Related Experiment Video
Updated: Sep 1, 2025
08:02
Robotic Sensing and Stimuli Provision for Guided Plant Growth
Published on: July 1, 2019
8.1K
In-Field Automatic Identification of Pomegranates Using a Farmer Robot
Rosa Pia Devanna1, Annalisa Milella1, Roberto Marani1
1Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing, National Research Council, Via G. Amendola 122D/O, 70126 Bari, Italy.
Sensors (Basel, Switzerland)
|August 12, 2022
Summary
This study introduces a semi-supervised deep learning method for automatic pomegranate detection in orchards. The novel approach reduces manual image labeling, achieving high accuracy in fruit segmentation for precision agriculture.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Machine Learning
Background:
- Precision agriculture relies on vision-based systems for orchard monitoring.
- Traditional deep learning for fruit detection requires extensive manual image annotation.
Purpose of the Study:
- To develop a semi-supervised deep learning framework for automatic pomegranate detection.
- To reduce the labor-intensive nature of image labeling in agricultural computer vision tasks.
Main Methods:
- A semi-supervised deep learning framework utilizing a multi-stage transfer learning approach.
- Fine-tuning a pre-trained network with controlled fruit images, then extending to field conditions.
- Implementation using the DeepLabv3+ (Resnet18) architecture.
Main Results:
- The framework achieved high accuracy in pomegranate segmentation.
- An F1-score of 86.42% and an IoU of 97.94% were obtained in field tests.
- The method significantly reduced the need for manual image annotation.
Conclusions:
- The proposed semi-supervised framework enables accurate and efficient pomegranate detection in orchards.
- This approach alleviates the burden of manual labeling, making precision agriculture more accessible.
- The multi-stage transfer learning strategy is effective for adapting models to complex field scenarios.
