Related Experiment Video
Updated: Jun 21, 2025
03:45
A Rapid Method to Confine and Safely Handle Bees in the Field
Published on: August 23, 2024
749
Comprehensive wheat coccinellid detection dataset: Essential resource for digital entomology.
Ivan Grijalva1, Nicholas Clark1, Emma Hamilton1
1Department of Entomology, Kansas State University, Manhattan, KS 66506, USA.
Data in Brief
|July 8, 2024
Summary
A new dataset of coccinellid (lady beetle) images aids in developing automated pest detection systems for wheat crops. This technology can reduce pesticide use and manual labor, benefiting precision agriculture and entomology research.
Area of Science:
- Agricultural Science
- Entomology
- Computer Vision
Background:
- Aphids are significant pests in wheat (Triticum aestivum), impacting crop yield.
- Pesticide use for aphid control affects biodiversity and natural predators like coccinellids (lady beetles).
- Manual monitoring of natural enemies is labor-intensive and costly.
Purpose of the Study:
- To address the need for automated detection of natural enemies in wheat.
- To provide a valuable dataset for training machine learning models.
- To support the development of precision agriculture technologies.
Main Methods:
- Collected 2,133 diverse images of coccinellids on wheat using mobile devices.
- Images are standard 640 × 640 pixels.
- Dataset includes annotated labels suitable for YOLO family models.
Main Results:
- A comprehensive image dataset of coccinellids in wheat was created.
- The dataset is ready for training machine learning and computer vision models.
- Facilitates research in automated insect detection.
Conclusions:
- The dataset advances automated pest management in agriculture.
- Enhances understanding of machine learning applications in entomology.
- Supports sustainable crop protection strategies and reduces reliance on chemical pesticides.
