Extended Gaussian images

TLDR

Extended Gaussian images provide a compact representation of surface shapes and can be derived directly from geometric models. The paper defines extended Gaussian images and explores their use for object recognition and attitude estimation in machine vision. Extended Gaussian images are computed from needle maps via photometric stereo or from depth maps produced by ranging devices or binocular stereo. The authors extend the method to nonconvex objects and illustrate it with several examples.

Abstract

This is a primer on extended Gaussian images. Extended Gaussian images are useful for representing the shapes of surfaces. They can be computed easily from: 1. needle maps obtained using photometric stereo; or 2. depth maps generated by ranging devices or binocular stereo. Importantly, they can also be determined simply from geometric models of the objects. Extended Gaussian images can be of use in at least two of the tasks facing a machine vision system: 1. recognition, and 2. determining the attitude in space of an object. Here, the extended Gaussian image is defined and some of its properties discussed. An elaboration for nonconvex objects is presented and several examples are shown.