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

Clinical effect of uterine artery embolization combined with curettage in the treatment of cesarean scar pregnancy.

Pakistan journal of medical sciences·2026
Same author

Dual-phase eutectic ceramics with improved hardness and toughness via nano-coherent high-entropy oxides.

Nature communications·2026
Same author

Safe and successful use of remimazolam for gastrointestinal endoscopy in a patient with propofol-induced seizure-like phenomena: a case report and literature review.

BMC anesthesiology·2026
Same author

DBML-Font :Double-branch multi-level feature fusion based on diffusion model for few-shot font generation.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Electroactive interface-enhanced dielectric elastomer with ultrahigh electroadhesion and multifunctional droplet actuation.

Science advances·2026
Same author

M2 macrophages promote lymphatic metastasis by regulating PKM2 nuclear translocation in triple-negative breast cancer.

Cell death & disease·2026

Related Experiment Video

Updated: Jun 15, 2025

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

492

A Multi-Scale Target Detection Method Using an Improved Faster Region Convolutional Neural Network Based on Enhanced

Qianyong Chen1, Mengshan Li1, Zhenghui Lai1

  • 1College of Physics and Electronic Information, Gannan Normal University, Ganzhou 341000, China.

Journal of Imaging
|August 28, 2024
PubMed
Summary

This study introduces an improved Faster R-CNN for multi-target detection, enhancing accuracy and reducing missed detections. The enhanced algorithm effectively handles multi-scale targets, offering better performance for complex visual recognition tasks.

Keywords:
DIoUResNet101Soft-NMSimproved Faster R-CNNmulti-scale target detection

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Related Experiment Videos

Last Updated: Jun 15, 2025

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

492
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

Area of Science:

  • Computer Vision
  • Deep Learning

Background:

  • Existing deep learning methods struggle with multi-target detection, leading to low accuracy and high false/missed detection rates.
  • Detecting multi-scale targets presents a significant challenge in computer vision applications.

Purpose of the Study:

  • To propose an improved Faster R-CNN algorithm for enhanced multi-target detection capabilities.
  • To address limitations in accuracy, false detections, and missed detections in current deep learning models.

Main Methods:

  • Utilized ResNet101 for superior feature extraction.
  • Integrated Online Hard Example Mining (OHEM), Soft non-maximum suppression (Soft-NMS), and Distance Intersection Over Union (DIOU) modules.
  • Simplified the Region Proposal Network (RPN) and employed multi-scale training (MST) for improved efficiency and accuracy.

Main Results:

  • The improved Faster R-CNN demonstrated significant advantages in mAP@0.5, F1-score, and Log average miss rate (LAMR) compared to other models.
  • The algorithm effectively improved positive/negative sample imbalance and reduced missed detections of small targets.
  • Achieved a balance between detection accuracy and efficiency.

Conclusions:

  • The proposed improved Faster R-CNN offers a robust solution for multi-target detection, particularly for multi-scale objects.
  • The advancements provide valuable insights for applications in smart agriculture, medical diagnosis, and face recognition.
  • This work contributes to the development of more accurate and efficient object detection systems.