Weed detection in cabbage fields using RGB and NIR images

This article evaluates the effectiveness of integrating near-infrared (NIR) data with RGB imaging in enhancing weed detection and classification in real-time field settings using the YOLO deep learning model family. Data was gathered from sown weed plots and various locations across Bohemia to docum...

Full description

Saved in:
Bibliographic Details
Main Authors: Adam Hruška, Pavel Hamouz, Jakub Lev, Josef Pavlíček, Milan Kroulík, Kateřina Hamouzová, Pavlína Košnarová, Josef Holec, Pavel Kouřím
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525004630
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849247333103960064
author Adam Hruška
Pavel Hamouz
Jakub Lev
Josef Pavlíček
Milan Kroulík
Kateřina Hamouzová
Pavlína Košnarová
Josef Holec
Pavel Kouřím
author_facet Adam Hruška
Pavel Hamouz
Jakub Lev
Josef Pavlíček
Milan Kroulík
Kateřina Hamouzová
Pavlína Košnarová
Josef Holec
Pavel Kouřím
author_sort Adam Hruška
collection DOAJ
description This article evaluates the effectiveness of integrating near-infrared (NIR) data with RGB imaging in enhancing weed detection and classification in real-time field settings using the YOLO deep learning model family. Data was gathered from sown weed plots and various locations across Bohemia to document diverse plant phenotypes under different field conditions. A multispectral RGB+NIR camera combined with an LED flashlight system was used for imaging. Besides the cabbage crop, 13 weed classes were classified in the images using various YOLO models. The YOLOv10l model provided the best classification results. The use of RGB+NIR data in training resulted in the mean average precision (mAP@0.5) value of 94.9 %, compared to 94.5 % for RGB-only images, underscoring NIR’s benefits in weed detection. When calculated exclusively for sown species, mAP@0.5 of 97.8 % was achieved for RGB+NIR data. The addition of the NIR images not only increased the classification accuracy but also improved semi-automated annotation efficiency, facilitating faster dataset preparation. These results suggest that NIR-enhanced YOLOv10l holds potential for precision agriculture, enabling targeted interventions that reduce herbicide use. Future research will focus on expanding model adaptability and accessibility for broader agricultural applications.
format Article
id doaj-art-8e4d14bf29e049a68bcd564678fcba67
institution Kabale University
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-8e4d14bf29e049a68bcd564678fcba672025-08-20T03:58:14ZengElsevierSmart Agricultural Technology2772-37552025-12-011210123210.1016/j.atech.2025.101232Weed detection in cabbage fields using RGB and NIR imagesAdam Hruška0Pavel Hamouz1Jakub Lev2Josef Pavlíček3Milan Kroulík4Kateřina Hamouzová5Pavlína Košnarová6Josef Holec7Pavel Kouřím8Czech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCorresponding author.; Czech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicCzech University of Life Sciences Prague, Kamýcká 129, Prague 165 00, Czech RepublicThis article evaluates the effectiveness of integrating near-infrared (NIR) data with RGB imaging in enhancing weed detection and classification in real-time field settings using the YOLO deep learning model family. Data was gathered from sown weed plots and various locations across Bohemia to document diverse plant phenotypes under different field conditions. A multispectral RGB+NIR camera combined with an LED flashlight system was used for imaging. Besides the cabbage crop, 13 weed classes were classified in the images using various YOLO models. The YOLOv10l model provided the best classification results. The use of RGB+NIR data in training resulted in the mean average precision (mAP@0.5) value of 94.9 %, compared to 94.5 % for RGB-only images, underscoring NIR’s benefits in weed detection. When calculated exclusively for sown species, mAP@0.5 of 97.8 % was achieved for RGB+NIR data. The addition of the NIR images not only increased the classification accuracy but also improved semi-automated annotation efficiency, facilitating faster dataset preparation. These results suggest that NIR-enhanced YOLOv10l holds potential for precision agriculture, enabling targeted interventions that reduce herbicide use. Future research will focus on expanding model adaptability and accessibility for broader agricultural applications.http://www.sciencedirect.com/science/article/pii/S2772375525004630Weed detectionComputer visionYoloRGB+NIR imagingVegetables
spellingShingle Adam Hruška
Pavel Hamouz
Jakub Lev
Josef Pavlíček
Milan Kroulík
Kateřina Hamouzová
Pavlína Košnarová
Josef Holec
Pavel Kouřím
Weed detection in cabbage fields using RGB and NIR images
Smart Agricultural Technology
Weed detection
Computer vision
Yolo
RGB+NIR imaging
Vegetables
title Weed detection in cabbage fields using RGB and NIR images
title_full Weed detection in cabbage fields using RGB and NIR images
title_fullStr Weed detection in cabbage fields using RGB and NIR images
title_full_unstemmed Weed detection in cabbage fields using RGB and NIR images
title_short Weed detection in cabbage fields using RGB and NIR images
title_sort weed detection in cabbage fields using rgb and nir images
topic Weed detection
Computer vision
Yolo
RGB+NIR imaging
Vegetables
url http://www.sciencedirect.com/science/article/pii/S2772375525004630
work_keys_str_mv AT adamhruska weeddetectionincabbagefieldsusingrgbandnirimages
AT pavelhamouz weeddetectionincabbagefieldsusingrgbandnirimages
AT jakublev weeddetectionincabbagefieldsusingrgbandnirimages
AT josefpavlicek weeddetectionincabbagefieldsusingrgbandnirimages
AT milankroulik weeddetectionincabbagefieldsusingrgbandnirimages
AT katerinahamouzova weeddetectionincabbagefieldsusingrgbandnirimages
AT pavlinakosnarova weeddetectionincabbagefieldsusingrgbandnirimages
AT josefholec weeddetectionincabbagefieldsusingrgbandnirimages
AT pavelkourim weeddetectionincabbagefieldsusingrgbandnirimages