Morse Functions for Activity Classification Using Spatiotemporal Volumes
Cuntoor, N.P.
Computer Vision and Pattern Recognition Workshop, 2006. CVPRW apos;06. Conference on
Volume , Issue , 17-22 June 2006 Page(s): 20 - 20
Digital Object Identifier   10.1109/CVPRW.2006.129
Summary: Activities can be represented using spatiotemporal volumes or xyt cubes that are formed by stacking frames in a video sequence. Objects moving in the scene carve out patterns in the volume. In this paper we present an algebraic way of characterizing the topology of the volume using Morse theory. We propose a Morse function based on dynamics of moving objects and use the critical points and the associated critical values as a signature of the activity. Experiments using the TSA airport surveillance dataset are used to demonstrate the usefulness of the proposed method for activity recognition.

» View citation and abstract

Log in by entering your IEEE Web Account Username and Password.

IEEE Communications Society members: If you subscribe to the IEEE Electronic Periodicals Package or IEEE Electronic Periodicals Package Plus, you must access your subscription at www.comsoc.org.

Check with your librarian, information professional, or system manager to determine if you need to log in. Please complete the online Technical Support Form if you need assistance.

Select the Purchase History link to access the document. You will have 5 Days after purchase to access the Full Text PDF. Please complete the online Technical Support Form if you need assistance.

• Search and access Abstract records free of charge
• Register for table of contents alerts
• Purchase Full Text PDF documents

» Learn more about subscription options or how to become an IEEE Member.