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

Systemic and characteristic metabolites in the serum of streptozotocin-induced diabetic rats at different stages as revealed by a (1)H-NMR based metabonomic approach.

Molecular bioSystems·2014
Same author

Syntheses of asymmetric zinc phthalocyanines as sensitizer of Pt-loaded graphitic carbon nitride for efficient visible/near-IR-light-driven H2 production.

Physical chemistry chemical physics : PCCP·2014
Same author

Entropy: a conceptual approach to measuring situation-level workload within emergency care and its relationship to emergency department crowding.

The Journal of emergency medicine·2014
Same author

[Cerebral microbleeds detected on T2-weighted gradient echo magnetic resonance and its clinical significance].

Zhonghua yi xue za zhi·2014
Same author

XB130 promotes proliferation and invasion of gastric cancer cells.

Journal of translational medicine·2014
Same author

GeneOptimizer program-assisted cDNA reengineering enhances sRAGE autologous expression in Chinese hamster ovary cells.

Protein expression and purification·2013

Related Experiment Video

Updated: Jul 21, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K

A Novel Deep Learning Model for Accurate Pest Detection and Edge Computing Deployment.

Huangyi Kang1, Luxin Ai2, Zengyi Zhen1

  • 1College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China.

Insects
|July 28, 2023
PubMed
Summary

This study introduces an enhanced object detection model for precise rice pest identification. The method improves accuracy and speed, making it ideal for real-time agricultural monitoring.

Keywords:
deep learningedge computingknowledge distillationmulti-scale feature fusionpest detection

More Related Videos

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

572
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

807

Related Experiment Videos

Last Updated: Jul 21, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
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

572
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

807

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Accurate rice pest detection is crucial for crop yield and food security.
  • Existing object detection models face challenges with varying pest scales and real-time processing.

Purpose of the Study:

  • To develop an attention-mechanism-enhanced object detection model for rice pest detection.
  • To improve predictive accuracy for pests of different sizes.
  • To enable efficient edge computing for agricultural applications.

Main Methods:

  • Implemented a single-stage object detection model.
  • Integrated a multi-scale feature fusion network for enhanced scale handling.
  • Incorporated attention mechanisms to focus on pest regions.
  • Designed a knowledge distillation network for edge deployment.

Main Results:

  • Achieved superior performance over state-of-the-art models on the IDADP dataset.
  • Obtained a mean Average Precision (mAP) of 87.5%.
  • Reached an inference speed of 56 Frames Per Second (FPS) with high accuracy.

Conclusions:

  • The proposed attention-enhanced method significantly improves rice pest detection accuracy and efficiency.
  • The model is effective for edge computing scenarios in agriculture.
  • This approach offers a superior solution for real-time pest monitoring.