National
Security
A Workflow
Environment for Video Forensics
Image
Enhancement and Recovery Methods for Analyzing Surveillance Imagery
 Researchers
at ORNL have developed a video forensics workflow environment that
provides a forensic analyst with image restoration and enhancement
tools for managing and processing digitized streams of video surveillance
data. The functionality of this system was driven by user needs
specified by video analysts from the U.S. Secret Service, FBI, and
ATF. This software environment, known as ViTAL (Video Tool for Aiding
Law Enforcement), provides unique capabilities for the video forensics
analyst. An abbreviated list of capabilities include sequence-oriented
processing of sets of video frames, as opposed to single frame processing;
de-interlacing and de-multiplexing of input sequences to accommodate
a wide variety of security camera formats; frame alignment and comparison
to detect and track subtle time varying changes; use of object motion
to perform multiple-frame fusion for resolution improvement and
noise reduction; image de-blurring to accommodate expected optical
aberrations; macro-recording for batch processing; and, automatic
case logging and report generation in HTML format to provide technical
evidentiary documentation.  The
work on ViTAL has also led to the development of a limited capability
for face tracking and recognition in surveillance video sequences.
Base
Technology
The
ORNL ViTAL software system uses multiple technologies to take and
image and attempt an improvement of fidelity. It uses demultiplexing
and de-interlacing methods to input data; motion-estimation, multi-frame
fusion, and optical deblur methods to recover resolution; and provides
image data management, automatic document generation for evidentiary
reporting.
Specifications
and Features
- Windows
OS / MS Visual Studio (VB, C++)
- Standard
image I/O (JPG, Tiff, BMP, etc.)
- Automatic
document generation (HTML)
- Batch
processing and macro recording
- Hardware
independent utility
Fact
Sheet available here in PDF format.
Point
of Contact:
Kenneth W. Tobin, Ph.D.
Group Leader, Image Science & Machine Vision
Engineering Science and Technology Division
Oak Ridge National Laboratory
P.O. Box 2008, MS-6010
Oak Ridge, Tennessee 37831-6010
Office: (865) 574-8521
E-mail: tobinkwjr@ornl.gov
|
