Bingham Procrustean Alignment for Object Detection in Clutter

TL;DR

The paper introduces Bingham Procrustean Alignment (BPA), a probabilistic method for aligning models with cluttered RGB-D scenes, improving object detection reliability by modeling pose uncertainty with Bingham distributions.

Contribution

It presents BPA, a novel probabilistic alignment technique using Bingham distributions for orientation, enhancing object detection in cluttered environments.

Findings

BPA models pose uncertainty effectively.

Improved object detection accuracy in cluttered scenes.

Probabilistic framework for rigid alignment.

Abstract

A new system for object detection in cluttered RGB-D images is presented. Our main contribution is a new method called Bingham Procrustean Alignment (BPA) to align models with the scene. BPA uses point correspondences between oriented features to derive a probability distribution over possible model poses. The orientation component of this distribution, conditioned on the position, is shown to be a Bingham distribution. This result also applies to the classic problem of least-squares alignment of point sets, when point features are orientation-less, and gives a principled, probabilistic way to measure pose uncertainty in the rigid alignment problem. Our detection system leverages BPA to achieve more reliable object detections in clutter.