Design of Weed Detection Technique Using Yolo Models

• Published in: 2024 IEEE Students Conference on Engineering and Systems (SCES) pp. 1 - 6
• Main Authors: M, Sreehari, Jain, Ankur
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21.06.2024
• Subjects: Accuracy; ADAM; Analytical models; Ensemble learning; mean average precision; object detection; precision; recall; Reliability; SGD; Stochastic processes; Task analysis; weed detection; YOLO; YOLOv7; YOLOv8
• DOI: 10.1109/SCES61914.2024.10652564

The use of the ADAM (Adaptive Moment Estimation) and SGD (Stochastic Gradient Descent) algorithms to optimize the YOLOv7(You Only Look Once), YOLOv8, and YOLO-NAS models for weed detection in agricultural landscapes is investigated in this study. Offering a thorough comparative study based on mean Average Precision (mAP), recall, and precision measures is the goal. When compared to YOLOv7, YOLOv8 regularly performs better, exhibiting balanced recall and higher precision. With remarkable mAP scores at IOU (Intersection Over Union) 0.50, YOLOv8 ADAM in particular sticks out, demonstrating strong weed identification abilities. The YOLOv7 ADAM exhibits a precision-recall trade-off, with precision being slightly sacrificed for recall. Model superiority is not solely determined by the optimization algorithm used (ADAM vs. SGD); YOLOv8 variations perform admirably. For real-world implementation, practical factors like processing efficiency and deployment viability are even more important than quantitative criteria. This work establishes the foundation for comprehending the complex trade-offs and advantages that are present in every model and algorithm, in addition to helping with the educated selection of the best YOLO models for weed detection. Future research directions in object detection in agriculture, including ensemble techniques and hyperparameter tuning, promise more advancements in this subject as technology develops.