Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A 3-Year Split-Mouth Randomized Controlled Clinical Trial of Zirconia and Titanium Implant-Supported Overdentures.

Journal of functional biomaterials·2026
Same author

A Prospective, International, Multicentre Registry of Patients Undergoing Segmental Mandibular Defect Reconstruction After Mandibular Resection for Tumours and Drug-Induced Osteonecrosis: A Study Protocol.

Craniomaxillofacial trauma & reconstruction·2026
Same author

The Impact of Early Postoperative Oral Intake on the Length of Hospital Stay: A Meta-Analysis.

Acta anaesthesiologica Scandinavica·2026
Same author

In Vivo Micro-Computed Tomography for Evaluation of Osteogenic Capability of Dental Pulp Stem Cells Under the Influence of Extracellular Vesicles on Alloplastic and Xenogeneic Bone Scaffolds in Rodent Intrabony Defect Model.

Life (Basel, Switzerland)·2025
Same author

The reliability of remote photoplethysmography under low illumination and elevated heart rates.

NPJ digital medicine·2025
Same author

Connected, digitalized wire arc additive manufacturing: utilizing data in the internet of production to enable industrie 4.0.

Scientific reports·2025

Related Experiment Video

Updated: Nov 10, 2025

A Protocol for Real-time 3D Single Particle Tracking
10:16

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

15.1K

Efficient Reject Options for Particle Filter Object Tracking in Medical Applications.

Johannes Kummert1, Alexander Schulz1, Tim Redick2

  • 1Machine Learning Group, Bielefeld University, 33619 Bielefeld, Germany.

Sensors (Basel, Switzerland)
|April 3, 2021
PubMed
Summary

Simple likelihood thresholds fail for reliable object tracking in surgery. Machine learning models, particularly ensembles of classifiers, offer a flexible and accurate solution for determining if tracking has been lost during robotic osteotomies.

Keywords:
assisted surgeryparticle filteringreject optionsecure object tracking

More Related Videos

Tracking Mouse Bone Marrow Monocytes In Vivo
12:08

Tracking Mouse Bone Marrow Monocytes In Vivo

Published on: February 27, 2015

9.8K
High-resolution Spatiotemporal Analysis of Receptor Dynamics by Single-molecule Fluorescence Microscopy
15:13

High-resolution Spatiotemporal Analysis of Receptor Dynamics by Single-molecule Fluorescence Microscopy

Published on: July 25, 2014

11.6K

Related Experiment Videos

Last Updated: Nov 10, 2025

A Protocol for Real-time 3D Single Particle Tracking
10:16

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

15.1K
Tracking Mouse Bone Marrow Monocytes In Vivo
12:08

Tracking Mouse Bone Marrow Monocytes In Vivo

Published on: February 27, 2015

9.8K
High-resolution Spatiotemporal Analysis of Receptor Dynamics by Single-molecule Fluorescence Microscopy
15:13

High-resolution Spatiotemporal Analysis of Receptor Dynamics by Single-molecule Fluorescence Microscopy

Published on: July 25, 2014

11.6K

Area of Science:

  • Computer Vision
  • Robotics
  • Medical Technology

Background:

  • Object tracking using video data is crucial for applications like assisted surgery.
  • Particle filtering is a state-of-the-art probabilistic method for object tracking.
  • Likelihood values from particle filters theoretically indicate tracking reliability.

Purpose of the Study:

  • To evaluate the suitability of particle filter likelihood values for detecting lost object tracking.
  • To assess the effectiveness of a simple threshold strategy for rejecting unreliable tracking.
  • To develop robust machine learning models for reliable object tracking in challenging environments.

Main Methods:

  • Investigated the use of particle filter likelihood values to determine if an object has been lost.
  • Applied a simple threshold strategy to reject low-likelihood tracking scenarios.
  • Developed and evaluated machine learning models (regression and ensemble classification) using particle filter outputs.
  • Tested methods in the medical domain, specifically object tracking in robotic osteotomies.

Main Results:

  • A simple threshold strategy based on likelihood values is unreliable for detecting lost object tracking, especially across different settings.
  • Machine learning models, utilizing diverse quantities from particle filters, can reliably predict tracking loss.
  • Ensemble classification models demonstrated superior performance compared to regression models while maintaining flexibility.

Conclusions:

  • Directly using particle filter likelihood values with a simple threshold is insufficient for reliable object tracking loss detection in surgical applications.
  • Machine learning approaches, particularly ensemble classification, provide a flexible and accurate method for enhancing the reliability of object tracking in robotic surgery.
  • Advanced computational methods are necessary to overcome the limitations of basic probabilistic indicators in complex tracking scenarios.