Revolutionizing Plant Phenotyping: 3d Plant Shoot Segmentation With Deep Learning

This article discusses the development of a weakly supervised deep learning framework for plant organ segmentation, called Eff-3DPSeg. This framework was tested on a newly created, well-labeled large-scale soybean spatiotemporal dataset, capturing various growth stages. The results demonstrated robust generalization and accuracy in stem-leaf segmentation, with some misclassifications at junctions and leaf edges. The framework performed better on simpler plant structures and had a higher accuracy with more training data.