An Enhanced Cycle Generative Adversarial Network Approach for Nighttime Pineapple Detection of Automated Harvesting Robots

Nighttime pineapple detection for automated harvesting robots is a significant challenge in intelligent agriculture. As a crucial component of robotic vision systems, accurate fruit detection is essential for round-the-clock operations. The study compared advanced end-to-end style transfer models, i...

Full description

Saved in:
Bibliographic Details
Published in:Agronomy (Basel) 2024-12, Vol.14 (12), p.3002
Main Authors: Wu, Fengyun, Zhu, Rong, Meng, Fan, Qiu, Jiajun, Yang, Xiaopei, Li, Jinhui, Zou, Xiangjun
Format: Article
Language:English
Subjects:
Accuracy
Apples
Automation
Cameras
computer vision
CycleGAN
Data collection
Datasets
Deep learning
fruit harvesting
Fruits
Generative adversarial networks
Harvesting
Image processing
Image quality
Leaves
Machine vision
Night
Nighttime
Pineapples
Research methodology
Robots
Vision systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nighttime pineapple detection for automated harvesting robots is a significant challenge in intelligent agriculture. As a crucial component of robotic vision systems, accurate fruit detection is essential for round-the-clock operations. The study compared advanced end-to-end style transfer models, including U-GAT-IT, SCTNet, and CycleGAN, finding that CycleGAN produced relatively good-quality images but had issues such as the inadequate restoration of nighttime details, color distortion, and artifacts. Therefore, this study further proposed an enhanced CycleGAN approach to address limited nighttime datasets and poor visibility, combining style transfer with small-sample object detection. The improved model features a novel generator structure with ResNeXtBlocks, an optimized upsampling module, and a hyperparameter optimization strategy. This approach achieves a 29.7% reduction in FID score compared to the original CycleGAN. When applied to YOLOv7-based detection, this method significantly outperforms existing approaches, improving precision, recall, average precision, and F1 score by 13.34%, 45.11%, 56.52%, and 30.52%, respectively. These results demonstrate the effectiveness of our enhanced CycleGAN in expanding limited nighttime datasets and supporting efficient automated harvesting in low-light conditions, contributing to the development of more versatile agricultural robots capable of continuous operation.
ISSN:2073-4395
2073-4395
DOI:10.3390/agronomy14123002