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

Robust ego-motion estimation and 3-D model refinement using surface parallax.

Amit Agrawal1, Rama Chellappa

  • 1Center for Automation Research, University of Maryland, College Park, MD 20742, USA. aagrawal@cfar.umd.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|May 5, 2006
PubMed
Summary
This summary is machine-generated.

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

Letter to the Editor Regarding "Creating a Comprehensive Research Platform for Surgical Technique and Operative Outcome in Primary Brain Tumor Neurosurgery".

World neurosurgery·2020
Same author

Letter to the Editor Regarding 'Stepping Up: How U.S. Neurosurgery Training Programs Can Innovatively Assess Resident Applicants in a Post-Step 1 World'.

World neurosurgery·2020
Same author

Letter to the Editor: Home Program for Acquisition and Maintenance of Microsurgical Skills During the COVID-19 Outbreak.

World neurosurgery·2020
Same author

Letter to the Editor Regarding: "Coronavirus Neurosurgical/Head and Neck Drape to Prevent Aerosolization of Coronavirus Disease 2019 (COVID-19): The Lenox Hill Hospital/Northwell Health Solution".

World neurosurgery·2020
Same author

Letter to the Editor Regarding"Surgical Outcomes of Laser Interstitial Thermal Therapy for Temporal Lobe Epilepsy".

World neurosurgery·2020
Same author

Letter to the Editor Regarding: "Case Volumes and Perioperative COVID-19 Incidence in Neurosurgical Patients During a Pandemic: Experiences at Two Tertiary Care Centers in Washington, DC".

World neurosurgery·2020
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces an iterative algorithm for robust ego-motion estimation and depth map refinement using parametric surface parallax and brightness derivatives. The method improves accuracy by combining motion constraints and confidence measures for reliable 3-D scene reconstruction.

Area of Science:

  • Computer Vision
  • Robotics
  • Photogrammetry

Background:

  • Accurate ego-motion estimation and depth map generation are crucial for autonomous systems.
  • Existing methods often struggle with robustness and accuracy, especially with limited initial data.

Purpose of the Study:

  • To develop an iterative algorithm for robust ego-motion estimation.
  • To refine and update coarse depth maps using parametric surface parallax models.
  • To enhance 3-D scene reconstruction accuracy from image pairs.

Main Methods:

  • Iterative algorithm combining global ego-motion and local brightness constancy constraints.
  • Utilizing parametric surface parallax models (CPM and DBPM) for depth map refinement.
  • Employing confidence measures to remove erroneous depth estimates for robust iterative updates.

Related Experiment Videos

Main Results:

  • Successfully estimated ego-motion and refined depth maps using synthetic and real-world data.
  • Demonstrated robustness in both indoor and outdoor image sequences.
  • Validated the effectiveness of confidence measures in improving iterative estimations.

Conclusions:

  • The proposed iterative algorithm provides a robust solution for ego-motion estimation and depth map refinement.
  • The integration of parallax models and confidence measures leads to improved 3-D scene understanding.
  • The algorithm shows significant potential for applications in robotics and augmented reality.