Deakin University
Browse
venkatesh-combiningimage-2005.pdf (569.87 kB)

Combining image regions and human activity for indirect object recognition in indoor wide-angle views

Download (569.87 kB)
conference contribution
posted on 2005-01-01, 00:00 authored by P Peursum, G West, Svetha VenkateshSvetha Venkatesh
Traditional methods of object recognition are reliant on shape and so are very difficult to apply in cluttered, wideangle and low-detail views such as surveillance scenes. To address this, a method of indirect object recognition is proposed, where human activity is used to infer both the location and identity of objects. No shape analysis is necessary. The concept is dubbed 'interaction signatures', since the premise is that a human will interact with objects in ways characteristic of the function of that object - for example, a person sits in a chair and drinks from a cup. The human-centred approach means that recognition is possible in low-detail views and is largely invariant to the shape of objects within the same functional class. This paper implements a Bayesian network for classifying region patches with object labels, building upon our previous work in automatically segmenting and recognising a human's interactions with the objects. Experiments show that interaction signatures can successfully find and label objects in low-detail views and are equally effective at recognising test objects that differ markedly in appearance from the training objects.

History

Event

IEEE International Conference on Computer Vision (10th : 2005 : Beijing, China)

Pagination

82 - 89

Publisher

IEEE

Location

Beijing, China

Place of publication

Los Alamitos, Calif.

Start date

2005-10-17

End date

2005-10-20

ISSN

1550-5499

ISBN-13

9780769523347

ISBN-10

076952334X

Language

eng

Notes

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2005, IEEE

Title of proceedings

ICCV 2005 : Proceedings of the IEEE International Conference on Computer Vision

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC