Localization and homing using combinations of model views

摘要

Navigation involves recognizing the environment, identifying the current position within the environment, and reaching particular positions. We present a method for localization (the act of recognizing the environment), positioning (the act of computing the exact coordinates of a robot in the environment), and homing (the act of returning to a previously visited position) from visual input. The method is based on representing the scene as a set of 2D views and predicting the appearances of novel views by linear combinations of the model views. The method accurately approximates the appearance of scenes under weak-perspective projection. Analysis of this projection as well as experimental results demonstrate that in many cases this approximation is sufficient to accurately describe the scene. When weak-perspective approximation is invalid, either a larger number of models can be acquired or an iterative solution to account for the perspective distortions can be employed.