Local feature trajectories for efficient event-based indexing of video sequences

Authors:
Nicolas Moënne-Loccoz;Eric Bruno;Stéphane Marchand-Maillet
Affiliations:
University of Geneva, Geneva 4, Switzerland;University of Geneva, Geneva 4, Switzerland;University of Geneva, Geneva 4, Switzerland
Venue:
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
Year:
2006

Citing 11
Cited 0

Feature tracking with automatic selection of spatial scales

Computer Vision and Image Understanding
The Recognition of Human Movement Using Temporal Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Space-time Interest Points

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Video Google: A Text Retrieval Approach to Object Matching in Videos

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Velocity Adaptation of Space-Time Interest Points

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Recognizing Human Actions: A Local SVM Approach

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Unsupervised event discrimination based on nonlinear temporal modeling of activity content

Pattern Analysis & Applications
Using multi-scale histograms to answer pattern existence and shape match queries

SSDBM'2005 Proceedings of the 17th international conference on Scientific and statistical database management
Nonparametric motion characterization using causal probabilistic models for video indexing and retrieval

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of indexing video sequences according to the events they depict. While a number of different approaches have been proposed in order to describe events, none is sufficiently generic and computationally efficient to be applied to event-based retrieval of video sequences within large databases. In this paper, we propose a novel index of video sequences which aims at describing their dynamic content. This index relies on the local feature trajectories estimated from the spatio-temporal volume of the video sequences. The computation of this index is efficient, makes assumption neither about the represented events nor about the video sequences. We show through a batch of experimentations on standard video sequence corpus that this index permits to classify complex human activities as efficiently as state of the art methods while being far more efficient to retrieve generic classes of events.