1 resultado para Here I Come!
em Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España
Filtro por publicador
- University of Cagliari UniCA Eprints (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (1)
- Adam Mickiewicz University Repository (11)
- AMS Campus - Alm@DL - Università di Bologna (3)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (114)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (116)
- Aquatic Commons (5)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (11)
- Archive of European Integration (2)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (3)
- Aston University Research Archive (6)
- Avian Conservation and Ecology - Eletronic Cientific Hournal - Écologie et conservation des oiseaux: (1)
- Biblioteca de Teses e Dissertações da USP (3)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (7)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (8)
- Biblioteca Digital de la Universidad Católica Argentina (1)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (6)
- Biblioteca Valenciana Digital - Ministerio de Educación, Cultura y Deporte - Valencia - Espanha (1)
- Blue Tiger Commons - Lincoln University - USA (1)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (31)
- Brock University, Canada (15)
- Bucknell University Digital Commons - Pensilvania - USA (5)
- Bulgarian Digital Mathematics Library at IMI-BAS (1)
- CaltechTHESIS (8)
- Cambridge University Engineering Department Publications Database (3)
- CentAUR: Central Archive University of Reading - UK (42)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (9)
- Coffee Science - Universidade Federal de Lavras (2)
- CORA - Cork Open Research Archive - University College Cork - Ireland (8)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (1)
- CUNY Academic Works (1)
- Dalarna University College Electronic Archive (27)
- Deakin Research Online - Australia (40)
- Digital Archives@Colby (1)
- Digital Commons - Michigan Tech (4)
- Digital Commons @ DU | University of Denver Research (1)
- Digital Commons @ Winthrop University (2)
- Digital Commons at Florida International University (13)
- Digital Peer Publishing (3)
- DigitalCommons@The Texas Medical Center (20)
- DigitalCommons@University of Nebraska - Lincoln (18)
- DRUM (Digital Repository at the University of Maryland) (13)
- Duke University (9)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (3)
- Fachlicher Dokumentenserver Paedagogik/Erziehungswissenschaften (1)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (1)
- Greenwich Academic Literature Archive - UK (4)
- Harvard University (2)
- Helda - Digital Repository of University of Helsinki (21)
- Illinois Digital Environment for Access to Learning and Scholarship Repository (3)
- Indian Institute of Science - Bangalore - Índia (21)
- Institutional Repository of Leibniz University Hannover (1)
- Instituto Gulbenkian de Ciência (1)
- Martin Luther Universitat Halle Wittenberg, Germany (1)
- Memoria Académica - FaHCE, UNLP - Argentina (8)
- Ministerio de Cultura, Spain (1)
- National Center for Biotechnology Information - NCBI (57)
- Nottingham eTheses (1)
- Open University Netherlands (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (1)
- Publishing Network for Geoscientific & Environmental Data (7)
- QSpace: Queen's University - Canada (2)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (44)
- Queensland University of Technology - ePrints Archive (39)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (2)
- Repositório digital da Fundação Getúlio Vargas - FGV (1)
- Repositório Digital da UNIVERSIDADE DA MADEIRA - Portugal (1)
- Repositório Institucional da Universidade de Aveiro - Portugal (1)
- Repositório Institucional da Universidade Estadual de São Paulo - UNESP (1)
- Repositório Institucional da Universidade Federal do Rio Grande do Norte (1)
- Repositorio Institucional de la Universidad Nacional Agraria (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (24)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (1)
- SAPIENTIA - Universidade do Algarve - Portugal (2)
- South Carolina State Documents Depository (1)
- Universidad de Alicante (2)
- Universidad del Rosario, Colombia (2)
- Universidad Politécnica de Madrid (15)
- Universidade de Lisboa - Repositório Aberto (2)
- Universidade Federal do Pará (3)
- Universidade Federal do Rio Grande do Norte (UFRN) (2)
- Universidade Metodista de São Paulo (1)
- Universita di Parma (3)
- Universitat de Girona, Spain (15)
- Université de Lausanne, Switzerland (5)
- Université de Montréal, Canada (23)
- University of Connecticut - USA (1)
- University of Michigan (23)
- University of Queensland eSpace - Australia (10)
- University of Southampton, United Kingdom (1)
- University of Washington (10)
- WestminsterResearch - UK (2)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
[EN] We analyze the discontinuity preserving problem in TV-L1 optical flow methods. This type of methods typically creates rounded effects at flow boundaries, which usually do not coincide with object contours. A simple strategy to overcome this problem consists in inhibiting the diffusion at high image gradients. In this work, we first introduce a general framework for TV regularizers in optical flow and relate it with some standard approaches. Our survey takes into account several methods that use decreasing functions for mitigating the diffusion at image contours. Consequently, this kind of strategies may produce instabilities in the estimation of the optical flows. Hence, we study the problem of instabilities and show that it actually arises from an ill-posed formulation. From this study, it is possible to come across with different schemes to solve this problem. One of these consists in separating the pure TV process from the mitigating strategy. This has been used in another work and we demonstrate here that it has a good performance. Furthermore, we propose two alternatives to avoid the instability problems: (i) we study a fully automatic approach that solves the problem based on the information of the whole image; (ii) we derive a semi-automatic approach that takes into account the image gradients in a close neighborhood adapting the parameter in each position. In the experimental results, we present a detailed study and comparison between the different alternatives. These methods provide very good results, especially for sequences with a few dominant gradients. Additionally, a surprising effect of these approaches is that they can cope with occlusions. This can be easily achieved by using strong regularizations and high penalizations at image contours.