检索结果-内蒙古大学图书馆

CrowdSim2: an Open Synthetic Benchmark for Object Detectors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Foszner, Pawel Szczęsna, Agnieszka Ciampi, Luca Messina, Nicola Cygan, Adam Bizon, Bartosz Cogiel, Michal Golba, Dominik Macioszek, Elżbieta Staniszewski, Michal Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Institute of Information Science and Technologies National Research Council Pisa Italy QSystems.pro sp. z o.o. Mochnackiego 34 Bytom41-907 Poland Blees sp. z o.o. Zygmunta Starego 24a/10 Gliwice44-100 Poland Department of Transport Systems Traffic Engineering and Logistics Faculty of Transport and Aviation Engineering Silesian University of Technology Katowice Poland

Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some state-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment. © 2023, CC BY.

关键词： Object detection

Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods

学校读者我要写书评

暂无评论

arXiv 2023年

Generally, crowd datasets can be collected or generated from real or synthetic sources. Real data is generated by using infrastructure-based sensors (such as static cameras or other sensors). The use of simulation tools can significantly reduce the time required to generate scenario-specific crowd datasets, facilitate data-driven research, and next build functional machine learning models. The main goal of this work was to develop an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment, weather conditions, traffic, and the movement and models of individual agents. Finally, three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA. © 2023, CC BY.

关键词： Deep learning

Inattentional Blindness for Redirected Walking Using Dynamic Foveated Rendering

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Joshi, Yashas Poullis, Charalambos Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concordia University

Redirected walking is a Virtual Reality(VR) locomotion technique which enables users to navigate virtual environments (VEs) that are spatially larger than the available physical tracked space. In this work we present a novel technique for redirected walking in VR based on the psychological phenomenon of inattentional blindness. Based on the user’s visual fixation points we divide the user’s view into zones. Spatially-varying rotations are applied according to the zone’s importance and are rendered using foveated rendering. Our technique is real-time and applicable to small and large physical spaces. Furthermore, the proposed technique does not require the use of stimulated saccades but rather takes advantage of naturally occurring saccades and blinks for a complete refresh of the framebuffer. We performed extensive testing and present the analysis of the results of three user studies conducted for the evaluation. Copyright © 2019, The Authors. All rights reserved.

关键词： Virtual reality

Semantic Segmentation from Remote Sensor Data and the Exploitation of Latent Learning for Classification of Auxiliary Tasks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chatterjee, Bodhiswatta Poullis, Charalambos Immersive and Creative Technologies lab and an Applied Scientist at Presagis Inc Canada Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concodia University MontrealQC Canada

—In this paper we address three different aspects of semantic segmentation from remote sensor data using deep neural networks. Firstly, we focus on the semantic segmentation of buildings from remote sensor data and propose ICT-Net: a novel network with the underlying architecture of a fully convolutional network, infused with feature re-calibrated Dense blocks at each layer. Uniquely, the proposed network combines the localization accuracy and use of context of the U-Net network architecture, the compact internal representations and reduced feature redundancy of the Dense blocks, and the dynamic channel-wise feature re-weighting of the Squeeze-and-Excitation(SE) blocks. The proposed network has been tested on the INRIA and AIRS benchmark datasets and is shown to outperform all other state of the art by more than 1.5% and 1.8% on the Jaccard index, respectively. Secondly, as the building classification is typically the first step of the reconstruction process, we investigate the relationship of the classification accuracy to the reconstruction accuracy. A comparative quantitative analysis of reconstruction accuracies corresponding to different classification accuracies confirms the strong correlation between the two. We present the results which show a consistent and considerable reduction in the reconstruction accuracy. Finally, we present the simple yet compelling concept of latent learning and the implications it carries within the context of deep learning. We posit that a network trained on a primary task (i.e. building classification) is unintentionally learning about auxiliary tasks (e.g. the classification of road, tree, etc) which are complementary to the primary task. Although embedded in a trained network, this latent knowledge relating to the auxiliary tasks is never externalized or immediately expressed but instead only knowledge relating to the primary task is ever output by the network. We experimentally prove this occurrence of incidental learning on t

关键词： Classification (of information)

NTU place4dr: A Detailed-Routing-Driven Placer for Mixed-Size Circuit Designs with Technology and Region Constraints

学校读者我要写书评

暂无评论

NTU place4dr: A Detailed-Routing-Driven Placer for Mixed-Siz...

作者： Huang, Chau-Chin Lee, Hsin-Ying Lin, Bo-Qiao Yang, Sheng-Wei Chang, Chin-Hao Chen, Szu-To Chang, Yao-Wen Chen, Tung-Chieh Bustany, Ismail Department of Electrical Engineering Graduate Institute of Electronics Engineering National Taiwan University Taipei106 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei106 Taiwan Maxeda Technologies Inc. Hsinchu300 Taiwan Place and Route Division Mentor Graphics FremontCA94538 United States

A placer without considering modern technology and region constraints could generate solutions with irresolvable detailed-routing (DR) violations or even illegal solutions. This paper presents a high-quality placement algorithm to satisfy technology and region constraints and optimize DR routability with five major techniques: 1) a clustering algorithm followed by two-round quadratic placement to obtain an initial placement satisfying region constraints;2) a novel density control technique to handle prefixed architectures and minimize global routing congestions;3) an analytical placement algorithm with new wirelength and density models to consider region constraints;4) a dynamic penalty increment strategy that reduces wirelength increments during global placement;and 5) a legalization algorithm that preserves the solution quality of global placement while satisfying technology and region constraints. Compared with the winning teams of the ISPD 2015 Blockage-Aware Detailed Routing-Driven Placement Contest and recent works, our placer achieves the best overall score and DR results. © 2017 IEEE.

关键词： Clustering algorithms

Evaluation of cybersecurity threats on smart metering system 14th

学校读者我要写书评

暂无评论

Evaluation of cybersecurity threats on smart metering system

14th International Conference on Information Technology - New Generations, ITNG 2017

作者： Tweneboah-Koduah, Samuel Tsetse, Anthony K. Azasoo, Julius Endicott-Popovsky, Barbara Centre for Media Information and Technology Aalborg University AC Meyers Vænge 15 Copenhagen SVDK-2450 Denmark Department of Computer Science Northern Kentucky University Highland HeightsKY41099 United States Department Computing and Immersive Technologies University of Northampton NorthamptonNN2 6JD United Kingdom Center for Information Assurance and Cybersecurity in Education University of Washington BothelWA98011-8246 United States

ISBN: (纸本)9783319549774

Smart metering has emerged as the next-generation of energy distribution, consumption, and monitoring systems via the convergence of power engineering and information and communication technology (ICT) integration otherwise known as smart grid systems. While the innovation is advancing the future power generation, distribution, consumption monitoring and information delivery, the success of the platform is positively correlated to the thriving integration of technologies upon which the system is built. Nonetheless, the rising trend of cybersecurity attacks on cyber infrastructure and its dependent systems coupled with the system’s inherent vulnerabilities present a source of concern not only to the vendors but also the consumers. These security concerns need to be addressed in order to increase consumer confidence so as to ensure greatest adoption and success of smart metering. In this paper, we present a functional communication architecture of the smart metering system. Following that, we demonstrate and discuss the taxonomy of smart metering common vulnerabilities exposure, upon which sophisticated threats can capitalize. We then introduce countermeasure techniques, whose integration is considered pivotal for achieving security protection against existing and future sophisticated attacks on smart metering systems. © Springer International Publishing AG 2018.

关键词： Smart power grids

Automatic 2D to stereoscopic video conversion for 3D TVS

学校读者我要写书评

暂无评论

Automatic 2D to stereoscopic video conversion for 3D TVS

3DTV Conference

作者： Xichen Zhou Bipin C. Desai Charalambos Poullis Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concordia University

ISBN: (纸本)9781538616369;9781538616352

In this paper we present a novel technique for automatically converting 2D videos to stereoscopic. Uniquely, the proposed approach leverages the strengths of Deep Learning to address the complex problem of depth estimation from a single image. A Convolutional Neural Network is trained on input RGB images and their corresponding depths maps. We reformulate and simplify the process of generating the second camera's depth map and present how this can be used to render an anaglyph image. The anaglyph image was used for demonstration only because of the easy and wide availability of red/cyan glasses however, this does not limit the applicability of the proposed technique to other stereo forms. Finally, we present preliminary results and discuss the challenges.

关键词： Cameras Three-dimensional displays Rendering (computer graphics) Stereo image processing Two dimensional displays Pipelines TV

VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Sekuboyina, Anjany Kumar Husseini, Malek E. Bayat, Amirhossein Löffler, Maximilian Liebl, Hans Li, Hongwei Tetteh, Giles Kukačka, Jan Payer, Christian Štern, Darko Urschler, Martin Chen, Maodong Cheng, Dalong Lessmann, Nikolas Hu, Yujin Wang, Tianfu Yang, Dong Xu, Daguang Ambellan, Felix Amiranashvili, Tamaz Ehlke, Moritz Lamecker, Hans Lehnert, Sebastian Lirio, Marilia de Olaguer, Nicolás Pérez Ramm, Heiko Sahu, Manish Tack, Alexander Zachow, Stefan Jiang, Tao Ma, Xinjun Angerman, Christoph Wang, Xin Brown, Kevin Kirszenberg, Alexandre Puybareau, Élodie Chen, Di Bai, Yiwei Rapazzo, Brandon H. Yeah, Timyoas Zhang, Amber Xu, Shangliang Hou, Feng He, Zhiqiang Zeng, Chan Xiangshang, Zheng Liming, Xu Netherton, Tucker J. Mumme, Raymond P. Court, Laurence E. Huang, Zixun He, Chenhang Wang, Li-Wen Ling, Sai Ho Huynh, Lê Duy Boutry, Nicolas Jakubicek, Roman Chmelik, Jiri Mulay, Supriti Sivaprakasam, Mohanasankar Paetzold, Johannes C. Shit, Suprosanna Ezhov, Ivan Wiestler, Benedikt Glocker, Ben Valentinitsch, Alexander Rempfler, Markus Menze, Björn H. Kirschke, Jan S. Department of Informatics Technical University of Munich Germany Munich School of BioEngineering Technical University of Munich Germany Department of Neuroradiology Klinikum Rechts der Isar Germany Department for Quantitative Biomedicine University of Zurich Switzerland Friedrich Miescher Institute for Biomedical Engineering Switzerland Institute of Biological and Medical Imaging Helmholtz Zentrum München Germany Department of Computing Imperial College London United Kingdom Institute of Computer Graphics and Vision Graz University of Technology Austria Gottfried Schatz Research Center: Biophysics Medical University of Graz Austria School of Computer Science The University of Auckland New Zealand Computer Vision Group iFLYTEK Research South China China Department of Radiology and Nuclear Medicine Radboud University Medical Center Nijmegen Netherlands Shenzhen Research Institute of Big Data China School of Biomedical Engineering Health Science Center Shenzhen University China NVIDIA Corporation United States Zuse Institute Berlin Germany 1000shapes GmbH Berlin Germany Damo Academy Alibaba Group China Department of Mathematics University of Innsbruck Austria Department of Electronic Engineering Fudan University China New York University United States France Deep Reasoning AI Inc United States Technical University of Munich Germany East China Normal University China Chinese Academy of Sciences China Lenovo Group China Ping An Technologies China College of Computer Science and Technology Zhejiang University China Real Doctor AI Research Centre Zhejiang University China The University of Texas MD Anderson Cancer Center United States Department of Electronic and Information Engineering The Hong Kong Polytechnic University China Department of Computing The Hong Kong Polytechnic University China The School of Biomedical Engineering University of Technology Sydney Australia Department of Biomedical Engineering Brno University of Technology Czech Republic India

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://***/nqjyw/, https://***/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://***/anjany/verse. © 2020, CC BY-NC-ND.

关键词： computerized tomography

Underwater photogrammetry in very shallow waters: Main challenges and caustics effect removal

学校读者我要写书评

暂无评论

Underwater photogrammetry in very shallow waters: Main chall...

2018 ISPRS TC II Mid-term Symposium "Towards Photogrammetry 2020"

作者： Agrafiotis, P. Skarlatos, D. Forbes, T. Poullis, C. Skamantzari, M. Georgopoulos, A. Cyprus University of Technology Civil Engineering and Geomatics Dept. Lab of Photogrammetric Vision 2-8 Saripolou str. Limassol3036 Cyprus Immersive and Creative Technologies Lab. Department of Computer Science and Software Engineering Concordia University QuebecH3G 1M8 Canada National Technical University of Athens School of Rural and Surveying Engineering Lab. of Photogrammetry Zografou Campus 9 Heroon Polytechniou str. Zografou Athens15780 Greece

In this paper, main challenges of underwater photogrammetry in shallow waters are described and analysed. The very short camera to object distance in such cases, as well as buoyancy issues, wave effects and turbidity of the waters are challenges to be resolved. Additionally, the major challenge of all, caustics, is addressed by a new approach for caustics removal (Forbes et al., 2018) which is applied in order to investigate its performance in terms of SfM-MVS and 3D reconstruction results. In the proposed approach the complex problem of removing caustics effects is addressed by classifying and then removing them from the images. We propose and test a novel solution based on two small and easily trainable Convolutional Neural Networks (CNNs). Real ground truth for caustics is not easily available. We show how a small set of synthetic data can be used to train the network and later transfer the le arning to real data with robustness to intra-class variation. The proposed solution results in caustic-free images which can be further used for other tasks as may be needed. © Authors 2018.

关键词： Underwater photogrammetry