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

A Hybrid Shared-Memory Parallel Max-Tree Algorithm for Extreme Dynamic-Range Images.

Ugo Moschini, Arnold Meijster, Michael H F Wilkinson

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 4, 2017
    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

    A Shared-Memory Parallel Alpha-Tree Algorithm for Extreme Dynamic Ranges.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    Evaluation of Alpha-Trees for Hierarchical Segmentation by Horizontal Cuts.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    Understanding the provenance and quality of methods is essential for responsible reuse of FAIR data.

    Nature medicine·2024
    Same author

    Stripe noise removal in conductive atomic force microscopy.

    Scientific reports·2024
    Same author

    A Fast Alpha-Tree Algorithm for Extreme Dynamic Range Pixel Dissimilarities.

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

    Community consensus on core open science practices to monitor in biomedicine.

    PLoS biology·2023
    Same journal

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

    Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

    Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

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

    We developed a novel parallel algorithm for constructing max-trees (component trees) from high bit-depth images. This method significantly improves performance over existing parallel approaches, achieving speed-ups on 64 threads.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Graph Theory

    Background:

    • Max-trees (component trees) hierarchically represent image connected components.
    • High-dynamic range and floating-point images are increasingly common.
    • Existing sequential algorithms efficiently build max-trees for any bit depth.

    Purpose of the Study:

    • To address the poor performance of current parallel max-tree algorithms on high bit-depth images (>16 bits).
    • To propose an efficient parallel method for constructing max-trees from high bit-depth images.

    Main Methods:

    • A hybrid parallel approach combining flooding and merging max-tree algorithms.
    • Building a pilot max-tree on a quantized image using a parallel flooding method.
    • Utilizing the pilot tree for a parallel leaf-to-root computation and sub-tree merging.

    Related Experiment Videos

    Main Results:

    • The proposed parallel method shows improved performance compared to sequential algorithms.
    • Significant speed-ups were observed, reaching up to X on 64 threads for 2D and 3D image data.
    • The algorithm effectively handles high bit-depth images.

    Conclusions:

    • The novel parallel max-tree algorithm overcomes limitations of existing methods for high bit-depth images.
    • This approach offers efficient and scalable construction of component trees for advanced image analysis.
    • The method demonstrates practical efficiency on both simulated and real-world 2D/3D image datasets.