TY - GEN
T1 - Drone-Based Tomato Fruit Detection Through Hardware-Accelerated YOLO Deployment
AU - Kafi, Abdellah Islam
AU - Sanfilippo, Antonio P.
AU - Jovanovic, Raka
AU - Shannak, Sa’d Abdel Halim
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In this paper, we develop a drone-based solution for detecting productivity characteristics of tomato crops inside agricultural greenhouses using the YOLO8 computer vision model; a mobile phone is used to deploy the trained model. The implementation leverages the Apple Neural Engine (NE), a hardware accelerator module embedded in recent Apple mobile phones, to enable fast and efficient inference. Our video acquisition component also employs a DJI remote controller that streams live video from the drone to the mobile app for processing. The main objective is to perform rapid and precise detection of tomatoes within greenhouses, where drones can improve efficiency and coverage. We describe the model architecture and various optimization techniques suitable for embedded-platform deployment. The experimental study demonstrates the system’s effectiveness in detection accuracy and inference time when utilizing NE compared to CPU-based inference. We also compare accuracy, model size, and inference speed across variants of the YOLO algorithm.
AB - In this paper, we develop a drone-based solution for detecting productivity characteristics of tomato crops inside agricultural greenhouses using the YOLO8 computer vision model; a mobile phone is used to deploy the trained model. The implementation leverages the Apple Neural Engine (NE), a hardware accelerator module embedded in recent Apple mobile phones, to enable fast and efficient inference. Our video acquisition component also employs a DJI remote controller that streams live video from the drone to the mobile app for processing. The main objective is to perform rapid and precise detection of tomatoes within greenhouses, where drones can improve efficiency and coverage. We describe the model architecture and various optimization techniques suitable for embedded-platform deployment. The experimental study demonstrates the system’s effectiveness in detection accuracy and inference time when utilizing NE compared to CPU-based inference. We also compare accuracy, model size, and inference speed across variants of the YOLO algorithm.
KW - Drone
KW - Live video streaming
KW - Neural engine
KW - Tomato detection
KW - YOLO
UR - https://www.scopus.com/pages/publications/105020024123
U2 - 10.1007/978-981-96-6438-2_35
DO - 10.1007/978-981-96-6438-2_35
M3 - Conference contribution
AN - SCOPUS:105020024123
SN - 9789819664375
T3 - Lecture Notes in Networks and Systems
SP - 507
EP - 519
BT - Proceedings of 10th International Congress on Information and Communication Technology - ICICT 2025
A2 - Yang, Xin-She
A2 - Sherratt, Simon
A2 - Dey, Nilanjan
A2 - Joshi, Amit
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th International Congress on Information and Communication Technology, ICICT 2025
Y2 - 18 February 2025 through 21 February 2025
ER -