检索结果-内蒙古大学图书馆

Stakeholders Acceptance and Expectations of Robot-Assisted Therapy for Children with Autism Spectrum Disorder

学校读者我要写书评

暂无评论

Stakeholders Acceptance and Expectations of Robot-Assisted T...

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Joan Oliver Rebeca Oliván Jainendra Shukla Annabel Folch Rafael Martínez-Leal Mireia Castellá Domènec Puig Instituto de Robótica para la Dependencia Sitges Barcelona Spain joliver Indraprastha Institute of Information Technology Delhi New Delhi India Intellectual Disability and Developmental Disorders Research Unit Fundaci Villablanca IISPV URV CIBERSAM Reus Spain Intelligent Robotics and Computer Vision Group Universitat Rovira i Virgili Tarragona Spain

ISBN: (纸本)9781728126234

Robot assisted therapy for children with Autism Spectrum Disorder (ASD) should take into account the stakeholders expectations about their potential benefits. Any disparity between the stakeholders expectations and the gained benefits may negatively impact the acceptance and adoption of the robot assisted therapy. In this research, we conducted an observational study with eleven parents and five clinical professionals related with the children with ASD who were preselected to undergo robot assisted therapeutic sessions. The aim was to investigate and identify the potential impact regarding the interventions delivered by the social robots during the interventions, roles of the social robots and benefit offered by them. Specifically, the social robot Cozmo was used for this study. Their opinions were collected using questionnaires and were analyzed quantitatively and *** results of the study confirm a positive attitude towards the adoption of these technologies, both among the caregivers and the professionals.

关键词： The results of the study confirm a positive attitude towards the adoption of these technologies Both among the caregivers and the professionals Autism Spectrum Disorders Robot ACCEPTANCE Child assisting with therapy heart atrium septum defect Observational Study potential impact Intervention Infant

Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bernal, Jose Kushibar, Kaisar Cabezas, Mariano Valverde, Sergi Oliver, Arnau Lladó, Xavier Computer Vision and Robotics Institute Dept. of Computer Architecture and Technology University of Girona Ed. P-IV Av. Lluis Santaló s/n Girona17003 Spain

Accurate brain tissue segmentation in Magnetic Resonance Imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume help in diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNN) approaches. In particular, in this paper, we analyse a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as Fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs and local spatial dependencies may be encoded since several voxels are classified at once. Our study focuses on understanding architectural strengths and weaknesses of literature-like approaches. Hence, we implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks. We evaluate them using the IBSR18, MICCAI2012 and iSeg2017 datasets as they contain infant and adult data and exhibit varied voxel spacing, image quality, number of scans and available imaging modalities. The discussion is driven in three directions: comparison between 2D and 3D approaches, the importance of multiple modalities and overlapping as a sampling strategy for training and testing models. To encourage other researchers to explore the evaluation framework, a public version is accessible to download from our research website. Copyright © 2018, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Automatic Scale Estimation of Structure from Motion based 3D models using laser scalers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Istenic, Klemen Gracias, Nuno Arnaubec, Aurlien Escartn, Javier Garcia, Rafael Underwater Robotics Research Center Computer Vision and Robotics Institute University of Girona Edifici P-IV Campus de Montilivi Girona17071 Spain Coronis Computing S.L. Science and Technological Park of UdG Carrer Pic de Peguera 15 Girona17003 Spain IFREMER Ctr Mediterranee Unit Syst. Marins La Seyne Sur MerF-83507 Universit de Paris Institut de Physique du Globe de Paris CNRS F-75005 France

Recent advances in structure-from-motion techniques are enabling many scientific fields to benefit from the routine creation of detailed 3D models. However, for a large number of applications, only a single camera is available for the image acquisition, due to cost or space constraints in the survey platforms. Monocular structure-from-motion raises the issue of properly estimating the scale of the 3D models, in order to later use those models for metrology. The scale can be determined from the presence of visible objects of known dimensions, or from information on the magnitude of the camera motion provided by other sensors, such as GPS. This paper addresses the problem of accurately scaling 3D models created from monocular cameras in GPS-denied environments, such as in underwater applications. Motivated by the common availability of underwater laser scalers, we present two novel approaches which are suitable for different laser scaler configurations. A fully-calibrated method enables the use of arbitrary laser setups, while a partially-calibrated method reduces the need for calibration by only assuming parallelism on the laser beams, with no constraints on the camera. The proposed methods have several advantages with respect to the existing methods. By using the known geometry of the scene expressed by the 3D model, along with some parameters of the laser scaler geometry, the need for laser alignment with the optical axis of the camera is removed. Furthermore, the extremely error-prone manual identification of image points on the 3D model, currently required in image-scaling methods, is eliminated as well. The performance of the methods and their applicability was evaluated on both data generated from a realistic 3D model and data collected during an oceanographic cruise in 2017. Three separate laser configurations have been tested, encompassing nearly all possible laser setups, to evaluate the effects of terrain roughness, noise, camera perspective angle and camer

关键词： Cameras

Convolutional Neural Networks for Automatic Meter Reading

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Laroca, Rayson Barroso, Victor Diniz, Matheus A. Gonçalves, Gabriel R. Schwartz, William Robson Menotti, David Federal University of Paraná Laboratory of Vision Robotics and Imaging Department of Informatics Av. Coronel Francisco Heráclito dos Santos 100 Curitiba81530-000 Brazil Federal University of Minas Gerais Smart Surveillance Interest Group Department of Computer Science Av. Antônio Carlos 6627 Belo Horizonte31270-010 Brazil

In this paper, we tackle Automatic Meter Reading (AMR) by leveraging the high capability of Convolutional Neural Networks (CNNs). We design a two-stage approach that employs the Fast-YOLO object detector for counter detection and evaluates three different CNN-based approaches for counter recognition. In the AMR literature, most datasets are not available to the research community since the images belong to a service company. In this sense, we introduce a new public dataset, called UFPR-AMR dataset, with 2,000 fully and manually annotated images. This dataset is, to the best of our knowledge, three times larger than the largest public dataset found in the literature and contains a well-defined evaluation protocol to assist the development and evaluation of AMR methods. Furthermore, we propose the use of a data augmentation technique to generate a balanced training set with many more examples to train the CNN models for counter recognition. In the proposed dataset, impressive results were obtained and a detailed speed/accuracy trade-off evaluation of each model was performed. In a public dataset, state-of-the-art results were achieved using less than 200 images for training. Copyright © 2019, The Authors. All rights reserved.

关键词： Public utilities

Augmented Vector Field Navigation Cost Mapping using Inertial Sensors

学校读者我要写书评

暂无评论

Augmented Vector Field Navigation Cost Mapping using Inertia...

International Conference on Advanced robotics (ICAR)

作者： Felipe G. Oliveira Armando Alves Neto Paulo Borges Mario F. M. Campos Douglas G. Macharet Institute of Exact Sciences and Technology Universidade Federal do Amazonas AM Brazil Universidade Federal de Minas Gerais Universidade Federal de Minas Gerais MG Brazil Data 61 Commonwealth Scientific and Industrial Research Organization Brisbane Queensland Australia Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais MG Brazil

In outdoor field robotics, considering the environmental characteristics is key to improving the efficiency of autonomous navigation. In this context, identifying rough terrain can significantly increase the reliability of operations. This paper addresses the problem of mapping the navigation cost associated with uneven outdoor terrains. We propose an augmented vector field representation obtained only with the use of inertial sensors. The map is determined considering characteristics such as roughness and slope. Experiments were carried out with different robots in real-world environments presenting different terrain characteristics to analyze the quality and efficiency of the mapping process. Results show that the obtained navigation cost maps provide a reliable indication of the ground characteristics of outdoor environments and can be used in the path planning stage.

关键词：

Composition loss for counting, density map estimation and localization in dense crowds

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Idrees, Haroon Tayyab, Muhmmad Athrey, Kishan Zhang, Dong Al-Maadeed, Somaya Rajpoot, Nasir Shah, Mubarak Robotics Institute Carnegie Mellon University NVIDIA Inc Computer Science Department Faculty of Engineering Qatar University Department of Computer Science University of Warwick United Kingdom Center for Research in Computer Vision University of Central Florida

With multiple crowd gatherings of millions of people every year in events ranging from pilgrimages to protests, concerts to marathons, and festivals to funerals;visual crowd analysis is emerging as a new frontier in computer vision. In particular, counting in highly dense crowds is a challenging problem with far-reaching applicability in crowd safety and management, as well as gauging political significance of protests and demonstrations. In this paper, we propose a novel approach that simultaneously solves the problems of counting, density map estimation and localization of people in a given dense crowd image. Our formulation is based on an important observation that the three problems are inherently related to each other making the loss function for optimizing a deep CNN decomposable. Since localization requires high-quality images and annotations, we introduce UCF-QNRF dataset that overcomes the shortcomings of previous datasets, and contains 1.25 million humans manually marked with dot annotations. Finally, we present evaluation measures and comparison with recent deep CNN networks, including those developed specifically for crowd counting. Our approach significantly outperforms state-of-the-art on the new dataset, which is the most challenging dataset with the largest number of crowd annotations in the most diverse set of scenes. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： de la Rosa, Ezequiel Reyes, Mauricio Liew, Sook-Lei Hutton, Alexandre Wiest, Roland Kaesmacher, Johannes Hanning, Uta Hakim, Arsany Zubal, Richard Valenzuela, Waldo Robben, David Sima, Diana M. Anania, Vincenzo Brys, Arne Meakin, James A. Mickan, Anne Broocks, Gabriel Heitkamp, Christian Gao, Shengbo Liang, Kongming Zhang, Ziji Siddiquee, Md Mahfuzur Rahman Myronenko, Andriy Ashtari, Pooya Van Huffel, Sabine Jeong, Hyun-Su Yoon, Chi-Ho Kim, Chulhong Huo, Jiayu Ourselin, Sebastien Sparks, Rachel Clèrigues, Albert Oliver, Arnau Lladó, Xavier Chalcroft, Liam Pappas, Ioannis Bertels, Jeroen Heylen, Ewout Moreau, Juliette Hatami, Nima Frindel, Carole Qayyum, Abdul Mazher, Moona Puig, Domenec Lin, Shao-Chieh Juan, Chun-Jung Hu, Tianxi Boone, Lyndon Goubran, Maged Liu, Yi-Jui Wegener, Susanne Kofler, Florian Ezhov, Ivan Shit, Suprosanna Hernandez Petzsche, Moritz R. Menze, Bjoern Kirschke, Jan S. Wiestler, Benedikt Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Informatics Technical University Munich Germany Icometrix Leuven Belgium ARTORG Center for Biomedical Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Switzerland University of Bern Bern Switzerland Chan Division of Occupational Science and Occupational Therapy University of Southern California Los AngelesCA United States Stevens Neuroimaging and Informatics Institute Department of Neurology Keck School of Medicine University of Southern California United States University Institute of Diagnostic and Interventional Neuroradiology Inselspital Bern Switzerland University Institute of Diagnostic and Interventional Neuroradiology University Hospital Bern Inselspital University of Bern Bern Switzerland Department of Diagnostic and Interventional neuroradiology University Medical Center Hamburg-Eppendorf Hamburg Germany Department of Medical Imaging Radboud University Medical Center Institute for Health Sciences Nijmegen Netherlands Deepwise AI Lab Beijing China Beijing University of Posts and Telecommunications Bejing China School of Computing and Augmented Intelligence Arizona State University TempeAZ United States NVIDIA Santa ClaraCA United States STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Pohang Korea Republic of School of Biomedical Engineering & Imaging Sciences King’s College London United Kingdom Institute of Computer Vision and Robotics University of Girona Spain Wellcome Centre for Human Neuroimaging University College London London United Kingdom Laboratory of Neuro Imaging Stevens Institute for Neuroimaging and Informatics Keck School of Medicine University of Southern California Los Angeles United States KU Leuven Leuven Belgium CREATIS Université Lyon1 CNRS UMR5220 INSERM U1206 INSA-Lyon Villeurbanne696

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad

关键词： Diagnosis

A holistic visual place recognition approach using lightweight CNNs for significant viewpoint and appearance changes

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Khaliq, Ahmad Ehsan, Shoaib Chen, Zetao Milford, Michael McDonald-Maier, Klaus Embedded and Intelligent System Lab School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Vision for Robotics Lab Eth Zurich Zurich8092 Switzerland Australian Centre for Robotic Vision School of Electrical Engineering and Computer Science Queensland University of Technology Brisbane Australia

This paper presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12x average speedup relative to state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Robot applications

A semi-global color correction for underwater image restoration 17

学校读者我要写书评

暂无评论

A semi-global color correction for underwater image restorat...

44th International Conference on computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017

作者： Ancuti, Codruta O. Ancuti, Cosmin De Vleeschouwer, Christophe Garcia, Rafael Computer Vision and Robotics Group UdG Spain MEO Universitatea Politehnica Timisoara Romania ICTEAM Universite Catholique de Louvain Belgium

ISBN: (纸本)9781450350150

In underwater the light propagation is distorted due to the absorption and scattering, which respectively affect the energy and direction of propagated light. These distortions result in scenes with foggy appearance and poor contrast. Moreover, in underwater the colors are faded because their composing wavelengths are cut according to the water depth. Since the deterioration of underwater scenes results from the combination of multiplicative and additive processes, enhancing the visibility in underwater is a challenging task. Underwater single image based techniques [Ancuti et al. 2012, 2016a] have been introduced only recently and in general have been inspired by the outdoor dehazing strategies [Ancuti et al. 2010], [He et al. 2011], [Ancuti and Ancuti 2013], [Ancuti et al. 2016b]. One of the most influential technique was introduced by He et al. [He et al. 2011] based on the Dark Channel Prior (DCP) shown to fail for underwater dehazing (see Figure 1). Indeed, underwater image restoration is more challenging since the attenuation medium factor is color dependent and higher than in aerial conditions. Even if the transmission is well estimated the result image can not be effectively restored without initial image color spectrum restoration (see UDCP result in Figure 1). © 2017 Copyright held by the owner/author(s).

关键词： Image reconstruction