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 Video

Updated: May 8, 2026

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine
08:27

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Published on: January 5, 2024

A speed-up scheme based on multiple-instance pruning for pedestrian detection using a support vector machine.

Jaehoon Yu, Ryusuke Miyamoto, Takao Onoye

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |August 20, 2013
    PubMed
    Summary

    This study introduces a novel speed-up scheme for pedestrian detection using multiple-instance pruning (MIP) with support vector machine (SVM) classifiers. The method significantly enhances processing speed without compromising detection accuracy.

    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

    Hinged amphipathic peptides with pH-inducible positive charges: A selective battering ram against bacterial outer membrane in infection sites.

    Biomaterials·2025
    Same author

    Author Correction: An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring.

    Scientific reports·2025
    Same author

    An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring.

    Scientific reports·2024
    Same author

    <i>De Novo</i> Designed Cell-Penetrating Peptide Self-Assembly Featuring Distinctive Tertiary Structure.

    ACS omega·2024
    Same author

    Computer-Vision-Oriented Adaptive Sampling in Compressive Sensing.

    Sensors (Basel, Switzerland)·2024
    Same author

    Proline-Hinged α-Helical Peptides Sensitize Gram-Positive Antibiotics, Expanding Their Physicochemical Properties to Be Used as Gram-Negative Antibiotics.

    Journal of medicinal chemistry·2023

    Area of Science:

    • Computer Vision
    • Machine Learning

    Background:

    • Sophisticated feature descriptors improve pedestrian detection accuracy but reduce processing speed.
    • Support Vector Machine (SVM) classifiers are commonly used but can be computationally intensive.

    Purpose of the Study:

    • To propose a novel speed-up scheme for SVM classifiers in pedestrian detection.
    • To enhance the processing speed of pedestrian detection systems without sacrificing accuracy.

    Main Methods:

    • A novel speed-up scheme based on multiple-instance pruning (MIP), a soft cascade method, is proposed.
    • The SVM classifier is split into multiple parts, forming a cascade structure.
    • The cascade structure is rearranged for improved rejection rates, and rejection thresholds are trained using MIP.

    Related Experiment Videos

    Last Updated: May 8, 2026

    Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine
    08:27

    Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

    Published on: January 5, 2024

    Main Results:

    • The proposed scheme was applied to a pedestrian classifier using co-occurrence histograms of oriented gradients (HOG) trained by an SVM.
    • Experimental results demonstrated a significant reduction in classification processing time, achieving speeds up to one-hundredth of the original classifier.
    • Detection accuracy was maintained without sacrifice.

    Conclusions:

    • The proposed multiple-instance pruning (MIP) based speed-up scheme effectively enhances the processing speed of SVM classifiers for pedestrian detection.
    • This method offers a viable solution for real-time pedestrian detection systems where both speed and accuracy are critical.