Using Ignorance in 3D Scene Understanding

Abstract EN

Awareness of its own limitations is a fundamental feature of the human sight, which has been almost completely omitted in computer vision systems.

In this paper we present a method of explicitly using information about perceptual limitations of a 3D vision system, such as occluded areas, limited field of view, loss of precision along with distance increase, and imperfect segmentation for a better understanding of the observed scene.

The proposed mechanism integrates metric and semantic inference using Dempster-Shafer theory, which makes it possible to handle observations that have different degrees and kinds of uncertainty.

The system has been implemented and tested in a real indoor environment, showing the benefits of the proposed approach.