Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Study On The Image Recognition Of Field-trapped Adult Spodoptera Frugiperda Using Sex Pheromone Lures.
  1. Home
  3. Study On The Image Recognition Of Field-trapped Adult Spodoptera Frugiperda Using Sex Pheromone Lures.

Related Experiment Video

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges
04:41

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges

Published on: July 14, 2023

2.1K

Study on the Image Recognition of Field-Trapped Adult Spodoptera frugiperda Using Sex Pheromone Lures.

Quanyuan Xu1,2, Caiyi Li1, Min Fan3

  • 1College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China.

Insects
|September 27, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

Accurate identification of Spodoptera frugiperda (fall armyworm) is crucial for pest control. An improved CBAM-YOLOv5 model achieved 97.8% accuracy in detecting this invasive pest in field images, enabling smart trapping systems.

Keywords:
Mask R-CNNSpodoptera frugiperdaYOLOv5image recognitiontrapping posture adults

More Related Videos

A Wind Tunnel for Odor Mediated Insect Behavioural Assays
05:25

A Wind Tunnel for Odor Mediated Insect Behavioural Assays

Published on: November 30, 2018

12.4K
Identification of Metabolically Active Bacteria in the Gut of the Generalist Spodoptera littoralis via DNA Stable Isotope Probing Using 13C-Glucose
12:11

Identification of Metabolically Active Bacteria in the Gut of the Generalist Spodoptera littoralis via DNA Stable Isotope Probing Using 13C-Glucose

Published on: November 13, 2013

15.8K

Related Experiment Videos

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges
04:41

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges

Published on: July 14, 2023

2.1K
A Wind Tunnel for Odor Mediated Insect Behavioural Assays
05:25

A Wind Tunnel for Odor Mediated Insect Behavioural Assays

Published on: November 30, 2018

12.4K
Identification of Metabolically Active Bacteria in the Gut of the Generalist Spodoptera littoralis via DNA Stable Isotope Probing Using 13C-Glucose
12:11

Identification of Metabolically Active Bacteria in the Gut of the Generalist Spodoptera littoralis via DNA Stable Isotope Probing Using 13C-Glucose

Published on: November 13, 2013

15.8K

Area of Science:

  • Agricultural Entomology
  • Computer Vision
  • Machine Learning

Background:

  • Spodoptera frugiperda is a significant global pest, necessitating precise monitoring for effective control.
  • Accurate identification and counting of trapped insects are vital for quantitative pest management.
  • Challenges in image recognition include scale variation and mixed insect species in field trap images.

Purpose of the Study:

  • To develop an advanced AI model for accurate identification and counting of Spodoptera frugiperda in field images.
  • To enhance existing deep learning models for improved performance under complex field conditions.
  • To create a practical, intelligent system for automated pest monitoring.

Main Methods:

  • A dataset of 9550 labeled images of trapped insects, including Spodoptera frugiperda, was created.
  • An improved YOLOv5s model was developed, incorporating Mosaic data augmentation and adaptive anchor boxes.
  • Attention mechanisms (SENet, CBAM, CA) were integrated, with CBAM showing superior performance.
  • The model was compared against YOLOv7, YOLOv8, Mask R-CNN, and DETR.

    • Main Results:

    • The optimized CBAM-YOLOv5 model achieved 97.8% mAP@0.5 for Spodoptera frugiperda identification.
    • Recognition accuracy for other insect species was at least 72.4%.
    • The model demonstrated superior performance compared to baseline models under complex field backgrounds.

    Conclusions:

    • The CBAM-YOLOv5 model provides a highly accurate and efficient solution for Spodoptera frugiperda detection.
    • An intelligent recognition system was developed for automated image acquisition, identification, and counting.
    • This technology offers a high-precision algorithmic solution for smart pest trapping devices.