. In this paper, we propose a novel Omni-directional particle visualization method and also evaluate multi-modal presentation methods in VR for DHH persons, such as audio, visual, haptic, and a combination of them (AVH). Additionally, we compare the results with the results of persons without hearing problems. The methods for information presentation in our study focus on spatial object localization in VR. Our user studies show that both DHH persons and persons without hearing problems were able to do VR tasks significantly faster using AVH. Also, we found out that DHH persons can do visual-related VR tasks faster than persons without hearing problems by using our new proposed visualization method. Our results suggest that the benefits of using audio among persons without hearing problems and the benefits of using vision among DHH persons cause an interesting balance in the results of AVH between both groups. Finally, our qualitative and quantitative evaluation indicates that both groups of participants preferred and enjoyed AVH modality more than other modalities.

关键词： Location awareness visualization Three-dimensional displays Cognitive processes Auditory system Virtual reality User interfaces