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

Probabilistic 3D object recognition and pose estimation using multiple interpretations generation.

Zhaojin Lu1, Sukhan Lee

  • 1School of Information and Communication Engineering, Sungkyunkwan University, Seoul, South Korea.

Journal of the Optical Society of America. A, Optics, Image Science, and Vision
|December 24, 2011
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

Mechanistic insights into oil droplet detachment from fibers for optimizing oil-water separation coalescers.

Water research·2026
Same author

T-cadherin deprivation in endothelial cells promotes vascular injury in Kawasaki disease through SOD2/ROS/NLRP3 pathway-mediated pyroptosis.

Journal of molecular cell biology·2025
Same author

Sound Localization Training and Induced Brain Plasticity: An fMRI Investigation.

Diagnostics (Basel, Switzerland)·2025
Same author

LINC00461 SNPs rs933647 and rs201864123 modify the risk of adenoid hypertrophy susceptibility for children in South China.

Frontiers in genetics·2025
Same author

The Identification of FN1 as an Early Diagnostic Marker for Recurrent Abortion by Single-Exosome Profiling.

International journal of general medicine·2025
Same author

Fusion of multiple self-diagnostic questionnaires into optimal diagnostic cut-offs and factor analysis for depression characterization of the Korean university student group.

BMC psychiatry·2024
Same journal

Multi-module collaborative optimization-driven fast speckle correlation imaging in variable environments.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Secrecy performance analysis of NOMA-UWOC systems over a vertically stratified WGG oceanic turbulence channel.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Backscattering of plane waves in a composite system containing a rough surface and anisotropic scatterers.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Aspherical surface construction methods based on extended Jacobi polynomials.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

OCT sidelobe suppression method based on dual-path phase sinusoidal modulation and minimum value fusion.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same journal

Optical design concepts using wavelength-selective diffractive optics to enable miniaturized multimodal endoscopic imaging across separated spectral ranges.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
See all related articles

This study introduces a probabilistic method for object recognition and pose estimation in cluttered indoor settings. It addresses pose uncertainty by representing hypotheses as regions, improving accuracy in real-world environments.

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • Object recognition and pose estimation are challenging in cluttered environments due to ambiguity and uncertainty.
  • Existing methods often struggle with partial occlusion and fragmented data, leading to inaccurate pose estimations.

Purpose of the Study:

  • To develop a probabilistic method for object recognition and pose estimation that handles ambiguity and uncertainty.
  • To improve the accuracy and robustness of pose estimation in cluttered indoor environments.

Main Methods:

  • Generating pose hypotheses as regions in pose space from detected line pairs in stereo images and 3D point clouds.
  • Incorporating ambiguity from partial occlusion and fragmentation into pose interpretation.
  • Utilizing Bayesian principles with likelihood and unlikelihood for probabilistic verification of pose interpretations.

Related Experiment Videos

  • Applying a fusion strategy to refine top-ranked interpretations for real-time, accurate pose estimation.

    • Main Results:

    • The proposed method effectively handles pose ambiguity and uncertainty.
    • Probabilistic representation of pose interpretations as regions improves robustness.
    • Experimental results demonstrate high performance in real cluttered domestic environments.

    Conclusions:

    • The probabilistic approach with multiple interpretation generation offers a robust solution for object recognition and pose estimation.
    • The method shows significant potential for real-time applications in complex, real-world scenarios.