This study aimed to produce a robust real-time pear fruit counter for mobile applications using only RGB data, the variants of the state-of-the-art object detection model YOLOv4, and the multiple object-tracking algorithm Deep SORT. This study also provided a systematic and pragmatic methodology for choosing the most suitable model for a desired application in agricultural sciences. In terms of accuracy, YOLOv4-CSP was observed as the optimal model, with an AP@0.50 of 98%. In terms of speed and computational cost, YOLOv4-tiny was found to be the ideal model, with a speed of more than 50 FPS and FLOPS of 6.8–14.5. If considering the balance in terms of accuracy, speed and computational cost, YOLOv4 was found to be most suitable and had the highest accuracy metrics while satisfying a real time speed of greater than or equal to 24 FPS. Between the two methods of counting with Deep SORT, the unique ID method was found to be more reliable, with an F1count of 87.85%. This was because YOLOv4 had a very low false negative in detecting pear fruits. The ROI line is more reliable because of its more restrictive nature, but due to flickering in detection it was not able to count some pears despite their being detected.

The real-time object detection system You Only Look Once (specifically YOLOv3) has recently shown remarkable speed, making it potentially suitable for Unmanned Aerial Vehicle (UAV) precision spraying. In this study, YOLO-WEED, a weed detection system based on YOLOv3, was developed. The dataset, derived from a five-minute UAV video, was split into a 69 : 17 : 13 ratio for training, validation, and testing, respectively. YOLO-WEED demonstrated a real-time detection speed (up to 24.4 FPS) and high performance using NVIDIA GeForce GTX 1060, with a mean average precision of 93.81 % and an F1 score of 0.94. These results successfully show the effectiveness of the YOLO-WEED system for real-time UAV weed detection, given its high speed and high accuracy in detection.[Keywords] you only look once (YOLO), deep learning, real time weed detection, convolutional neural network (CNN), unmanned aerial vehicle

No abstract