Learning Effective Sparse Sampling Strategies using Deep Active Sensing

Mehdi Patrick Stapleton, Dieter Schmalstieg, Clemens Arth, Thomas Gloor

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Registering a known model with noisy sample measurements is in general a difficult task due to the problem in finding correspondences between the samples and points on the known model. General frameworks exist, such as variants of the classical iterative closest point (ICP) method to iteratively refine correspondence estimates. However, the methods are prone to getting trapped in locally optimal configurations, which may be far from the true registration. The quality of the final registration depends strongly on the set of samples. The quality of the set of sample measurements is more noticeable when the number of samples is relatively low (≈ 20). We consider sample selection in the context of active perception, i.e. an objective-driven decision-making process, to motivate our research and the construction of our system. We design a system for learning how to select the regions of the scene to sample, and, in doing so, improve the accuracy and efficiency of the sampling process. We present a full environment for learning how best to sample a scene in order to quickly and accurately register a model with the scene. This work has broad applicability from the fields of geodesy to medical robotics, where the cost of taking a measurement is much higher than the cost of incremental changes to the pose of the equipment.

Original languageEnglish
Title of host publicationVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsGiovanni Maria Farinella, Petia Radeva, Jose Braz
PublisherSciTePress
Pages835-846
Number of pages12
Volume4
ISBN (Electronic)9789897584022
DOIs
Publication statusPublished - Feb 2020
Event15th International Conference on Computer Vision Theory and Applications: VISAPP 2020 - Grand Hotel Excelsior, Valetta, Malta
Duration: 27 Feb 202029 Feb 2020
http://www.visapp.visigrapp.org/
https://www.insticc.org/node/technicalprogram/visigrapp/2020

Conference

Conference15th International Conference on Computer Vision Theory and Applications
Abbreviated titleVISAPP 2020
CountryMalta
CityValetta
Period27/02/2029/02/20
Internet address

Keywords

  • Active Localization
  • Active Perception
  • General Hough Transform
  • Sparse Registration

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Learning Effective Sparse Sampling Strategies using Deep Active Sensing'. Together they form a unique fingerprint.

Cite this