Upper Limit for Context--based Crop Classification in Robotic Weeding Applications

Henrik Skov Midtiby, Björn Åstrand, Ole Jørgensen, Rasmus Nyholm Jørgensen

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

120 Downloads (Pure)

Resumé

Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density (ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σx and σy, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσxσy)−1. This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials.
OriginalsprogEngelsk
TidsskriftBiosystems Engineering
Vol/bind146
Sider (fra-til)183-192
ISSN1537-5110
DOI
StatusUdgivet - 15. feb. 2016

Citer dette

Midtiby, Henrik Skov ; Åstrand, Björn ; Jørgensen, Ole ; Jørgensen, Rasmus Nyholm. / Upper Limit for Context--based Crop Classification in Robotic Weeding Applications. I: Biosystems Engineering. 2016 ; Bind 146. s. 183-192.
@article{7f1fab48e3af49d9bbef1f9bd1ad78d3,
title = "Upper Limit for Context--based Crop Classification in Robotic Weeding Applications",
abstract = "Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density (ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σx and σy, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσxσy)−1. This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials.",
author = "Midtiby, {Henrik Skov} and Bj{\"o}rn {\AA}strand and Ole J{\o}rgensen and J{\o}rgensen, {Rasmus Nyholm}",
year = "2016",
month = "2",
day = "15",
doi = "10.1016/j.biosystemseng.2016.01.012",
language = "English",
volume = "146",
pages = "183--192",
journal = "Biosystems Engineering",
issn = "1537-5110",
publisher = "Heinemann",

}

Upper Limit for Context--based Crop Classification in Robotic Weeding Applications. / Midtiby, Henrik Skov; Åstrand, Björn; Jørgensen, Ole; Jørgensen, Rasmus Nyholm.

I: Biosystems Engineering, Bind 146, 15.02.2016, s. 183-192.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Upper Limit for Context--based Crop Classification in Robotic Weeding Applications

AU - Midtiby, Henrik Skov

AU - Åstrand, Björn

AU - Jørgensen, Ole

AU - Jørgensen, Rasmus Nyholm

PY - 2016/2/15

Y1 - 2016/2/15

N2 - Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density (ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σx and σy, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσxσy)−1. This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials.

AB - Knowledge of the precise position of crop plants is a prerequisite for effective mechanical weed control in robotic weeding application such as in crops like sugar beets which are sensitive to mechanical stress. Visual detection and recognition of crop plants based on their shapes has been described many times in the literature. In this paper the potential of using knowledge about the crop seed pattern is investigated based on simulated output from a perception system. The reliability of position–based crop plant detection is shown to depend on the weed density (ρ, measured in weed plants per square metre) and the crop plant pattern position uncertainty (σx and σy, measured in metres along and perpendicular to the crop row, respectively). The recognition reliability can be described with the positive predictive value (PPV), which is limited by the seeding pattern uncertainty and the weed density according to the inequality: PPV ≤ (1 + 2πρσxσy)−1. This result matches computer simulations of two novel methods for position–based crop recognition as well as earlier reported field–based trials.

U2 - 10.1016/j.biosystemseng.2016.01.012

DO - 10.1016/j.biosystemseng.2016.01.012

M3 - Journal article

VL - 146

SP - 183

EP - 192

JO - Biosystems Engineering

JF - Biosystems Engineering

SN - 1537-5110

ER -