High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding
Precision weeding can significantly reduce or even eliminate the use of herbicides in farming. To achieve high-precision, individual targeting of weeds, high-speed, low-cost plant identification is essential. Our system using the red, green, and near-infrared reflectance, combined with a size differ...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/2/455 |
id |
doaj-ebe7decb7ce0421fbadee65f1d067086 |
---|---|
record_format |
Article |
spelling |
doaj-ebe7decb7ce0421fbadee65f1d0670862020-11-25T02:05:45ZengMDPI AGSensors1424-82202020-01-0120245510.3390/s20020455s20020455High Speed Crop and Weed Identification in Lettuce Fields for Precision WeedingLydia Elstone0Kin Yau How1Samuel Brodie2Muhammad Zulfahmi Ghazali3William P. Heath4Bruce Grieve5School of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKSchool of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKSchool of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKSchool of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKSchool of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKSchool of Electrical and Electronic Engineering, The University of Manchester, Oxford Rd, Manchester M13 9PL, UKPrecision weeding can significantly reduce or even eliminate the use of herbicides in farming. To achieve high-precision, individual targeting of weeds, high-speed, low-cost plant identification is essential. Our system using the red, green, and near-infrared reflectance, combined with a size differentiation method, is used to identify crops and weeds in lettuce fields. Illumination is provided by LED arrays at 525, 650, and 850 nm, and images are captured in a single-shot using a modified RGB camera. A kinematic stereo method is utilised to compensate for parallax error in images and provide accurate location data of plants. The system was verified in field trials across three lettuce fields at varying growth stages from 0.5 to 10 km/h. In-field results showed weed and crop identification rates of 56% and 69%, respectively. Post-trial processing resulted in average weed and crop identifications of 81% and 88%, respectively.https://www.mdpi.com/1424-8220/20/2/455precision weedingmultispectral imagingkinetic stereo imagingplant detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lydia Elstone Kin Yau How Samuel Brodie Muhammad Zulfahmi Ghazali William P. Heath Bruce Grieve |
spellingShingle |
Lydia Elstone Kin Yau How Samuel Brodie Muhammad Zulfahmi Ghazali William P. Heath Bruce Grieve High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding Sensors precision weeding multispectral imaging kinetic stereo imaging plant detection |
author_facet |
Lydia Elstone Kin Yau How Samuel Brodie Muhammad Zulfahmi Ghazali William P. Heath Bruce Grieve |
author_sort |
Lydia Elstone |
title |
High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding |
title_short |
High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding |
title_full |
High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding |
title_fullStr |
High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding |
title_full_unstemmed |
High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding |
title_sort |
high speed crop and weed identification in lettuce fields for precision weeding |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-01-01 |
description |
Precision weeding can significantly reduce or even eliminate the use of herbicides in farming. To achieve high-precision, individual targeting of weeds, high-speed, low-cost plant identification is essential. Our system using the red, green, and near-infrared reflectance, combined with a size differentiation method, is used to identify crops and weeds in lettuce fields. Illumination is provided by LED arrays at 525, 650, and 850 nm, and images are captured in a single-shot using a modified RGB camera. A kinematic stereo method is utilised to compensate for parallax error in images and provide accurate location data of plants. The system was verified in field trials across three lettuce fields at varying growth stages from 0.5 to 10 km/h. In-field results showed weed and crop identification rates of 56% and 69%, respectively. Post-trial processing resulted in average weed and crop identifications of 81% and 88%, respectively. |
topic |
precision weeding multispectral imaging kinetic stereo imaging plant detection |
url |
https://www.mdpi.com/1424-8220/20/2/455 |
work_keys_str_mv |
AT lydiaelstone highspeedcropandweedidentificationinlettucefieldsforprecisionweeding AT kinyauhow highspeedcropandweedidentificationinlettucefieldsforprecisionweeding AT samuelbrodie highspeedcropandweedidentificationinlettucefieldsforprecisionweeding AT muhammadzulfahmighazali highspeedcropandweedidentificationinlettucefieldsforprecisionweeding AT williampheath highspeedcropandweedidentificationinlettucefieldsforprecisionweeding AT brucegrieve highspeedcropandweedidentificationinlettucefieldsforprecisionweeding |
_version_ |
1724937077330542592 |