Deep Learning Tracks Cabbage Growth From Seedling to Harvest in 3D
· newswise.com · popularity 16/100 · 0 similar stories today · Machine Learning Research (Artificial Intelligence)
Read the original at newswise.com →
Summary
Monitoring the growth dynamics of field-grown cabbage is essential for stable vegetable production and precision agriculture. Conventional two-dimensional (2D) imaging captures only planar projection information and lacks spatial structural detail, limiting its ability to support high-precision, full-cycle phenotyping in open-field conditions. To address this, researchers constructed a high-precision three-dimensional (3D) point cloud dataset covering the period from seedling to maturity using depth cameras and multi-view spatial registration. Building on this dataset, they proposed an adaptive point cloud segmentation network for whole-cycle growth monitoring, incorporating a Head Refinement Module (HRM), a Leaf Instance Segmentation Module (LISM), and Cross Module Interaction (CMI) to handle leaf adhesion and head boundary delineation. Growth parameters extracted from segmentation results showed strong agreement with ground-truth measurements.
Found in: Newswise. Rating basis: single outlet; outlet tier 2 (unlisted); 1 feeds; feed position 17.