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 Experiment Videos

Stable real-time 3D tracking using online and offline information.

Luca Vacchetti1, Vincent Lepetit, Pascal Fua

  • 1Computer Vision Lab, Swiss Federal Institute of Technology, 1015 Lausanne, Switzerland. luca.vacchetti@epfl.ch

IEEE Transactions on Pattern Analysis and Machine Intelligence
|January 12, 2005
PubMed
Summary

This study introduces a robust real-time 3D object tracking system using a single camera. The novel approach overcomes limitations of existing methods, preventing jitter and drift for reliable tracking.

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

Two Projections Suffice for Cerebral Vascular Reconstruction.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2025
Same author

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT.

Communications medicine·2025
Same author

<i>MedShapeNet</i> - a large-scale dataset of 3D medical shapes for computer vision.

Biomedizinische Technik. Biomedical engineering·2024
Same author

Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields.

Medical image analysis·2024
Same author

Author Correction: BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets.

Nature methods·2024

Area of Science:

  • Computer Vision
  • Robotics
  • 3D Reconstruction

Background:

  • Robust online 3D object tracking with a single camera is challenging due to large displacements, aspect changes, and occlusions.
  • Existing real-time algorithms often lack robustness, leading to drift and jitter.

Purpose of the Study:

  • To develop an efficient and robust real-time 3D tracking solution for rigid objects using a single camera.
  • To address the limitations of current online tracking methods.

Main Methods:

  • Formulated the tracking problem using local bundle adjustment.
  • Developed a novel image correspondence method for both short and wide-baseline matching.
  • Merged information from preceding frames with keyframes from a training stage.

Related Experiment Videos

Main Results:

  • Achieved real-time tracking without jitter or drift.
  • Successfully handled large camera displacements, drastic aspect changes, and partial occlusions.
  • Demonstrated robustness in challenging tracking scenarios.

Conclusions:

  • The proposed method provides an efficient and robust solution for real-time 3D object tracking.
  • The technique effectively overcomes common issues like drift and jitter in single-camera tracking systems.