.png){kind=icon}
.png){kind=icon}
Return
Postharvest moisture-level classification using LiDAR point clouds: Integrating 3D structure and spectral intensity
.png){kind=icon}
OA
AI
M
A
B
V
M
M
DOI：10.1016/j.compag.2026.112262.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Dual-wavelength LiDAR enables non-invasive moisture classification in produce. • First public 3D LiDAR dataset for moisture classification in vegetables. • Fusion of geometry and intensity improves prediction accuracy up to 0.93. • 1450 nm intensity provides the strongest moisture-sensitive signal. • Core-trained models generalize better to periphery than the reverse.
Keywords:
Non-invasive food monitoring
Food security
PointNet
Decision support in food systems
AI in food systems
Sustainable food systems
Journal
IF:
8.9
Papers:
9.9K
Citations:
4.8W
Organization
Cited Papers