Cargando…
Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards
Autonomous harvesting shows a promising prospect in the future development of the agriculture industry, while the vision system is one of the most challenging components in the autonomous harvesting technologies. This work proposes a multi-function network to perform the real-time detection and sema...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832306/ https://www.ncbi.nlm.nih.gov/pubmed/31652634 http://dx.doi.org/10.3390/s19204599 |
_version_ | 1783466140810346496 |
---|---|
author | Kang, Hanwen Chen, Chao |
author_facet | Kang, Hanwen Chen, Chao |
author_sort | Kang, Hanwen |
collection | PubMed |
description | Autonomous harvesting shows a promising prospect in the future development of the agriculture industry, while the vision system is one of the most challenging components in the autonomous harvesting technologies. This work proposes a multi-function network to perform the real-time detection and semantic segmentation of apples and branches in orchard environments by using the visual sensor. The developed detection and segmentation network utilises the atrous spatial pyramid pooling and the gate feature pyramid network to enhance feature extraction ability of the network. To improve the real-time computation performance of the network model, a lightweight backbone network based on the residual network architecture is developed. From the experimental results, the detection and segmentation network with ResNet-101 backbone outperformed on the detection and segmentation tasks, achieving an [Formula: see text] score of 0.832 on the detection of apples and 87.6% and 77.2% on the semantic segmentation of apples and branches, respectively. The network model with lightweight backbone showed the best computation efficiency in the results. It achieved an [Formula: see text] score of 0.827 on the detection of apples and 86.5% and 75.7% on the segmentation of apples and branches, respectively. The weights size and computation time of the network model with lightweight backbone were 12.8 M and 32 ms, respectively. The experimental results show that the detection and segmentation network can effectively perform the real-time detection and segmentation of apples and branches in orchards. |
format | Online Article Text |
id | pubmed-6832306 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-68323062019-11-21 Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards Kang, Hanwen Chen, Chao Sensors (Basel) Article Autonomous harvesting shows a promising prospect in the future development of the agriculture industry, while the vision system is one of the most challenging components in the autonomous harvesting technologies. This work proposes a multi-function network to perform the real-time detection and semantic segmentation of apples and branches in orchard environments by using the visual sensor. The developed detection and segmentation network utilises the atrous spatial pyramid pooling and the gate feature pyramid network to enhance feature extraction ability of the network. To improve the real-time computation performance of the network model, a lightweight backbone network based on the residual network architecture is developed. From the experimental results, the detection and segmentation network with ResNet-101 backbone outperformed on the detection and segmentation tasks, achieving an [Formula: see text] score of 0.832 on the detection of apples and 87.6% and 77.2% on the semantic segmentation of apples and branches, respectively. The network model with lightweight backbone showed the best computation efficiency in the results. It achieved an [Formula: see text] score of 0.827 on the detection of apples and 86.5% and 75.7% on the segmentation of apples and branches, respectively. The weights size and computation time of the network model with lightweight backbone were 12.8 M and 32 ms, respectively. The experimental results show that the detection and segmentation network can effectively perform the real-time detection and segmentation of apples and branches in orchards. MDPI 2019-10-22 /pmc/articles/PMC6832306/ /pubmed/31652634 http://dx.doi.org/10.3390/s19204599 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Kang, Hanwen Chen, Chao Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title | Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title_full | Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title_fullStr | Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title_full_unstemmed | Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title_short | Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards |
title_sort | fruit detection and segmentation for apple harvesting using visual sensor in orchards |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832306/ https://www.ncbi.nlm.nih.gov/pubmed/31652634 http://dx.doi.org/10.3390/s19204599 |
work_keys_str_mv | AT kanghanwen fruitdetectionandsegmentationforappleharvestingusingvisualsensorinorchards AT chenchao fruitdetectionandsegmentationforappleharvestingusingvisualsensorinorchards |