Extracting primary features of a statistical pressure snake.
Author(s) -
Hanspeter Schaub
Publication year - 2004
Publication title -
osti oai (u.s. department of energy office of scientific and technical information)
Language(s) - English
Resource type - Reports
DOI - 10.2172/974894
Subject(s) - artificial intelligence , computer vision , pixel , orientation (vector space) , computer science , position (finance) , a priori and a posteriori , plane (geometry) , track (disk drive) , image (mathematics) , motion (physics) , pattern recognition (psychology) , series (stratigraphy) , image plane , mathematics , geometry , geology , paleontology , philosophy , finance , epistemology , economics , operating system
Assume a target motion is visible in the video signal. Statistical pressure snakes are used to track a target specified by a single or a multitude of colors. These snakes define the target contour through a series of image plane coordinate points. This report outlines how to compute certain target degrees of freedom. The image contour can be used to efficiently compute the area moments of the target, which in return will yield the target center of mass, as well as the orientation of the target principle axes. If the target has a known shape such as begin rectangular or circular, then the dimensions of this shape can be estimated in units of image pixels. If the physical target dimensions are known apriori, then the measured target dimensions can be used to estimate the target depth
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom