Multi-Frame Object Detection

Download
Author
Laielli, Michael J.
Date
2012-09Advisor
Kolsch, Mathias
Second Reader
Olsen, Richard C.
Metadata
Show full item recordAbstract
This thesis describes an object detection system that extracts and combines appearance information over multiple consecutive video frames, inherently gaining and analyzing information related to motion. Objects that exhibit characteristic motion over the course of multiple frames are able to be detected at smaller scales than achievable by a single-frame detector. Our method builds on the detection work of Viola and Jones, with our extension being the added ability to combine information from multiple frames. Our implementation detects an object in synthetic images at very small scales, down to 3�3 pixels, and has a low false-alarm rate
Description
Approved for public release; distribution is unlimited
Collections
Related items
Showing items related by title, author, creator and subject.
-
Implementation and integration of the object transaction service of CORBA to a JAVA application database program
Hazir, Yildiray (Monterey, California. Naval Postgraduate School, 2000-03);In examining the recent trend of the Client / Server computing technology, it can be seen that distributed object technology is ready to take off. The CORBA (Common Object Request Broker) architecture is the most widely ... -
Finding a hider by an unknown deadline
Lin, Kyle Y.; Singham, Dashi I. (Elsevier, 2016);An object is hidden among several locations. Each search at the object's location independently finds the object with some location-dependent probability. The goal is to find the object by a deadline, but the deadline ... -
Design and specification of an object-oriented data definition language
Badgett, Robert B. (Monterey, California. Naval Postgraduate School, 1995-09);The problem addressed by this thesis is the inability of traditional data models to efficiently support the new database applications of today, such as Computer-Aided Design and multimedia. Traditional data models were ...