Content-based software demultiplexing of surveillance video

Steven G. Goodridge

doi:10.1117/12.417567

21 February 2001 Content-based software demultiplexing of surveillance video

Steven G. Goodridge

Proceedings Volume 4232, Enabling Technologies for Law Enforcement and Security; (2001) https://doi.org/10.1117/12.417567
Event: Enabling Technologies for Law Enforcement, 2000, Boston, MA, United States

Abstract

Time-multiplexed video recordings must be demultiplexed for effective analysis by investigators: a task often made difficult by the proprietary nature of the recording equipment. In addition to a lack of standards, some systems may record scenes from different cameras with a time-varying sequence. To address this issue, a content-based image analysis technique for extracting a specified camera view from a multiplexed video sequence is presented. A single frame from the specified view is used as a reference to which subsequent frames are compared. Frames matching the reference within a specified similarity threshold are passed on to the demultiplexed output. An optional region of interest may be used to select an area of the scene that is unique to that camera view but relatively consistent over time. The software implementation of this technique allows multiple camera views to be demultiplexed simultaneously from a digitized stream of multiplexed video. Similarity metrics and adaptive techniques are discussed.

Citation Download Citation

Steven G. Goodridge "Content-based software demultiplexing of surveillance video", Proc. SPIE 4232, Enabling Technologies for Law Enforcement and Security, (21 February 2001); https://doi.org/10.1117/12.417567

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available