Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images
Phenology has become a field of growing importance due to the increasingly apparent impacts of climate change. However, the time-consuming, subjective and tedious nature of traditional human field observations have hindered the development of large-scale phenology networks. Such networks are rare an...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8954712/ |
id |
doaj-914ab1d3430a4eef955f8ea4ef0f0680 |
---|---|
record_format |
Article |
spelling |
doaj-914ab1d3430a4eef955f8ea4ef0f06802021-03-30T03:15:15ZengIEEEIEEE Access2169-35362020-01-018131511316010.1109/ACCESS.2020.29654628954712Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse ImagesDavid L. P. Correia0https://orcid.org/0000-0003-2318-1572Wassim Bouachir1https://orcid.org/0000-0003-3896-7674David Gervais2https://orcid.org/0000-0002-3489-9566Deepa Pureswaran3https://orcid.org/0000-0002-4040-7708Daniel D. Kneeshaw4https://orcid.org/0000-0003-2585-8436Louis De Grandpre5https://orcid.org/0000-0002-0368-4597Laurentian Forestry Centre, Canadian Forest Service, Natural Resources Canada, Québec, QC, CanadaDepartment of Science and Technology, TÉLUQ University, Montréal, QC, CanadaLaurentian Forestry Centre, Canadian Forest Service, Natural Resources Canada, Québec, QC, CanadaLaurentian Forestry Centre, Canadian Forest Service, Natural Resources Canada, Québec, QC, CanadaCentre d’étude de la forêt (CEF), Université du Québec à Montréal, Montréal, QC, CanadaLaurentian Forestry Centre, Canadian Forest Service, Natural Resources Canada, Québec, QC, CanadaPhenology has become a field of growing importance due to the increasingly apparent impacts of climate change. However, the time-consuming, subjective and tedious nature of traditional human field observations have hindered the development of large-scale phenology networks. Such networks are rare and rely on time-lapse cameras and simplistic color indexes to monitor phenology. To automatize rapid, detailed and repeatable analyzes, we propose an Artificial Intelligence (AI) framework based on machine learning and computer vision techniques. Our approach extracts multiple ecologically-relevant indicators from time-lapse digital photography datasets. The proposed framework consists of three main components: (i) a random forest model to automatically select relevant images based on color information; (ii) a convolutional neural network (CNN) to identify and localize open tree buds; and (iii) a density-based spatial clustering algorithm to cluster open bud detections across the time-series. We tested this framework on a dataset including thousands of black spruce and balsam fir tree images captured using our phenological camera network. The performed experiments showed the efficiency of the proposed approach under challenging perturbation factors, such as significant image noise. Our framework is exceedingly faster and more accurate than human analysts, reducing the time-series processing time from multiple days to under an hour. The proposed methodology is particularly appropriate for large-scale and long-term analyzes of ecological imagery datasets. Our work demonstrates that the use of computer vision and machine learning methods represents a promising direction for the implementation of national, continental, or even global plant phenology networks.https://ieeexplore.ieee.org/document/8954712/Balsam firblack sprucecomputer visionconvolutional neural networkdeep learningforest ecology |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
David L. P. Correia Wassim Bouachir David Gervais Deepa Pureswaran Daniel D. Kneeshaw Louis De Grandpre |
spellingShingle |
David L. P. Correia Wassim Bouachir David Gervais Deepa Pureswaran Daniel D. Kneeshaw Louis De Grandpre Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images IEEE Access Balsam fir black spruce computer vision convolutional neural network deep learning forest ecology |
author_facet |
David L. P. Correia Wassim Bouachir David Gervais Deepa Pureswaran Daniel D. Kneeshaw Louis De Grandpre |
author_sort |
David L. P. Correia |
title |
Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images |
title_short |
Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images |
title_full |
Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images |
title_fullStr |
Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images |
title_full_unstemmed |
Leveraging Artificial Intelligence for Large-Scale Plant Phenology Studies From Noisy Time-Lapse Images |
title_sort |
leveraging artificial intelligence for large-scale plant phenology studies from noisy time-lapse images |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Phenology has become a field of growing importance due to the increasingly apparent impacts of climate change. However, the time-consuming, subjective and tedious nature of traditional human field observations have hindered the development of large-scale phenology networks. Such networks are rare and rely on time-lapse cameras and simplistic color indexes to monitor phenology. To automatize rapid, detailed and repeatable analyzes, we propose an Artificial Intelligence (AI) framework based on machine learning and computer vision techniques. Our approach extracts multiple ecologically-relevant indicators from time-lapse digital photography datasets. The proposed framework consists of three main components: (i) a random forest model to automatically select relevant images based on color information; (ii) a convolutional neural network (CNN) to identify and localize open tree buds; and (iii) a density-based spatial clustering algorithm to cluster open bud detections across the time-series. We tested this framework on a dataset including thousands of black spruce and balsam fir tree images captured using our phenological camera network. The performed experiments showed the efficiency of the proposed approach under challenging perturbation factors, such as significant image noise. Our framework is exceedingly faster and more accurate than human analysts, reducing the time-series processing time from multiple days to under an hour. The proposed methodology is particularly appropriate for large-scale and long-term analyzes of ecological imagery datasets. Our work demonstrates that the use of computer vision and machine learning methods represents a promising direction for the implementation of national, continental, or even global plant phenology networks. |
topic |
Balsam fir black spruce computer vision convolutional neural network deep learning forest ecology |
url |
https://ieeexplore.ieee.org/document/8954712/ |
work_keys_str_mv |
AT davidlpcorreia leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages AT wassimbouachir leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages AT davidgervais leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages AT deepapureswaran leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages AT danieldkneeshaw leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages AT louisdegrandpre leveragingartificialintelligenceforlargescaleplantphenologystudiesfromnoisytimelapseimages |
_version_ |
1724183775327289344 |