Search research articles

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

Related Concept Videos

Sight Distance in a Vertical Curve

Sight Distance in a Vertical Curve

Sight distance on vertical curves is critical in roadway design. It ensures drivers can see far enough ahead to identify and respond to hazards effectively. This directly impacts safety, driver comfort, and the overall efficiency of the transportation network.Vertical curves are classified into crest and sag curves based on their geometry. For crest curves, sight distance is determined by the line of sight between a driver's eye and a small object on the road's surface. Design parameters for...

You might also read

Related Articles

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

Sort by

Same author

Study on a risk model for prediction and avoidance of unmanned environmental hazard.

Scientific reports·2022

Same author

mi R -15a/15b Cluster Modulates Survival of Mesenchymal Stem Cells to Improve Its Therapeutic Efficacy of Myocardial Infarction.

Journal of the American Heart Association·2019

Same author

Retrospective analysis of Clostridium difficile infection in patients with ulcerative colitis in a tertiary hospital in China.

BMC gastroenterology·2019

Same author

CCCH-type zinc finger antiviral protein is specifically overexpressed in spleen in response to subgroup J avian leukosis virus infection in chicken.

Research in veterinary science·2018

Same author

Mapping Twisted Light into and out of a Photonic Chip.

Physical review letters·2018

Same author

Dynamic community structure in major depressive disorder: A resting-state MEG study.

Progress in neuro-psychopharmacology & biological psychiatry·2018

Search research articles

Related Experiment Video

Updated: Jun 25, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles.

Chengqun Qiu^1,2, Hao Tang¹, Yuchen Yang²

¹School of Automotive Engineering, Yancheng Institute of Technology, Yancheng, 224051, China.

Scientific Reports

|May 28, 2024

Summary

This study enhances autonomous driving safety by optimizing YOLOv5s for small target detection. The improved algorithm ensures more stable vehicle control and robust visual avoidance, addressing traffic congestion and personal safety concerns.

Keywords:

Control algorithm Deep learning Machine vision Risk avoidance Self-Driving YOLOv5s

More Related Videos

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Published on: September 18, 2012

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

Related Experiment Videos

Last Updated: Jun 25, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Driving Simulation in the Clinic: Testing Visual Exploratory Behavior in Daily Life Activities in Patients with Visual Field Defects

Published on: September 18, 2012

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

Area of Science:

Computer Vision
Deep Learning
Autonomous Driving Systems

Background:

Traffic congestion and personal safety are critical issues.
Autonomous driving systems require advanced perception for complex navigation.
Deep learning significantly improves machine vision in autonomous vehicles.

Purpose of the Study:

To address limitations in small target detection within traditional YOLOv5s algorithms.
To enhance the accuracy and efficiency of object detection for autonomous driving.
To improve the overall safety and performance of autonomous driving systems.

Main Methods:

An optimized target detection algorithm was proposed, upgrading the C3 module to CBAMC3.
Integration of a novel GELU activation function and EfficiCIoU loss function.
Testing involved a vehicle-mounted camera and analysis of depth position information.

Main Results:

The optimized algorithm demonstrated accelerated convergence for position, confidence, and classification losses.
Enhanced image learning capabilities and improved detection of small targets were achieved.
The avoidance model, using Pure Pursuit and MPC, showed more stable vehicle dynamics (speed, steering angle, lateral acceleration).

Conclusions:

The enhanced YOLOv5s algorithm improves the robustness of autonomous driving visual avoidance.
The study contributes to mitigating traffic congestion and enhancing personal safety through advanced autonomous driving technology.