Using t-distributed stochastic neighbor embedding for visualization and segmentation of 3D point clouds of plants
This work addresses the challenge of processing 3D plant data for phenotyping, offering a visualization and segmentation approach that could benefit plant scientists, but it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of visualizing and segmenting 3D point clouds of plants by using t-SNE to embed them into 2D space, demonstrating its potential as a tool for plant characterization and enabling semantic and instance segmentation through simple methods on a public dataset.
In this work, the use of t-SNE is proposed to embed 3D point clouds of plants into 2D space for plant characterization. It is demonstrated that t-SNE operates as a practical tool to flatten and visualize a complete 3D plant model in 2D space. The perplexity parameter of t-SNE allows 2D rendering of plant structures at various organizational levels. Aside from the promise of serving as a visualization tool for plant scientists, t-SNE also provides a gateway for processing 3D point clouds of plants using their embedded counterparts in 2D. In this paper, simple methods were proposed to perform semantic segmentation and instance segmentation via grouping the embedded 2D points. The evaluation of these methods on a public 3D plant data set conveys the potential of t-SNE for enabling of 2D implementation of various steps involved in automatic 3D phenotyping pipelines.