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

Fast unambiguous stereo matching using reliability-based dynamic programming.

Minglun Gong1, Yee-Hong Yang

  • 1Department of Mathematics and Computer Science, Laurentian University, Ramsey Lake Road, Sudbury, ON, Canada P3E 2C6. gong@cs.laurentian.ca

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 10, 2005
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

V-Sparse: From temporal-spatial visual semantic compression to coarse-to-fine interaction for text-video retrieval.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Learning to Recover Spectral Reflectance From RGB Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

Effects of MRI scanner manufacturers in classification tasks with deep learning models.

Scientific reports·2023
Same author

DSMRI: Domain Shift Analyzer for Multi-Center MRI Datasets.

Diagnostics (Basel, Switzerland)·2023
Same author

SF2Former: Amyotrophic lateral sclerosis identification from multi-center MRI data using spatial and frequency fusion transformer.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2023
Same author

Blind Image Deconvolution Using Variational Deep Image Prior.

IEEE transactions on pattern analysis and machine intelligence·2023
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a novel reliability measure for stereo vision, enhancing dynamic programming to achieve efficient and accurate disparity matching. The new method significantly improves dense matching accuracy with a low error rate.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Robotics

Background:

  • Stereo vision systems require accurate depth perception through disparity matching.
  • Existing dynamic programming methods for stereo matching can be computationally intensive and may lack robustness.
  • The reliability of pixel matches is crucial for the overall performance of stereo vision algorithms.

Purpose of the Study:

  • To introduce a new reliability measure for dynamic programming-based stereo matching.
  • To develop an efficient and unambiguous stereo matching technique.
  • To improve the accuracy and density of disparity maps in stereo vision applications.

Main Methods:

  • Introduced a novel reliability measure for stereo vision, defined as the cost difference between including and excluding a match.

Related Experiment Videos

  • Developed a reliability-based dynamic programming algorithm that selectively assigns disparities based on a threshold.
  • Evaluated the algorithm on the Middlebury stereo datasets for performance benchmarking.

    • Main Results:

    • Achieved dense disparity maps covering over 70% of unoccluded pixels.
    • Demonstrated high reliability with an error rate below 0.5%.
    • Showcased efficient performance, completing matches in under 0.2 seconds on a 2GHz P4 processor.

    Conclusions:

    • The proposed reliability measure enhances dynamic programming for stereo matching.
    • The novel approach offers an efficient, accurate, and dense solution for stereo vision.
    • This technique provides a significant advancement for real-time stereo vision applications.