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 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 High-Performance Si-Based Photocathode Enhanced by Spatial Confinement Strategy for Photoelectrochemical Hydrogen Production.

ACS applied materials & interfaces·2026
Same author

Polarity Inversion-Driven Band Structure Modulation, Strain Engineering, and Electrical Property Analysis on GaN/4H-SiC Heterojunctions.

ACS omega·2026
Same author

Diagnostic Accuracy of MiRNA Panels for Endometrial Cancer: A Systematic Review and Meta-Analysis.

Journal of lower genital tract disease·2026
Same author

rSiglec-10(V set) armed oncolytic adenovirus improves the effects of virotherapy through enhancing oncolysis and antitumor immunity.

International immunopharmacology·2026
Same author

Advances in vascularized organoids.

Chinese medical journal·2026
Same author

Study on the Variation of Resistance Factor of Polymer Microspheres with Distance from the Injection Well.

ACS omega·2026

Related Experiment Video

Updated: Aug 13, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

Detection and Recognition Algorithm of Arbitrary-Oriented Oil Replenishment Target in Remote Sensing Image.

Yongjie Hou1, Qingwen Yang1, Li Li1

  • 1School of Information Science and Engineering, Xinjiang University, Urumqi 830017, China.

Sensors (Basel, Switzerland)
|January 21, 2023
PubMed
Summary

A new lightweight network, MR-YOLO, enhances road status assessment using aerial imagery. This algorithm improves detection accuracy and speed while reducing computational load, making it ideal for real-world applications.

Keywords:
CSPNetMobileNetv3YOLOv5sdeep learningpavement refill detection

More Related Videos

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

3.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600

Related Experiment Videos

Last Updated: Aug 13, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

3.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Remote Sensing

Background:

  • Aerial imagery from UAVs presents challenges for object detection due to perspective, resolution changes, and small targets.
  • Existing natural scene detection methods are ineffective for remote sensing images with arbitrary orientations.
  • Accurate road technology status assessment requires specialized detection algorithms for aerial imagery.

Purpose of the Study:

  • To propose a lightweight network architecture, MobileNetv3-YOLOv5s (MR-YOLO), for efficient road technology status assessment.
  • To enhance detection accuracy and speed while reducing model size and computational complexity.
  • To adapt existing object detection frameworks for the specific demands of remote sensing applications.

Main Methods:

  • Integrated MobileNetv3 into YOLOv5s backbone for efficient feature extraction, reducing model size and improving speed.
  • Incorporated CSPNet to maintain accuracy while decreasing computation.
  • Improved focal loss function for enhanced localization accuracy and faster bounding box regression.
  • Modified YOLOv5 with prior frame design, improved bounding box regression, and added rotation angle detection.

Main Results:

  • The MR-YOLO algorithm achieved 91.1% accuracy and 92.4% average precision on the Xinjiang Altay highway dataset.
  • Detection speed reached 96.8 FPS, significantly faster than standard YOLOv5s.
  • Demonstrated substantial improvements in p-value and mAP compared to YOLOv5s.
  • Significantly reduced model parameters and computation while enhancing performance.

Conclusions:

  • The proposed MR-YOLO algorithm effectively addresses the challenges of detecting small targets and arbitrary orientations in aerial remote sensing imagery.
  • MR-YOLO offers a superior balance of accuracy, speed, and computational efficiency for road technology status assessment.
  • The algorithm's performance validates its feasibility and effectiveness on real-world highway datasets.