Video event detection based on over-segmented STV regions

Jing Wang; Zhijie Xu

doi:10.1109/ICCVW.2011.6130423

Video event detection based on over-segmented STV regions

Jing Wang, Zhijie Xu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Real-world environment introduces many variations into video recordings such as changing illumination and object dynamics. In this paper, a technique for abstracting useful spatio-temporal features from graph-based segmentation operations has been proposed. A spatio-temporal volume (STV)-based shape matching algorithm is then devised by using the intersection theory to facilitate the definition and detection of video events. To maintain system efficiency, this research has integrated an innovative feature-weight evaluation mechanism which rewards or punishes recognition outputs based on the segmentation quality. Substantial improvements on both the event Precision and Recall rate and the processing efficiency have been observed in the experiments in the project.

Original language	English
Title of host publication	2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops 2011)
Publisher	IEEE Computer Society
Pages	1464-1471
Number of pages	8
ISBN (Electronic)	9781467300636, 9781467300612
ISBN (Print)	9781467300629
DOIs	https://doi.org/10.1109/ICCVW.2011.6130423
Publication status	Published - 2011
Event	IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011 - Barcelona, Spain Duration: 6 Nov 2011 → 13 Nov 2011

Conference

Conference	IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
Country/Territory	Spain
City	Barcelona
Period	6/11/11 → 13/11/11

Access to Document

10.1109/ICCVW.2011.6130423Licence: Unspecified

Cite this

@inproceedings{65c8246c6aa74e6bb3c5973810abef5b,

title = "Video event detection based on over-segmented STV regions",

abstract = "Real-world environment introduces many variations into video recordings such as changing illumination and object dynamics. In this paper, a technique for abstracting useful spatio-temporal features from graph-based segmentation operations has been proposed. A spatio-temporal volume (STV)-based shape matching algorithm is then devised by using the intersection theory to facilitate the definition and detection of video events. To maintain system efficiency, this research has integrated an innovative feature-weight evaluation mechanism which rewards or punishes recognition outputs based on the segmentation quality. Substantial improvements on both the event Precision and Recall rate and the processing efficiency have been observed in the experiments in the project.",

keywords = "Graph-based segmentation, Object dynamics, Precision and recall, Real world environments, Segmentation quality, Shape matching, Spatio-temporal, System efficiency, Video events",

author = "Jing Wang and Zhijie Xu",

year = "2011",

doi = "10.1109/ICCVW.2011.6130423",

language = "English",

isbn = "9781467300629",

pages = "1464--1471",

booktitle = "2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops 2011)",

publisher = "IEEE Computer Society",

address = "United States",

note = "IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011 ; Conference date: 06-11-2011 Through 13-11-2011",

}

TY - GEN

T1 - Video event detection based on over-segmented STV regions

AU - Wang, Jing

AU - Xu, Zhijie

PY - 2011

Y1 - 2011

N2 - Real-world environment introduces many variations into video recordings such as changing illumination and object dynamics. In this paper, a technique for abstracting useful spatio-temporal features from graph-based segmentation operations has been proposed. A spatio-temporal volume (STV)-based shape matching algorithm is then devised by using the intersection theory to facilitate the definition and detection of video events. To maintain system efficiency, this research has integrated an innovative feature-weight evaluation mechanism which rewards or punishes recognition outputs based on the segmentation quality. Substantial improvements on both the event Precision and Recall rate and the processing efficiency have been observed in the experiments in the project.

AB - Real-world environment introduces many variations into video recordings such as changing illumination and object dynamics. In this paper, a technique for abstracting useful spatio-temporal features from graph-based segmentation operations has been proposed. A spatio-temporal volume (STV)-based shape matching algorithm is then devised by using the intersection theory to facilitate the definition and detection of video events. To maintain system efficiency, this research has integrated an innovative feature-weight evaluation mechanism which rewards or punishes recognition outputs based on the segmentation quality. Substantial improvements on both the event Precision and Recall rate and the processing efficiency have been observed in the experiments in the project.

KW - Graph-based segmentation

KW - Object dynamics

KW - Precision and recall

KW - Real world environments

KW - Segmentation quality

KW - Shape matching

KW - Spatio-temporal

KW - System efficiency

KW - Video events

UR - http://www.scopus.com/inward/record.url?scp=84863049828&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2011.6130423

DO - 10.1109/ICCVW.2011.6130423

M3 - Conference contribution

AN - SCOPUS:84863049828

SN - 9781467300629

SP - 1464

EP - 1471

BT - 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops 2011)

PB - IEEE Computer Society

T2 - IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011

Y2 - 6 November 2011 through 13 November 2011

ER -

Video event detection based on over-segmented STV regions

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this