EcoIP: An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras

Joel A. Granados; Eric A. Graham; Philippe Bonnet; Eric M. Yuen; Michael Hamilton

doi:10.1016/j.ecoinf.2013.03.002

EcoIP: An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras

Joel A. Granados^*, Eric A. Graham, Philippe Bonnet, Eric M. Yuen, Michael Hamilton

^*Corresponding author for this work

Research output: Contribution to journal › Journal article › Research › peer-review

7 Citations (Scopus)

Abstract

Because of the increased number of cameras employed in environmental sensing and the tremendous image output they produce, we have created a flexible, open-source software solution called EcoIP to help automatically determine different phenophases for different species from digital image sequences. Onset and ending dates are calculated through an iterative process: (1) training images are chosen and areas of interest identified, (2) separation of foreground and background is accomplished based on a naive Bayesian method, (3) a signal is created based on the separation model and (4) it is then fit to a sigmoid that contains the dates of interest. Results using different phenological events of different species indicate that estimated dates fall within a few days of the observed dates for most cases. Our experiments indicate that color separability and scene illumination are contributing factors to this error. EcoIP is implemented as an open platform that encourages anyone to execute, copy, distribute, study, change, and/or improve the application.

Original language	English
Journal	Ecological Informatics
Volume	15
Pages (from-to)	58-65
Number of pages	8
ISSN	1574-9541
DOIs	https://doi.org/10.1016/j.ecoinf.2013.03.002
Publication status	Published - May 2013
Externally published	Yes

Bibliographical note

Funding Information:
The research leading to these results has received funding from INTERACT (grant agreement No 262693 ), under the European Union's Seventh Framework Program . A portion of this research was also supported by National Science Foundation award 0120778 to the Center for Embedded Networked Sensing at the University of California, Los Angeles.

Keywords

Bayesian analysis
Camera
Color transformation
Digital photography
Onset ending date
Phenology

Access to Document

10.1016/j.ecoinf.2013.03.002

Cite this

EcoIP : An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras. / Granados, Joel A.; Graham, Eric A.; Bonnet, Philippe; Yuen, Eric M.; Hamilton, Michael.

In: Ecological Informatics, Vol. 15, 05.2013, p. 58-65.

Research output: Contribution to journal › Journal article › Research › peer-review

@article{dd84b993c5db4bcf89a948eca33b9343,

title = "EcoIP: An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras",

abstract = "Because of the increased number of cameras employed in environmental sensing and the tremendous image output they produce, we have created a flexible, open-source software solution called EcoIP to help automatically determine different phenophases for different species from digital image sequences. Onset and ending dates are calculated through an iterative process: (1) training images are chosen and areas of interest identified, (2) separation of foreground and background is accomplished based on a naive Bayesian method, (3) a signal is created based on the separation model and (4) it is then fit to a sigmoid that contains the dates of interest. Results using different phenological events of different species indicate that estimated dates fall within a few days of the observed dates for most cases. Our experiments indicate that color separability and scene illumination are contributing factors to this error. EcoIP is implemented as an open platform that encourages anyone to execute, copy, distribute, study, change, and/or improve the application.",

keywords = "Bayesian analysis, Camera, Color transformation, Digital photography, Onset ending date, Phenology",

author = "Granados, {Joel A.} and Graham, {Eric A.} and Philippe Bonnet and Yuen, {Eric M.} and Michael Hamilton",

note = "Funding Information: The research leading to these results has received funding from INTERACT (grant agreement No 262693 ), under the European Union's Seventh Framework Program . A portion of this research was also supported by National Science Foundation award 0120778 to the Center for Embedded Networked Sensing at the University of California, Los Angeles.",

year = "2013",

month = may,

doi = "10.1016/j.ecoinf.2013.03.002",

language = "English",

volume = "15",

pages = "58--65",

journal = "Ecological Informatics",

issn = "1574-9541",

publisher = "Elsevier",

}

TY - JOUR

T1 - EcoIP

T2 - An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras

AU - Granados, Joel A.

AU - Graham, Eric A.

AU - Bonnet, Philippe

AU - Yuen, Eric M.

AU - Hamilton, Michael

N1 - Funding Information: The research leading to these results has received funding from INTERACT (grant agreement No 262693 ), under the European Union's Seventh Framework Program . A portion of this research was also supported by National Science Foundation award 0120778 to the Center for Embedded Networked Sensing at the University of California, Los Angeles.

PY - 2013/5

Y1 - 2013/5

N2 - Because of the increased number of cameras employed in environmental sensing and the tremendous image output they produce, we have created a flexible, open-source software solution called EcoIP to help automatically determine different phenophases for different species from digital image sequences. Onset and ending dates are calculated through an iterative process: (1) training images are chosen and areas of interest identified, (2) separation of foreground and background is accomplished based on a naive Bayesian method, (3) a signal is created based on the separation model and (4) it is then fit to a sigmoid that contains the dates of interest. Results using different phenological events of different species indicate that estimated dates fall within a few days of the observed dates for most cases. Our experiments indicate that color separability and scene illumination are contributing factors to this error. EcoIP is implemented as an open platform that encourages anyone to execute, copy, distribute, study, change, and/or improve the application.

AB - Because of the increased number of cameras employed in environmental sensing and the tremendous image output they produce, we have created a flexible, open-source software solution called EcoIP to help automatically determine different phenophases for different species from digital image sequences. Onset and ending dates are calculated through an iterative process: (1) training images are chosen and areas of interest identified, (2) separation of foreground and background is accomplished based on a naive Bayesian method, (3) a signal is created based on the separation model and (4) it is then fit to a sigmoid that contains the dates of interest. Results using different phenological events of different species indicate that estimated dates fall within a few days of the observed dates for most cases. Our experiments indicate that color separability and scene illumination are contributing factors to this error. EcoIP is implemented as an open platform that encourages anyone to execute, copy, distribute, study, change, and/or improve the application.

KW - Bayesian analysis

KW - Camera

KW - Color transformation

KW - Digital photography

KW - Onset ending date

KW - Phenology

U2 - 10.1016/j.ecoinf.2013.03.002

DO - 10.1016/j.ecoinf.2013.03.002

M3 - Journal article

AN - SCOPUS:84876372007

VL - 15

SP - 58

EP - 65

JO - Ecological Informatics

JF - Ecological Informatics

SN - 1574-9541

ER -