Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting
Advancements in deep learning and computer vision have led to the discovery of numerous effective solutions to challenging problems in the field of agricultural automation. With the aim to improve the detection precision in the autonomous harvesting process of green asparagus, in this article, we pr...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/23/9270 |
_version_ | 1797462091127324672 |
---|---|
author | Xiangpeng Liu Danning Wang Yani Li Xiqiang Guan Chengjin Qin |
author_facet | Xiangpeng Liu Danning Wang Yani Li Xiqiang Guan Chengjin Qin |
author_sort | Xiangpeng Liu |
collection | DOAJ |
description | Advancements in deep learning and computer vision have led to the discovery of numerous effective solutions to challenging problems in the field of agricultural automation. With the aim to improve the detection precision in the autonomous harvesting process of green asparagus, in this article, we proposed the DA-Mask RCNN model, which utilizes the depth information in the region proposal network. Firstly, the deep residual network and feature pyramid network were combined to form the backbone network. Secondly, the DA-Mask RCNN model added a depth filter to aid the softmax function in anchor classification. Afterwards, the region proposals were further processed by the detection head unit. The training and test images were mainly acquired from different regions in the basin of the Yangtze River. During the capturing process, various weather and illumination conditions were taken into account, including sunny weather, sunny but overshadowed conditions, cloudy weather, and daytime greenhouse conditions as well as nighttime greenhouse conditions. Performance experiments, comparison experiments, and ablation experiments were carried out using the five constructed datasets to verify the effectiveness of the proposed model. Precision, recall, and F1-score values were applied to evaluate the performances of different approaches. The overall experimental results demonstrate that the balance of the precision and speed of the proposed DA-Mask RCNN model outperform those of existing algorithms. |
first_indexed | 2024-03-09T17:31:28Z |
format | Article |
id | doaj.art-0b290ee6661f40f6ac6945060e3450e9 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T17:31:28Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-0b290ee6661f40f6ac6945060e3450e92023-11-24T12:11:24ZengMDPI AGSensors1424-82202022-11-012223927010.3390/s22239270Detection of Green Asparagus Using Improved Mask R-CNN for Automatic HarvestingXiangpeng Liu0Danning Wang1Yani Li2Xiqiang Guan3Chengjin Qin4College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaSchool of Engineering and Telecommunications, University of New South Wales, Sydney 2052, AustraliaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaSchool of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaAdvancements in deep learning and computer vision have led to the discovery of numerous effective solutions to challenging problems in the field of agricultural automation. With the aim to improve the detection precision in the autonomous harvesting process of green asparagus, in this article, we proposed the DA-Mask RCNN model, which utilizes the depth information in the region proposal network. Firstly, the deep residual network and feature pyramid network were combined to form the backbone network. Secondly, the DA-Mask RCNN model added a depth filter to aid the softmax function in anchor classification. Afterwards, the region proposals were further processed by the detection head unit. The training and test images were mainly acquired from different regions in the basin of the Yangtze River. During the capturing process, various weather and illumination conditions were taken into account, including sunny weather, sunny but overshadowed conditions, cloudy weather, and daytime greenhouse conditions as well as nighttime greenhouse conditions. Performance experiments, comparison experiments, and ablation experiments were carried out using the five constructed datasets to verify the effectiveness of the proposed model. Precision, recall, and F1-score values were applied to evaluate the performances of different approaches. The overall experimental results demonstrate that the balance of the precision and speed of the proposed DA-Mask RCNN model outperform those of existing algorithms.https://www.mdpi.com/1424-8220/22/23/9270agricultural automationgreen asparagus detectionDA-Mask RCNNdepth filterdifferent weatherillumination conditions |
spellingShingle | Xiangpeng Liu Danning Wang Yani Li Xiqiang Guan Chengjin Qin Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting Sensors agricultural automation green asparagus detection DA-Mask RCNN depth filter different weather illumination conditions |
title | Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting |
title_full | Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting |
title_fullStr | Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting |
title_full_unstemmed | Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting |
title_short | Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting |
title_sort | detection of green asparagus using improved mask r cnn for automatic harvesting |
topic | agricultural automation green asparagus detection DA-Mask RCNN depth filter different weather illumination conditions |
url | https://www.mdpi.com/1424-8220/22/23/9270 |
work_keys_str_mv | AT xiangpengliu detectionofgreenasparagususingimprovedmaskrcnnforautomaticharvesting AT danningwang detectionofgreenasparagususingimprovedmaskrcnnforautomaticharvesting AT yanili detectionofgreenasparagususingimprovedmaskrcnnforautomaticharvesting AT xiqiangguan detectionofgreenasparagususingimprovedmaskrcnnforautomaticharvesting AT chengjinqin detectionofgreenasparagususingimprovedmaskrcnnforautomaticharvesting |