Related Experiment Video
Updated: Dec 30, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
2.0K
A Recognition Method for Rice Plant Diseases and Pests Video Detection Based on Deep Convolutional Neural Network
Dengshan Li1,2, Rujing Wang1, Chengjun Xie1
1Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China.
Sensors (Basel, Switzerland)
|January 25, 2020
Summary
A new deep learning system effectively detects plant diseases and pests in videos, crucial for increasing grain production in food-scarce regions. This custom backbone architecture outperforms existing methods for untrained rice video detection.
Area of Science:
- Agricultural Science
- Computer Vision
- Deep Learning
Background:
- Increasing grain production is vital for food security in regions facing scarcity.
- Timely control of crop diseases and pests is essential for boosting agricultural yields.
Purpose of the Study:
- To develop a deep learning-based video detection architecture for identifying plant diseases and pests.
- To establish a foundation for a real-time crop disease and pest video detection system.
Main Methods:
- Video data was converted into still frames for analysis.
- A Faster R-CNN framework was employed as the still-image detector.
- A custom backbone was developed and integrated into the detection system.
Main Results:
- The proposed system demonstrated superior performance in detecting diseases and pests in untrained rice videos compared to VGG16, ResNet-50, ResNet-101, and YOLOv3.
- Image-training models were utilized for detecting blurry video segments.
- Novel video-based evaluation metrics were introduced and validated.
Conclusions:
- The custom backbone deep learning architecture is highly suitable for detecting plant diseases and pests in videos, particularly for untrained crop varieties.
- The developed system offers a promising approach for enhancing crop monitoring and disease management strategies.
