Go to:
Logótipo
Comuta visibilidade da coluna esquerda
Você está em: Start > Publications > View > Video object matching across multiple independent views using local descriptors and adaptive learning
Publication

Publications

Video object matching across multiple independent views using local descriptors and adaptive learning

Title
Video object matching across multiple independent views using local descriptors and adaptive learning
Type
Article in International Scientific Journal
Year
2009
Journal
Vol. 30 No. 2
Pages: 157-167
ISSN: 0167-8655
Publisher: Elsevier
Indexing
Publicação em ISI Web of Science ISI Web of Science
COMPENDEX
INSPEC
Scientific classification
FOS: Natural sciences > Computer and information sciences
CORDIS: Technological sciences > Technology > Computer technology > Image processing
Other information
Authenticus ID: P-003-NS9
Abstract (EN): Object detection and tracking is an essential preliminary task in event analysis systems (e.g. visual surveillance). Typically objects are extracted and tagged, forming representative tracks of their activity. Tagging is Usually performed by probabilistic data association, however, in systems capturing disjoint areas it is often not possible to establish such associations, as data may have been collected at different times OF in different locations. In this case, appearance matching is a valuable aid. We propose using bag-of-visterms, i.e. an histogram of quantized local feature descriptors, to represent and match tracked objects. This method has proven to be effective for object matching and classification in image retrieval applications, where descriptors can be extracted a priori. An important difference in event analysis systems is that relevant information is typically restricted to the foreground. Descriptors can, therefore, be extracted faster, approaching real-time requirements. Also, unlike image retrieval, objects can change over time and therefore their model needs to be updated Continuously. Incremental or adaptive learning is used to tackle this problem. Using independent tracks of 30 different persons, we show that the bag-of-visterms representation effectively discriminates visual object tracks and that it presents high resilience to incorrect object segmentation. Additionally, this methodology allows the construction of scalable object models that can be used to match tracks across independent views.
Language: English
Type (Professor's evaluation): Scientific
No. of pages: 11
Documents
We could not find any documents associated to the publication.
Related Publications

Of the same authors

Editing and Description Framework for Video Objects (2004)
Thesis
Luis F. Teixeira; Luís Corte-Real
Partition-distance methods for assessing spatial segmentations of images and videos (2009)
Article in International Scientific Journal
Jaime S Cardoso; Pedro Carvalho; Luis F Teixeira; Luis Corte Real
Object segmentation using background modelling and cascaded change detection (2007)
Article in International Scientific Journal
Teixeira, LF; Cardoso, JS; Corte Real, L
Analysis of object description methods in a video object tracking environment (2013)
Article in International Scientific Journal
Pedro Carvalho; Telmo Oliveira; Lucian Ciobanu; Filipe Gaspar; Luis F Teixeira; Rafael Bastos; Jaime S Cardoso; Miguel S Dias; Luis Corte Real

See all (11)

Of the same scientific areas

Feature extraction for classification of thin-layer chromatography images (2005)
Article in International Scientific Journal
Sousa, AV; Mendonca, AM; Campilho, A; Aguiar, R; Miranda, CS
Dissimilarity-based classification of chromatographic profiles (2008)
Article in International Scientific Journal
Antonio V Sousa; Ana Maria Mendonca; Aurelio Campilho
Detection of rib borders on X-ray chest radiographs (2004)
Article in International Scientific Journal
R. Moreira; Ana Maria Mendonça; Aurélio Campilho
Real-time implementation of an optical flow algorithm (2002)
Article in International Conference Proceedings Book
Miguel V. Correia; Aurélio Campilho
Image retargeting using stable paths (2009)
Article in International Conference Proceedings Book
Hélder P. Oliveira; Jaime S. Cardoso

Of the same journal

Special issue - Selected papers from the 11th Portuguese Conference on Pattern Recognition - RECPAD2000 - Preface (2001)
Another Publication in an International Scientific Journal
Campilho, AC; Mendonca, AM
Editorial of the special section on CIARP 2021 (2022)
Another Publication in an International Scientific Journal
Papa, JP; João Manuel R. S. Tavares
Understanding the decisions of CNNs: An in-model approach (2020)
Article in International Scientific Journal
Rio Torto, I; Fernandes, K; Luis F Teixeira
Support vector machines with different norms: motivation, formulations and results (2001)
Article in International Scientific Journal
Pedroso, JP; Murata, N
Special Issue of the 11th Portuguese Conference on Pattern Recognition (PRL-RECPAD2000) (2001)
Article in International Scientific Journal
Aurélio Campilho; Ana Maria Mendonça

See all (16)

Recommend this page Top
Copyright 1996-2025 © Faculdade de Direito da Universidade do Porto  I Terms and Conditions  I Acessibility  I Index A-Z
Page created on: 2025-07-10 at 00:48:52 | Privacy Policy | Personal Data Protection Policy | Whistleblowing