Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy

Wei Guo, Bangyou Zheng, Andries B. Potgieter, Julien Diot, Kakeru Watanabe, Koji Noshita, David R. Jordan, Xuemin Wang, James Watson, Seishi Ninomiya, Scott C. Chapman

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Sorghum (Sorghum bicolor L. Moench) is a C4 tropical grass that plays an essential role in providing nutrition to humans and livestock, particularly in marginal rainfall environments. The timing of head development and the number of heads per unit area are key adaptation traits to consider in agronomy and breeding but are time consuming and labor intensive to measure. We propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial. To demonstrate the performance of the proposed method, 52 images were manually labeled; the precision and recall of head detection were 0.87 and 0.98, respectively, and the coefficient of determination (R2) between the manual and new methods of counting was 0.84. To verify the utility of the method in breeding programs, a geolocation-based plot segmentation method was applied to pre-processed ortho-mosaic images to extract >1000 plots from original RGB images. Forty of these plots were randomly selected and labeled manually; the precision and recall of detection were 0.82 and 0.98, respectively, and the coefficient of determination between manual and algorithm counting was 0.56, with the major source of error being related to the morphology of plants resulting in heads being displayed both within and outside the plot in which the plants were sown, i.e., being allocated to a neighboring plot. Finally, the potential applications in yield estimation from UAV-based imagery from agronomy experiments and scouting of production fields are also discussed.

Original languageEnglish
Article number1544
JournalFrontiers in Plant Science
Volume871
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

agronomy
Sorghum (Poaceae)
image analysis
breeding
plant morphology
breeding methods
processing technology
Sorghum bicolor
labor
livestock
methodology
nutrition
grasses
rain
extracts
unmanned aerial vehicles

All Science Journal Classification (ASJC) codes

  • Plant Science

Cite this

Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy. / Guo, Wei; Zheng, Bangyou; Potgieter, Andries B.; Diot, Julien; Watanabe, Kakeru; Noshita, Koji; Jordan, David R.; Wang, Xuemin; Watson, James; Ninomiya, Seishi; Chapman, Scott C.

In: Frontiers in Plant Science, Vol. 871, 1544, 01.01.2018.

Research output: Contribution to journalArticle

Guo, W, Zheng, B, Potgieter, AB, Diot, J, Watanabe, K, Noshita, K, Jordan, DR, Wang, X, Watson, J, Ninomiya, S & Chapman, SC 2018, 'Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy', Frontiers in Plant Science, vol. 871, 1544. https://doi.org/10.3389/fpls.2018.01544
Guo, Wei ; Zheng, Bangyou ; Potgieter, Andries B. ; Diot, Julien ; Watanabe, Kakeru ; Noshita, Koji ; Jordan, David R. ; Wang, Xuemin ; Watson, James ; Ninomiya, Seishi ; Chapman, Scott C. / Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy. In: Frontiers in Plant Science. 2018 ; Vol. 871.
@article{9e5b53c293684472af8261a4d5c66398,
title = "Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy",
abstract = "Sorghum (Sorghum bicolor L. Moench) is a C4 tropical grass that plays an essential role in providing nutrition to humans and livestock, particularly in marginal rainfall environments. The timing of head development and the number of heads per unit area are key adaptation traits to consider in agronomy and breeding but are time consuming and labor intensive to measure. We propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial. To demonstrate the performance of the proposed method, 52 images were manually labeled; the precision and recall of head detection were 0.87 and 0.98, respectively, and the coefficient of determination (R2) between the manual and new methods of counting was 0.84. To verify the utility of the method in breeding programs, a geolocation-based plot segmentation method was applied to pre-processed ortho-mosaic images to extract >1000 plots from original RGB images. Forty of these plots were randomly selected and labeled manually; the precision and recall of detection were 0.82 and 0.98, respectively, and the coefficient of determination between manual and algorithm counting was 0.56, with the major source of error being related to the morphology of plants resulting in heads being displayed both within and outside the plot in which the plants were sown, i.e., being allocated to a neighboring plot. Finally, the potential applications in yield estimation from UAV-based imagery from agronomy experiments and scouting of production fields are also discussed.",
author = "Wei Guo and Bangyou Zheng and Potgieter, {Andries B.} and Julien Diot and Kakeru Watanabe and Koji Noshita and Jordan, {David R.} and Xuemin Wang and James Watson and Seishi Ninomiya and Chapman, {Scott C.}",
year = "2018",
month = "1",
day = "1",
doi = "10.3389/fpls.2018.01544",
language = "English",
volume = "871",
journal = "Frontiers in Plant Science",
issn = "1664-462X",
publisher = "Frontiers Media S. A.",

}

TY - JOUR

T1 - Aerial imagery analysis – Quantifying appearance and number of sorghum heads for applications in breeding and agronomy

AU - Guo, Wei

AU - Zheng, Bangyou

AU - Potgieter, Andries B.

AU - Diot, Julien

AU - Watanabe, Kakeru

AU - Noshita, Koji

AU - Jordan, David R.

AU - Wang, Xuemin

AU - Watson, James

AU - Ninomiya, Seishi

AU - Chapman, Scott C.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Sorghum (Sorghum bicolor L. Moench) is a C4 tropical grass that plays an essential role in providing nutrition to humans and livestock, particularly in marginal rainfall environments. The timing of head development and the number of heads per unit area are key adaptation traits to consider in agronomy and breeding but are time consuming and labor intensive to measure. We propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial. To demonstrate the performance of the proposed method, 52 images were manually labeled; the precision and recall of head detection were 0.87 and 0.98, respectively, and the coefficient of determination (R2) between the manual and new methods of counting was 0.84. To verify the utility of the method in breeding programs, a geolocation-based plot segmentation method was applied to pre-processed ortho-mosaic images to extract >1000 plots from original RGB images. Forty of these plots were randomly selected and labeled manually; the precision and recall of detection were 0.82 and 0.98, respectively, and the coefficient of determination between manual and algorithm counting was 0.56, with the major source of error being related to the morphology of plants resulting in heads being displayed both within and outside the plot in which the plants were sown, i.e., being allocated to a neighboring plot. Finally, the potential applications in yield estimation from UAV-based imagery from agronomy experiments and scouting of production fields are also discussed.

AB - Sorghum (Sorghum bicolor L. Moench) is a C4 tropical grass that plays an essential role in providing nutrition to humans and livestock, particularly in marginal rainfall environments. The timing of head development and the number of heads per unit area are key adaptation traits to consider in agronomy and breeding but are time consuming and labor intensive to measure. We propose a two-step machine-based image processing method to detect and count the number of heads from high-resolution images captured by unmanned aerial vehicles (UAVs) in a breeding trial. To demonstrate the performance of the proposed method, 52 images were manually labeled; the precision and recall of head detection were 0.87 and 0.98, respectively, and the coefficient of determination (R2) between the manual and new methods of counting was 0.84. To verify the utility of the method in breeding programs, a geolocation-based plot segmentation method was applied to pre-processed ortho-mosaic images to extract >1000 plots from original RGB images. Forty of these plots were randomly selected and labeled manually; the precision and recall of detection were 0.82 and 0.98, respectively, and the coefficient of determination between manual and algorithm counting was 0.56, with the major source of error being related to the morphology of plants resulting in heads being displayed both within and outside the plot in which the plants were sown, i.e., being allocated to a neighboring plot. Finally, the potential applications in yield estimation from UAV-based imagery from agronomy experiments and scouting of production fields are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=85058787073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058787073&partnerID=8YFLogxK

U2 - 10.3389/fpls.2018.01544

DO - 10.3389/fpls.2018.01544

M3 - Article

AN - SCOPUS:85058787073

VL - 871

JO - Frontiers in Plant Science

JF - Frontiers in Plant Science

SN - 1664-462X

M1 - 1544

ER -