Авторы:
Издательство:
Дата издания
27.04.2026На каком языке издана
ISSN
2227-7080Область исследования
Тип исследования
Аннотация (краткое описание)
Computer vision–based weed detection plays a critical role in agricultural robotics, enabling accurate, selective weeding. These systems operate on resource-constrained embedded platforms, which introduces a significant trade-off between accuracy and efficiency. This study presents a comparative evaluation of six detection models (YOLOv11n, YOLOv11s, SSDLite, NanoDet, Faster R-CNN, RT-DETR) for agro-robotic applications, measuring precision, recall, mAP@0.5, and runtime on low-power hard-ware. NanoDet achieved the highest detection accuracy (precision 98.6%, recall 94.2%, mAP@0.5 97.7%). YOLOv11s demonstrated similar performance (mAP@0.5: 96.1%) but required more computation. YOLOv11n provides the most favourable balance between accuracy and throughput (mAP@0.5: 94.6%, 207 FPS on a workstation). On Raspberry Pi 5, light models achieved 3–5 FPS. RT-DETR and Faster R-CNN exhibited high latency (3112–6500 ms/frame), which prevents real-time operation. NanoDet excelled in detection, while YOLOv11n provides the best balance between accuracy and efficiency for limited devices.DOI
https://doi.org/10.3390/technologies14050265Тип публикаций
Практическое значение
The practical significance of this study lies in improving the efficiency and reliability of computer vision systems used in agricultural robotics for weed detection and precision farming. The comparative evaluation of modern object detection models enables the selection of optimal algorithms that balance accuracy and computational efficiency, which is critical for deployment on resource-constrained embedded platforms. The results demonstrate that lightweight models such as YOLOv11n and NanoDet are suitable for real-time or near-real-time operation in field conditions, where processing power and energy consumption are limited. This allows agricultural robots to perform selective weeding more accurately, reducing the need for chemical herbicides and supporting more sustainable farming practices. From a practical standpoint, the study provides clear guidance for integrating AI-based detection systems into autonomous agricultural machinery. It helps engineers and developers choose appropriate models depending on hardware capabilities, ensuring reliable performance on devices such as Raspberry Pi-based platforms. Overall, the findings contribute to the advancement of precision agriculture by enabling more efficient crop management, reducing operational costs, minimizing environmental impact, and improving crop yield through targeted weed control.Квартиль
Источник квартиля
JCR (WoS)Impact Factor
3.6Количество цитирований
0Данный документ располагается в коллекциях
Международные публикации ученых SU
Scopus
Файлы документа
technologies-14-00265-v2 (1).pdf