1 resultado para Smoke detectors
em Massachusetts Institute of Technology
Filtro por publicador
- Repository Napier (1)
- University of Cagliari UniCA Eprints (1)
- Aberdeen University (3)
- Abertay Research Collections - Abertay University’s repository (1)
- Aberystwyth University Repository - Reino Unido (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (4)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (5)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (3)
- Aquatic Commons (22)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (1)
- Archive of European Integration (3)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (10)
- Aston University Research Archive (5)
- Biblioteca de Teses e Dissertações da USP (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (11)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (5)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (24)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (37)
- Boston University Digital Common (9)
- Brock University, Canada (1)
- Bucknell University Digital Commons - Pensilvania - USA (1)
- CaltechTHESIS (27)
- Cambridge University Engineering Department Publications Database (54)
- CentAUR: Central Archive University of Reading - UK (19)
- Center for Jewish History Digital Collections (2)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (118)
- CORA - Cork Open Research Archive - University College Cork - Ireland (4)
- Deakin Research Online - Australia (37)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (3)
- Digital Commons - Michigan Tech (1)
- Digital Commons - Montana Tech (1)
- Digital Commons at Florida International University (6)
- DigitalCommons@The Texas Medical Center (6)
- Diposit Digital de la UB - Universidade de Barcelona (1)
- Doria (National Library of Finland DSpace Services) - National Library of Finland, Finland (1)
- Duke University (11)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (4)
- Greenwich Academic Literature Archive - UK (11)
- Helda - Digital Repository of University of Helsinki (33)
- Illinois Digital Environment for Access to Learning and Scholarship Repository (1)
- Indian Institute of Science - Bangalore - Índia (56)
- Institutional Repository of Leibniz University Hannover (1)
- INSTITUTO DE PESQUISAS ENERGÉTICAS E NUCLEARES (IPEN) - Repositório Digital da Produção Técnico Científica - BibliotecaTerezine Arantes Ferra (5)
- Instituto Nacional de Saúde de Portugal (2)
- Instituto Politécnico de Bragança (1)
- Instituto Politécnico do Porto, Portugal (1)
- Massachusetts Institute of Technology (1)
- National Center for Biotechnology Information - NCBI (2)
- Publishing Network for Geoscientific & Environmental Data (1)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (100)
- Queensland University of Technology - ePrints Archive (155)
- RCAAP - Repositório Científico de Acesso Aberto de Portugal (1)
- Repositório Alice (Acesso Livre à Informação Científica da Embrapa / Repository Open Access to Scientific Information from Embrapa) (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (1)
- Repositório Institucional da Universidade de Aveiro - Portugal (15)
- Repositório Institucional da Universidade Federal de São Paulo - UNIFESP (1)
- Repositorio Institucional de la Universidad de Málaga (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (58)
- Research Open Access Repository of the University of East London. (2)
- SAPIENTIA - Universidade do Algarve - Portugal (1)
- South Carolina State Documents Depository (1)
- Universidad de Alicante (3)
- Universidad Politécnica de Madrid (11)
- Universidade de Lisboa - Repositório Aberto (1)
- Universidade Federal do Pará (1)
- Universitat de Girona, Spain (1)
- Université de Lausanne, Switzerland (1)
- Université de Montréal, Canada (3)
- University of Michigan (46)
- University of Queensland eSpace - Australia (13)
- University of Washington (1)
- WestminsterResearch - UK (1)
Resumo:
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. In particular, for independently trained detectors, the (run-time) computational complexity, and the (training-time) sample complexity, scales linearly with the number of classes to be detected. It seems unlikely that such an approach will scale up to allow recognition of hundreds or thousands of objects. We present a multi-class boosting procedure (joint boosting) that reduces the computational and sample complexity, by finding common features that can be shared across the classes (and/or views). The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required, and therefore the computational cost, is observed to scale approximately logarithmically with the number of classes. The features selected jointly are closer to edges and generic features typical of many natural structures instead of finding specific object parts. Those generic features generalize better and reduce considerably the computational cost of an algorithm for multi-class object detection.