Edinburgh Research Explorer

DUGMA: Dynamic Uncertainty-Based Gaussian Mixture Alignment

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://ieeexplore.ieee.org/document/8491030
Original languageEnglish
Title of host publicationProceedings International Conference on 3D Vision 2018
Subtitle of host publicationVerona, Italy, 5-8 September 2018
Place of PublicationVerona, Italy
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages766-774
Number of pages9
ISBN (Electronic)978-1-5386-8425-2
ISBN (Print)978-1-5386-8426-9
DOIs
Publication statusPublished - 15 Oct 2018
Event6th International Conference on 3D Vision 2018 - Verona, Italy
Duration: 5 Sep 20188 Sep 2018
http://3dv18.uniud.it/index.html

Conference

Conference6th International Conference on 3D Vision 2018
Abbreviated title3DV 2018
CountryItaly
CityVerona
Period5/09/188/09/18
Internet address

Abstract

Accurately registering point clouds from a cheap low-resolution sensor is a challenging task. Existing rigid registration methods
failed to use the physical 3D uncertainty distribution of each point from a real sensor in the dynamic alignment process. It is mainly because the uncertainty model for a point is static and invariant and it is hard to describe the change of these physical uncertainty models in different views. Additionally, the existing Gaussian mixture alignment architecture cannot efficiently implement these dynamic changes.

This paper proposes a simple architecture combining error estimation from sample covariances and dynamic global probability
alignment using the convolution of uncertainty-based Gaussian Mixture Models (GMM). Firstly, we propose an efficient way to describe the change of each 3D uncertainty model, which represents the structure of the point cloud better. Unlike the invariant GMM (representing a fixed point cloud) in traditional Gaussian mixture alignment, we use two uncertainty-based GMMs that change and interact with each other in each iteration. In order to have a wider basin of convergence than other local algorithms, we design a more robust energy function by convolving efficiently the two GMMs over the whole 3D space.

Tens of thousands of trials have been conducted on hundreds of models from multiple datasets to demonstrate the proposed method’s superior performance compared with the current state-of-the-art methods. All the materials including our code are
available from https://github.com/Canpu999/DUGMA.

Event

6th International Conference on 3D Vision 2018

5/09/188/09/18

Verona, Italy

Event: Conference

Download statistics

No data available

ID: 69747492