Filling the gap in quality assessment of video object tracking

• Tipo: Artigo em Revista Científica Internacional
• Data: 2012

Autores

Pedro Carvalho (Autor) Outra; Jaime S Cardoso (Autor) FEUP; Luis Corte Real (Autor) FEUP

Revista

Título: Image and Vision Computing

Vol. 30 Nº 9

Páginas: 630-640

ISSN: 0262-8856

Editora: Elsevier

Indexação

ISI Web of Knowledge - 7 Citações

ISI Web of Science

Scopus - 8 Citações

Classificação Científica

CORDIS: Ciências Tecnológicas > Engenharia > Engenharia electrotécnica

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

Outras Informações

ID Authenticus: P-002-5SC

DOI: 10.1016/j.imavis.2012.06.002

Abstract (EN): Current evaluation methods either rely heavily on reference information manually annotated or, by completely avoiding human input, provide only a rough evaluation of the performance of video object tracking algorithms. The main objective of this paper is to present a novel approach to the problem of evaluating video object tracking algorithms. It is proposed the use different types of reference information and the combination of heterogeneous metrics for the purpose of approximating the ideal error. This will enable a significant decrease of the required reference information, thus bridging the gap between metrics with different requirements concerning this type of data. As a result, evaluation frameworks can aggregate the benefits from individual approaches while overcoming their weaknesses, providing a flexible and powerful tool to assess and characterize the behavior of the tracking algorithms.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 11