YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment
The real-time detection of banana bunches and stalks in banana orchards is a key technology in the application of agricultural robots. The complex conditions of the orchard make accurate detection a difficult task, and the light weight of the deep learning network is an application trend. This study...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Agronomy |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4395/12/2/391 |
_version_ | 1797483641858686976 |
---|---|
author | Lanhui Fu Zhou Yang Fengyun Wu Xiangjun Zou Jiaquan Lin Yongjun Cao Jieli Duan |
author_facet | Lanhui Fu Zhou Yang Fengyun Wu Xiangjun Zou Jiaquan Lin Yongjun Cao Jieli Duan |
author_sort | Lanhui Fu |
collection | DOAJ |
description | The real-time detection of banana bunches and stalks in banana orchards is a key technology in the application of agricultural robots. The complex conditions of the orchard make accurate detection a difficult task, and the light weight of the deep learning network is an application trend. This study proposes and compares two improved YOLOv4 neural network detection models in a banana orchard. One is the YOLO-Banana detection model, which analyzes banana characteristics and network structure to prune the less important network layers; the other is the YOLO-Banana-l4 detection model, which, by adding a YOLO head layer to the pruned network structure, explores the impact of a four-scale prediction structure on the pruning network. The results show that YOLO-Banana and YOLO-Banana-l4 could reduce the network weight and shorten the detection time compared with YOLOv4. Furthermore, YOLO-Banana detection model has the best performance, with good detection accuracy for banana bunches and stalks in the natural environment. The average precision (AP) values of the YOLO-Banana detection model on banana bunches and stalks are 98.4% and 85.98%, and the mean average precision (mAP) of the detection model is 92.19%. The model weight is reduced from 244 to 137 MB, and the detection time is shortened from 44.96 to 35.33 ms. In short, the network is lightweight and has good real-time performance and application prospects in intelligent management and automatic harvesting in the banana orchard. |
first_indexed | 2024-03-09T22:49:57Z |
format | Article |
id | doaj.art-05c4be82090846eb83ad6fcf982bf47f |
institution | Directory Open Access Journal |
issn | 2073-4395 |
language | English |
last_indexed | 2024-03-09T22:49:57Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Agronomy |
spelling | doaj.art-05c4be82090846eb83ad6fcf982bf47f2023-11-23T18:21:13ZengMDPI AGAgronomy2073-43952022-02-0112239110.3390/agronomy12020391YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural EnvironmentLanhui Fu0Zhou Yang1Fengyun Wu2Xiangjun Zou3Jiaquan Lin4Yongjun Cao5Jieli Duan6College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510641, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaThe real-time detection of banana bunches and stalks in banana orchards is a key technology in the application of agricultural robots. The complex conditions of the orchard make accurate detection a difficult task, and the light weight of the deep learning network is an application trend. This study proposes and compares two improved YOLOv4 neural network detection models in a banana orchard. One is the YOLO-Banana detection model, which analyzes banana characteristics and network structure to prune the less important network layers; the other is the YOLO-Banana-l4 detection model, which, by adding a YOLO head layer to the pruned network structure, explores the impact of a four-scale prediction structure on the pruning network. The results show that YOLO-Banana and YOLO-Banana-l4 could reduce the network weight and shorten the detection time compared with YOLOv4. Furthermore, YOLO-Banana detection model has the best performance, with good detection accuracy for banana bunches and stalks in the natural environment. The average precision (AP) values of the YOLO-Banana detection model on banana bunches and stalks are 98.4% and 85.98%, and the mean average precision (mAP) of the detection model is 92.19%. The model weight is reduced from 244 to 137 MB, and the detection time is shortened from 44.96 to 35.33 ms. In short, the network is lightweight and has good real-time performance and application prospects in intelligent management and automatic harvesting in the banana orchard.https://www.mdpi.com/2073-4395/12/2/391banana detectionstalk detectionimproved YOLOv4green fruitorchard |
spellingShingle | Lanhui Fu Zhou Yang Fengyun Wu Xiangjun Zou Jiaquan Lin Yongjun Cao Jieli Duan YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment Agronomy banana detection stalk detection improved YOLOv4 green fruit orchard |
title | YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment |
title_full | YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment |
title_fullStr | YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment |
title_full_unstemmed | YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment |
title_short | YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment |
title_sort | yolo banana a lightweight neural network for rapid detection of banana bunches and stalks in the natural environment |
topic | banana detection stalk detection improved YOLOv4 green fruit orchard |
url | https://www.mdpi.com/2073-4395/12/2/391 |
work_keys_str_mv | AT lanhuifu yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT zhouyang yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT fengyunwu yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT xiangjunzou yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT jiaquanlin yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT yongjuncao yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment AT jieliduan yolobananaalightweightneuralnetworkforrapiddetectionofbananabunchesandstalksinthenaturalenvironment |