UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence
Traditional plant breeding evaluation methods are time-consuming, labor-intensive, and costly. Accurate and rapid phenotypic trait data acquisition and analysis can improve genomic selection and accelerate cultivar development. In this work, a technique for data acquisition and image processing was...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/4/410 |
id |
doaj-d1994c764a774a54ad192f0527633c8f |
---|---|
record_format |
Article |
spelling |
doaj-d1994c764a774a54ad192f0527633c8f2020-11-24T20:48:14ZengMDPI AGRemote Sensing2072-42922019-02-0111441010.3390/rs11040410rs11040410UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial IntelligenceYiannis Ampatzidis0Victor Partel1Agricultural and Biological Engineering department, Southwest Florida Research and Education Center, University of Florida, IFAS, 2685 SR 29 North, Immokalee, FL 34142, USAAgricultural and Biological Engineering department, Southwest Florida Research and Education Center, University of Florida, IFAS, 2685 SR 29 North, Immokalee, FL 34142, USATraditional plant breeding evaluation methods are time-consuming, labor-intensive, and costly. Accurate and rapid phenotypic trait data acquisition and analysis can improve genomic selection and accelerate cultivar development. In this work, a technique for data acquisition and image processing was developed utilizing small unmanned aerial vehicles (UAVs), multispectral imaging, and deep learning convolutional neural networks to evaluate phenotypic characteristics on citrus crops. This low-cost and automated high-throughput phenotyping technique utilizes artificial intelligence (AI) and machine learning (ML) to: (i) detect, count, and geolocate trees and tree gaps; (ii) categorize trees based on their canopy size; (iii) develop individual tree health indices; and (iv) evaluate citrus varieties and rootstocks. The proposed remote sensing technique was able to detect and count citrus trees in a grove of 4,931 trees, with precision and recall of 99.9% and 99.7%, respectively, estimate their canopy size with overall accuracy of 85.5%, and detect, count, and geolocate tree gaps with a precision and recall of 100% and 94.6%, respectively. This UAV-based technique provides a consistent, more direct, cost-effective, and rapid method to evaluate phenotypic characteristics of citrus varieties and rootstocks.https://www.mdpi.com/2072-4292/11/4/410UAVartificial intelligencemachine learningsmart agricultureprecision agricultureneural networksdeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yiannis Ampatzidis Victor Partel |
spellingShingle |
Yiannis Ampatzidis Victor Partel UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence Remote Sensing UAV artificial intelligence machine learning smart agriculture precision agriculture neural networks deep learning |
author_facet |
Yiannis Ampatzidis Victor Partel |
author_sort |
Yiannis Ampatzidis |
title |
UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence |
title_short |
UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence |
title_full |
UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence |
title_fullStr |
UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence |
title_full_unstemmed |
UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence |
title_sort |
uav-based high throughput phenotyping in citrus utilizing multispectral imaging and artificial intelligence |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-02-01 |
description |
Traditional plant breeding evaluation methods are time-consuming, labor-intensive, and costly. Accurate and rapid phenotypic trait data acquisition and analysis can improve genomic selection and accelerate cultivar development. In this work, a technique for data acquisition and image processing was developed utilizing small unmanned aerial vehicles (UAVs), multispectral imaging, and deep learning convolutional neural networks to evaluate phenotypic characteristics on citrus crops. This low-cost and automated high-throughput phenotyping technique utilizes artificial intelligence (AI) and machine learning (ML) to: (i) detect, count, and geolocate trees and tree gaps; (ii) categorize trees based on their canopy size; (iii) develop individual tree health indices; and (iv) evaluate citrus varieties and rootstocks. The proposed remote sensing technique was able to detect and count citrus trees in a grove of 4,931 trees, with precision and recall of 99.9% and 99.7%, respectively, estimate their canopy size with overall accuracy of 85.5%, and detect, count, and geolocate tree gaps with a precision and recall of 100% and 94.6%, respectively. This UAV-based technique provides a consistent, more direct, cost-effective, and rapid method to evaluate phenotypic characteristics of citrus varieties and rootstocks. |
topic |
UAV artificial intelligence machine learning smart agriculture precision agriculture neural networks deep learning |
url |
https://www.mdpi.com/2072-4292/11/4/410 |
work_keys_str_mv |
AT yiannisampatzidis uavbasedhighthroughputphenotypingincitrusutilizingmultispectralimagingandartificialintelligence AT victorpartel uavbasedhighthroughputphenotypingincitrusutilizingmultispectralimagingandartificialintelligence |
_version_ |
1716808523061395456 |