4 Matching Results

Search Results

Advanced search parameters have been applied.

Matching a statistical pressure snake to a four-sided polygon and estimating the polygon corners.

Description: Given a video image source, a statistical pressure snake is able to track a color target in real time. This report presents an algorithm that exploits the one-dimensional nature of the visual snake target outline. If the target resembles a four-sided polygon, then the four polygon sides are identified by mapping all image snake point coordinates into Hough space where lines become points. After establishing that four dominant lines are present in snake contour, the polygon corner points are estimated. The computation burden of this algorithm is of the N logN type. The advantage of this method is that it can provide real-time target corner estimates, even if the corners themselves might be occluded.
Date: May 1, 2004
Creator: Schaub, Hanspeter (ORION International Technologies, Albuquerque, NM) & Wilson, Chris C.
Partner: UNT Libraries Government Documents Department

Extracting primary features of a statistical pressure snake.

Description: 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.
Date: May 1, 2004
Creator: Schaub, Hanspeter (ORION International Technologies, Albuquerque, NM)
Partner: UNT Libraries Government Documents Department

Reading color barcodes using visual snakes.

Description: Statistical pressure snakes are used to track a mono-color target in an unstructured environment using a video camera. The report discusses an algorithm to extract a bar code signal that is embedded within the target. The target is assumed to be rectangular in shape, with the bar code printed in a slightly different saturation and value in HSV color space. Thus, the visual snake, which primarily weighs hue tracking errors, will not be deterred by the presence of the color bar codes in the target. The bar code is generate with the standard 3 of 9 method. Using this method, the numeric bar codes reveal if the target is right-side-up or up-side-down.
Date: May 1, 2004
Creator: Schaub, Hanspeter (ORION International Technologies, Albuquerque, NM)
Partner: UNT Libraries Government Documents Department

The Knowledge Base Interface for Parametric Grid Information

Description: The parametric grid capability of the Knowledge Base (KBase) provides an efficient robust way to store and access interpolatable information that is needed to monitor the Comprehensive Nuclear Test Ban Treaty. To meet both the accuracy and performance requirements of operational monitoring systems, we use an approach which combines the error estimation of kriging with the speed and robustness of Natural Neighbor Interpolation. The method involves three basic steps: data preparation, data storage, and data access. In past presentations we have discussed in detail the first step. In this paper we focus on the latter two, describing in detail the type of information which must be stored and the interface used to retrieve parametric grid data from the Knowledge Base. Once data have been properly prepared, the information (tessellation and associated value surfaces) needed to support the interface functionality, can be entered into the KBase. The primary types of parametric grid data that must be stored include (1) generic header information; (2) base model, station, and phase names and associated ID's used to construct surface identifiers; (3) surface accounting information; (4) tessellation accounting information; (5) mesh data for each tessellation; (6) correction data defined for each surface at each node of the surfaces owning tessellation (7) mesh refinement calculation set-up and flag information; and (8) kriging calculation set-up and flag information. The eight data components not only represent the results of the data preparation process but also include all required input information for several population tools that would enable the complete regeneration of the data results if that should be necessary.
Date: August 3, 1999
Creator: Hipp, James R.; Simons, Randall W. & Young, Chris J.
Partner: UNT Libraries Government Documents Department