Key points are not available for this paper at this time.
Tomatoes are widely used in India for daily meals and are very sensitive to environmental changes, pests, and diseases, which can have a significant impact on the growth and productivity of the crop. To address these issues, it is important to monitor plant growth. This paper presents the design and implementation of a real-time tomato growth-monitoring system based on a deep learning YOLO model and Raspberry Pi. The system leverages the YOLOv8 architecture for accurate detection and classification of the tomato plant growth stage and anomalies in real time. The Raspberry Pi serves as the central processing unit, integrating camera sensor data and image analysis to provide a cost-effective, portable, and scalable solution. This system incorporates high-resolution cameras to capture real-time images. The proposed system demonstrated high accuracy in detecting various growth stages and facilitating timely interventions. This technology provides an efficient and automated approach to precision agriculture, enabling farmers to optimize resource utilization, improve yields, and reduce the environmental footprint of tomato cultivation. The performance and feasibility of the system were validated through extensive testing in controlled and open-field environments, highlighting its potential for adoption in smart agriculture.
Sharma et al. (Mon,) studied this question.