Search papers, labs, and topics across Lattice.
This paper introduces a UAV-based system for automated fruit detection and counting in controlled agricultural environments, leveraging fine-tuned YOLOv8 for fruit detection and a hybrid A* TSP algorithm for efficient 3D path planning in simulation. To address real-world challenges, the system incorporates LiDAR-based mapping and point cloud filtering to prevent recounting. Experiments demonstrate high fruit counting accuracy, achieving 98% in simulation and 90% in real-world tests, validated by a strong performance in the ICUAS UAV Competition 2024.
Achieve near-perfect fruit counts with drones: a new system nails 98% accuracy in simulation and 90% in real-world agricultural settings.
This paper presents a solution for high accuracy fruit counting in a Controlled Environment Agriculture (CEA) settings using Unmanned Aerial Vehicles (UAV) implemented in simulation and real-world scenarios. Using the fine-tuned YOLOv8 [1] model for precise object detection and classification along with a custom path planning algorithm for simulation. This approach integrates a hybrid A* Traveling Salesman Problem (TSP) algorithm for efficient 3D path planning. The solution is further extended to the real-life scenario using LiDAR based mapping and point-cloud filtering techniques to avoid recounting of fruits. The suggested methodology increases operating efficiency, reduces dependency on human labor, and improves accuracy. Experimental results, derived from both simulations and real-world testing, achieving a fruitcount accuracy of 98 % and 90 % respectively, demonstrate the effectiveness of this integrated approach. This solution was implemented in the International Conference of Unmanned Aircraft System (ICUAS) [2] UAV Competition 2024, securing $2^{\text {nd }}$ position in the simulation phase (out of 24 teams) and $3^{\text {rd }}$ overall in the real-world phase.
