Showing papers by "David G. Lowe published in 1991"
TL;DR: Current methods of parameter solving are extended to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulation, variable dimensions, or surface deformations to allow model-based vision to be used for a much wider class of problems than was possible with previous methods.
Abstract: Model-based recognition and motion tracking depend upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. The author extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulation, variable dimensions, or surface deformations. Numerical stabilization methods are developed that take account of inherent inaccuracies in the image measurements and allow useful solutions to be determined even when there are fewer matches than unknown parameters. The Levenberg-Marquardt method is used to always ensure convergence of the solution. These techniques allow model-based vision to be used for a much wider class of problems than was possible with previous methods. Their application is demonstrated for tracking the motion of curved, parameterized objects. >
1,000 citations
18 Nov 1991
TL;DR: The authors describe experiments in which the rescaling back-propagation learning algorithm was used to learn sets of linear filters for the task of determining the orientation and location of edges to subpixel accuracy.
Abstract: The authors describe experiments in which the rescaling back-propagation learning algorithm was used to learn sets of linear filters for the task of determining the orientation and location of edges to subpixel accuracy. A model of edge formation was used to generate input-output pairs for each iteration of the training process. The desired output included determining the interpolated location and orientation of the edge. >