Journal
IEEE ACCESS
Volume 10, Issue -, Pages 77263-77271Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3192028
Keywords
Spraying; Laser radar; Point cloud compression; Three-dimensional displays; Size measurement; Measurement by laser beam; Solid modeling; Drift; deep leraning; moblie LiDAR; intelligent spraying system
Categories
Funding
- Cooperative Research Program or Agriculture Science and Technology Development [PJ0150532021]
- Rural Development Administration, Republic of Korea
Ask authors/readers for more resources
This study proposes a novel spray drift analysis method using 3D deep learning and a mobile LiDAR method to manage and reduce spray drift. LiDAR point clouds were trained with the PointNet++ model to classify and segment spraying forms in orchards, achieving an accuracy of 96.23%. The efficacy of the system was demonstrated through field experiments in a pear orchard, confirming the satisfactory performance of the 3D deep learning-based spray drift analysis method. It is expected that this system can effectively measure and manage spray drift.
This study proposes a novel spray drift analysis method, based on 3D deep learning, managing and reducing spray drift using a mobile LiDAR method. LiDAR point clouds were trained to classify and segment spraying forms from orchards using the PointNet++ model, which is a 3D deep learning structure. The trained deep learning model represented an accuracy of 96.23%. The spray drift analysis system was demonstrated through its application in intelligent spraying systems. Three control field experiments were performed in a pear orchard to verify the effectiveness of the system. The obtained results confirm the satisfactory performance of 3D deep learning-based spray drift analysis method. It is expected that the proposed system can measure and manage spray drift.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available