loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: G. J. Burghouts ; L. de Penning ; M. Kruithof ; P. Hanckmann ; J-M Ten Hove ; S. Landsmeer ; S. P. van den Broek ; R. den Hollander ; C. van Leeuwen ; S. Korzec ; H. Bouma and K. Schutte

Affiliation: TNO, Netherlands

ISBN: 978-989-8565-41-9

Keyword(s): Human Behavior Understanding, Search Engine, Video Retrieval, Action Recognition, Textual Description, Meta Data, Indexing, 48 Human Actions.

Related Ontology Subjects/Areas/Topics: Applications ; Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis ; Image Understanding ; Learning of Action Patterns ; Pattern Recognition ; Software Engineering ; Video Analysis

Abstract: The contribution of this paper is a search engine that recognizes and describes 48 human actions in realistic videos. The core algorithms have been published recently, from the early visual processing (Bouma, 2012), discriminative recognition (Burghouts, 2012) and textual description (Hanckmann, 2012) of 48 human actions. We summarize the key algorithms and specify their performance. The novelty of this paper is that we integrate these algorithms into a search engine. In this paper, we add an algorithm that finds the relevant spatio-temporal regions in the video, which is the input for the early visual processing. As a result, meta-data is produced by the recognition and description algorithms. The meta-data is filtered by a novel algorithm that selects only the most informative parts of the video. We demonstrate the power of our search engine by retrieving relevant parts of the video based on three different queries. The search results indicate where specific events occurred, and whi ch actors and objects were involved. We show that events can be successfully retrieved and inspected by usage of the proposed search engine. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.224.89.34

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
J. Burghouts G., de Penning L., Kruithof M., Hanckmann P., Ten Hove J., Landsmeer S., P. van den Broek S., den Hollander R., van Leeuwen C., Korzec S., Bouma H. and Schutte K. (2013). A Search Engine for Retrieval and Inspection of Events with 48 Human Actions in Realistic Videos.In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 413-418. DOI: 10.5220/0004196904130418

@conference{icpram13,
author={G. J. Burghouts and L. de Penning and M. Kruithof and P. Hanckmann and J-M Ten Hove and S. Landsmeer and S. P. van den Broek and R. den Hollander and C. van Leeuwen and S. Korzec and H. Bouma and K. Schutte},
title={A Search Engine for Retrieval and Inspection of Events with 48 Human Actions in Realistic Videos},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={413-418},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004196904130418},
isbn={978-989-8565-41-9},
}

TY - CONF

JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Search Engine for Retrieval and Inspection of Events with 48 Human Actions in Realistic Videos
SN - 978-989-8565-41-9
AU - J. Burghouts G.
AU - de Penning L.
AU - Kruithof M.
AU - Hanckmann P.
AU - Ten Hove J.
AU - Landsmeer S.
AU - P. van den Broek S.
AU - den Hollander R.
AU - van Leeuwen C.
AU - Korzec S.
AU - Bouma H.
AU - Schutte K.
PY - 2013
SP - 413
EP - 418
DO - 10.5220/0004196904130418

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.