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: Apr 27, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.4K

Domain adaptation for pedestrian detection based on prediction consistency.

Yu Li-ping1, Tang Huan-ling2, An Zhi-yong3

  • 1Key Laboratory of Intelligent Information Processing, Universities of Shandong (Shandong Institute of Business and Technology), Yantai 264005, China ; School of Computer Science and Technology, Shandong Institute of Business and Technology, Yantai 264005, China.

Thescientificworldjournal
|July 12, 2014
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Enhancing Environmental Performance for Green Building Projects: Assessment Study due to the Applicability of Industry 4.0 Technologies.

TheScientificWorldJournal·2026
Same journal

Ethnobotanical Survey of Medicinal Plants Utilized by Traditional Healers in Managing Respiratory Tract Infections in the Kagera Region, Tanzania.

TheScientificWorldJournal·2026
Same journal

Solvent Extraction of Metals in the Circular Economy: Enhancing Resource Efficiency and Sustainability.

TheScientificWorldJournal·2026
Same journal

Agronomic Performance and Nutritive Value Evaluation of Desho Grass Varieties Under Supplementary Irrigation in Western Oromia, Ethiopia.

TheScientificWorldJournal·2026
Same journal

Physicians' and Hospital Administrators' Perspectives of Diagnosis-Related Groups (DRGs) in High-Income Countries: A Systematic Review.

TheScientificWorldJournal·2026
Same journal

The Eco-Friendly Preparation of Se, Zn, and Ag MONPs and Their Current Medical Applications and Drug Delivery for AD Diseases.

TheScientificWorldJournal·2026

This study introduces a novel domain adaptation model to improve pedestrian detection. The method effectively merges source and target data, enhancing performance even with limited target scene data.

Area of Science:

  • Computer Vision
  • Machine Learning

Background:

  • Pedestrian detection is crucial for many applications but faces challenges due to domain mismatch between training data and real-world scenes.
  • Existing methods struggle when target domain data is scarce, limiting the generalizability of pedestrian detectors.

Purpose of the Study:

  • To develop a novel domain adaptation model for pedestrian detection that addresses the challenge of limited labeled data in the target scene.
  • To create a scene-specific pedestrian detector by effectively merging abundant source domain data with scarce target domain data.

Main Methods:

  • The proposed approach combines a boosting-based learning algorithm with an entropy-based transferability measure.
  • Transferability is derived from prediction consistency with source classifications to selectively identify useful source domain samples.

More Related Videos

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.1K

Related Experiment Videos

Last Updated: Apr 27, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.4K
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.1K
  • This enables the model to adapt a detector trained on a large source dataset to a specific target scene with limited data.

    • Main Results:

    • The domain adaptation model significantly improves pedestrian detection rates, particularly in scenarios with insufficient labeled target data.
    • Experimental results demonstrate the effectiveness of merging source and target domain samples for scene-specific detector performance.
    • The approach successfully enhances detection performance compared to methods relying solely on limited target data.

    Conclusions:

    • The novel domain adaptation model offers a robust solution for improving pedestrian detection in challenging, data-scarce target environments.
    • Selective sample transferability is key to adapting general models to specific scenes effectively.
    • This research contributes to more reliable and accurate pedestrian detection systems in real-world applications.