Title

Invariance In Motion Analysis Of Videos

Keywords

Human actions; Learning; Spatiotemporal curvature; View-invariant action representation; View-invariant dynamic time warping; View-invariant measure

Abstract

In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represented as a sequence of dynamic instants and intervals, which are automatically computed using the spatiotemporal curvature of the trajectory of moving object in the videos. Dynamic Time Warping (DTW) method matches trajectories using a view invariant similarity measure. Our system is able to incrementally learn different actions without any initialization mode, therefore it can work in an unsupervised manner. The retrieval of relevant videos can be easily performed by computing a simple distance metric. This paper makes two fundamental contribution to view invariant video retrieval: (1) Dynamic Instant detection in trajectories of moving objects acquired from video. (2) View-invariant Dynamic Time Warping to measure similarity between two trajectories of actions performed by different persons and from different viewpoints. Although the learning algorithm is relatively simple in our approach, we can achieve high recognition rate because of the view-invariant representation and the similarity measure using DTW.

Publication Date

1-1-2003

Publication Title

Proceedings of the ACM International Multimedia Conference and Exhibition

Number of Pages

518-527

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/957013.957125

Socpus ID

2342579394 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/2342579394

This document is currently not available here.

Share

COinS