Artículos relacionados a Robotics Research Technical Report: Two Dimensional...

Robotics Research Technical Report: Two Dimensional Model Based Boundary Matching Using Footprints (Classic Reprint) - Tapa blanda

Kalvin, Alan

 
9781332207534: Robotics Research Technical Report: Two Dimensional Model Based Boundary Matching Using Footprints (Classic Reprint)

Sinopsis

Excerpt from Robotics Research Technical Report: Two Dimensional Model Based Boundary Matching Using Footprints

A technique for geometrically hashing two-dimensional model objects is described. Used in conjunction with other methods for recognizing partially obscured and overlapping objects, this technique, which is based on use of an artificially generated attribute of an object called its footprint, enables us to recognize overlapping 2-dimensional objects selected from large databases of model objects without significant performance degradation. Experimental results from databases of size 48 and 100 are presented.

About the Publisher

Forgotten Books publishes hundreds of thousands of rare and classic books. Find more at www.forgottenbooks.com

This book is a reproduction of an important historical work. Forgotten Books uses state-of-the-art technology to digitally reconstruct the work, preserving the original format whilst repairing imperfections present in the aged copy. In rare cases, an imperfection in the original, such as a blemish or missing page, may be replicated in our edition. We do, however, repair the vast majority of imperfections successfully; any imperfections that remain are intentionally left to preserve the state of such historical works.

"Sinopsis" puede pertenecer a otra edición de este libro.

Reseña del editor

Excerpt from Robotics Research Technical Report: Two Dimensional Model Based Boundary Matching Using Footprints

A technique for geometrically hashing two-dimensional model objects is described. Used in conjunction with other methods for recognizing partially obscured and overlapping objects, this technique, which is based on use of an artificially generated attribute of an object called its footprint, enables us to recognize overlapping 2-dimensional objects selected from large databases of model objects without significant performance degradation. Experimental results from databases of size 48 and 100 are presented.

1. Introduction

The goal of model-based object recognition is to identify a given object as one of a collection of known model objects. In complicated versions of this problem, the object to be recognized may be partially occluded, or several objects to be identified may overlap. Techniques for solving these object recognition problems in the 2-dimensional case are presented in [9]. The recognition algorithm described there works by matching, i.e. identifies an object by matching all model objects against the boundary curve of the given object and choosing the best match. Therefore as the database of model objects grows large, the performance of that algorithm degrades linearly.

This report describes a technique that can be used to radically reduce the number of models used by the matching algorithm; that is, given a large list of models and an object O to be identified, we are able to obtain a small set of candidate models that potentially can match O. This technique, which is based on geometric hashing, is sublinear in the number of models so that we are able to work effectively with a large database of models. The object attribute that we form for purposes of hashing will be called a footprint.

About the Publisher

Forgotten Books publishes hundreds of thousands of rare and classic books. Find more at www.forgottenbooks.com

This book is a reproduction of an important historical work. Forgotten Books uses state-of-the-art technology to digitally reconstruct the work, preserving the original format whilst repairing imperfections present in the aged copy. In rare cases, an imperfection in the original, such as a blemish or missing page, may be replicated in our edition. We do, however, repair the vast majority of imperfections successfully; any imperfections that remain are intentionally left to preserve the state of such historical works.

"Sobre este título" puede pertenecer a otra edición de este libro.