Probabilistic Depth Image Registration incorporating Nonvisual Information

TL;DR

This paper introduces a novel probabilistic registration algorithm for object modeling and tracking that combines visual and nonvisual information within a Bayesian framework, providing a posterior distribution over object alignment.

Contribution

It presents the first Bayesian registration method that integrates visual and nonvisual data, considering observed non-object space and computing a full posterior distribution.

Findings

Outperforms traditional ICP and feature mapping in experiments

Effectively incorporates nonvisual information for improved accuracy

Provides a probabilistic estimate of object pose rather than a single point estimate

Abstract

In this paper, we derive a probabilistic registration algorithm for object modeling and tracking. In many robotics applications, such as manipulation tasks, nonvisual information about the movement of the object is available, which we will combine with the visual information. Furthermore we do not only consider observations of the object, but we also take space into account which has been observed to not be part of the object. Furthermore we are computing a posterior distribution over the relative alignment and not a point estimate as typically done in for example Iterative Closest Point (ICP). To our knowledge no existing algorithm meets these three conditions and we thus derive a novel registration algorithm in a Bayesian framework. Experimental results suggest that the proposed methods perform favorably in comparison to PCL implementations of feature mapping and ICP, especially if nonvisual information is available.