Weed detection in cabbage fields using RGB and NIR images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41310%2F25%3A102590" target="_blank" >RIV/60460709:41310/25:102590 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/60460709:41110/25:102590 RIV/60460709:41210/25:102590

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2772375525004630" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2772375525004630</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.atech.2025.101232" target="_blank" >10.1016/j.atech.2025.101232</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Weed detection in cabbage fields using RGB and NIR images

Popis výsledku v původním jazyce

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 ([email protected]) 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, [email protected] 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.

Název v anglickém jazyce

Weed detection in cabbage fields using RGB and NIR images

Popis výsledku anglicky

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 ([email protected]) 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, [email protected] 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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40106 - Agronomy, plant breeding and plant protection; (Agricultural biotechnology to be 4.4)

Projekt

<a href="/cs/project/QK22010348" target="_blank" >QK22010348: Autonomní systémy jako nástroje integrované produkce zeleniny.</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

SMART AGRICULTURAL TECHNOLOGY

ISSN

2772-3755

e-ISSN

2772-3755

Svazek periodika

12

Číslo periodika v rámci svazku

DEC 2025

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

8

Strana od-do

—

Kód UT WoS článku

001543354000001

EID výsledku v databázi Scopus

2-s2.0-105011945408