Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

1 Machine Graphics and Vision

1 2000

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

View invariant object recognition using coloured receptive fields

100%

Hall D. , Crowley J. L. , de Verdiere V. C.

Machine Graphics and Vision

2000

tom Vol. 9, No. 1/2

341-352

This paper decribes a technique for the recognition and tracking of every day objects. The goal is to build a system in which orinary desktop objects serve as physical icons in a vision based system for man-machine interaction. In such a system, the manipulation of objects replaces user commands. This method is based on sampling a local appearance function at discrete viewpoints by projecting it conto a vector of receptive fields which have been normalised to local scale and orientation. This paper reports on the experimental validation of the approach, and of its extension to the use receptive fields based on colour. The experimental results indicate that the technique does indeed provide a method for building a fast and robust recognition technique. Furthermore, the extension to coloured receptive fields provides a greater degree of local discrimination. The coloured receptive field approach is aplied to the recognition of objects under changing view points. Appearance of objects depends strongly on the view point and the lighting. In the experiments we show that the developed technique based on coloured receptive fields allows the recognition of objects invariant from the view point of the camera. This is obtained by training images from view points that sample the view sphare. this experiment shows that the approach is suitable for the recognition of general objects as physical icons in an augmentad reality.