Active Learning from Video Streams in a Multi-Camera Scenario

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2014

Autores

Samaneh Khoshrou (Autor) Outra; Jaime S Cardoso (Autor) FEUP; Luis F Teixeira (Autor) FEUP

Ata de Conferência Internacional

Título: 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)

Páginas: 1248-1253

22nd International Conference on Pattern Recognition (ICPR)

Stockholm, SWEDEN, AUG 24-28, 2014

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 2 Citações

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

Outras Informações

ID Authenticus: P-00A-4DD

DOI: 10.1109/icpr.2014.224

Abstract (EN): While video surveillance systems are spreading everywhere, extracting meaningful information from what they are recording is still prohibitively expensive. There is a major effort under way in order to make this process economical by including an intelligent software that eases the burden of the system. In this paper, we introduce an incremental learning framework to classify parallel data streams generated in a multi-camera surveillance scenario. The framework exploits active learning strategies in order to interact wisely with operators to address various problems that exist in such non-stationary environments, such as concept drift and concept evolution. If we look at the problem as mining parallel streams, the framework can address learning from uneven parallel streams applying a class-based ensemble, a problem that has not been addressed before. Favourable results indicate the success of the framework.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6