Matching actions in presence of camera motion

    Authors

    A. Yimaz;M. Shah

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Comput. Vis. Image Underst.

    Keywords

    action recognition; epipolar geometry; video; action retrieval; moving; camera; COMPUTER VISION; HUMAN MOVEMENT; RECOGNITION; MATRICES; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

    Abstract

    When the camera viewing an action is moving, the motion observed in the video not only contains the motion of the actor but also the motion of the camera. At each time instant, in addition to the camera motion, a different view of the action is observed. In this paper, we propose a novel method to perform action recognition in presence of camera motion. Proposed method is based on the epipolar geometry between any two views. However, instead of relating two static views using the standard fundamental matrix, we model the motions of independently moving cameras in the equations governing the epipolar geometry and derive a new relation which is referred to as the "temporal fundamental matrix." Using the temporal fundamental matrix, a matching score between two actions is computed by evaluating the quality of the recovered geometry. We demonstrate the versatility of the proposed approach for action recognition in a number of challenging sequences. (c) 2006 Elsevier Inc. All rights reserved.

    Journal Title

    Computer Vision and Image Understanding

    Volume

    104

    Issue/Number

    2-3

    Publication Date

    1-1-2006

    Document Type

    Article

    Language

    English

    First Page

    221

    Last Page

    231

    WOS Identifier

    WOS:000241689800009

    ISSN

    1077-3142

    Share

    COinS