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

Light Acquisition02:16

Light Acquisition

9.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.4K
  1. Home
  3. Research Domains
  5. Agricultural, Veterinary And Food Sciences
  7. Agricultural Biotechnology
  9. Agricultural Biotechnology Diagnostics (incl. Biosensors)
  11. Field-deployable Lightweight Yolov8n For Real-time Detection And Counting Of Maize Seedlings Using Uav Rgb Imagery

Field-deployable lightweight YOLOv8n for real-time detection and counting of Maize seedlings using UAV RGB imagery

Pengbo Feng1, Zhigang Nie1,2, Guang Li2,3

  • 1College of Information Science and Technology, Gansu Agricultural University, Lanzhou, China.

Frontiers in Plant Science
|September 24, 2025

Related Experiment Videos

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.1K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.6K

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a lightweight YOLOv8n maize seedling detection algorithm, achieving high accuracy with significantly reduced model size and computational cost. The enhanced model is ideal for resource-constrained devices in precision agriculture.

Area of Science:

  • Computer Vision
  • Agricultural Technology
  • Machine Learning

Background:

  • Existing maize seedling detection models suffer from large parameters, high computation, and limited real-time performance.
  • A small detection range and low efficiency hinder practical application in precision agriculture.

Purpose of the Study:

  • To develop a lightweight YOLOv8n algorithm for maize seedling detection.
  • To improve real-time performance and detection range while reducing model complexity.

Main Methods:

  • Designed a Rep_HGNetV2 lightweight backbone by fusing RepConv with HGNetV2.
  • Integrated BiFPN into the neck network for enhanced multi-scale feature fusion.
  • Developed a Task Dynamically Aligned Detection Head (TDADH) using Distribution Focal Loss (DFL) for classification and localization.
Keywords:
Grad-CAM++Maize seedlingYOLOv8nlightweight

Related Experiment Videos

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.1K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.6K

Main Results:

  • Achieved a detection accuracy of 96.5%, comparable to the original model.
  • Reduced model weight size to 3.5 MB, parameters to 1.58 M, and FLOPs to 7.4 G (43%, 47%, 8.6% reduction).
  • Maintained a high frame rate (FPS) of 146.3, with only a 2.4% decrease.

Conclusions:

  • The lightweight YOLOv8n model offers high accuracy, speed, and low complexity.
  • It is suitable for deployment on resource-constrained edge devices, UAVs, and embedded systems.
  • Provides technical support for precise maize management during the seedling stage.
small target