Search research articles

Search research articles

Related Experiment Video

Updated: Jun 28, 2026

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

Published on: September 21, 2017

Helmet detection in traffic scenarios: enhanced performance for complex environments.

Hua Hou¹, Tianxiang Tan², Diancheng Wang²

¹School of Information and Electrical Engineering, Hebei University of Engineering, Handan, 056038, China. houhua@hebeu.edu.cn.

Scientific Reports

|June 26, 2026

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 author

Excellent Thermal Stability and Environmental Sustainability of Trifluorodimethyl Sulfide as a Potential Alternative Refrigerant.

The journal of physical chemistry. A·2026

Same author

Comprehensive analysis of brain tissue transcriptome and serum miRNA reveals molecular signatures of cognitive impairment after traumatic brain injury.

Brain research·2026

Same author

Investigation of the Mechanism of Action of <i>Liu Miao San</i> in the Treatment of Lipid Metabolism Disorders on the basis of Network Analysis and Dynamic Ultrasound.

Endocrine, metabolic & immune disorders drug targets·2026

Same author

The Synergism of β-Cyclodextrin and Fe<sup>3+</sup> Enabled Anti-Swelling Ion-Conductive Hydrogels for Multimodal Underwater Sensing Aided by Machine Learning Algorithms.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Potential role of stabilized criegee intermediates in the reactivity of isocyanic acid.

Communications chemistry·2026

Same author

Fusion of multi-scale geometric features and frequency domain decomposition for stereo matching network.

PloS one·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces an improved YOLOv10n object detection algorithm that enhances accuracy and efficiency. The new model excels in detecting occluded targets and small objects, making it ideal for real-time applications.

Area of Science:

Computer Vision
Deep Learning
Object Detection

Background:

Object detection systems face challenges with missed detections due to target occlusion and high computational costs.
Existing models struggle with real-world deployment due to these limitations.

Purpose of the Study:

To develop an improved YOLOv10n-based algorithm addressing missed detections and computational costs.
To enhance object detection accuracy and efficiency in complex scenarios.

Main Methods:

Introduced Adaptive-DySample (ADS) for dynamic alignment, challenging sample prioritization, and multi-scale fusion.
Developed C2fCIB-Fusion (C2fCIB-F) integrating multi-scale/dynamic channel optimization, Spatial-Channel Interaction, RepVGGDW, and residual connections.
Implemented Gated Multi-Scale Fusion Convolution (GMFConv) for enhanced small object detection and lightweight design.

Keywords:

ADS C2fCIB-F GMFConv Helmet Detection YOLOv10n

Related Experiment Videos

Last Updated: Jun 28, 2026

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

Published on: September 21, 2017

Main Results:

Achieved a 2.4% higher mAP@0.5 and 5.1% better parameter efficiency compared to the original model.
Significantly improved helmet detection accuracy in complex environments.
Maintained real-time performance with a lightweight design suitable for edge computing.

Conclusions:

The improved YOLOv10n algorithm effectively overcomes limitations of traditional object detection methods.
The model demonstrates suitability for safety monitoring and edge computing applications requiring robust and efficient object detection.