Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping
This work addresses the challenge of automated plant phenotyping for agricultural or biological research, representing an incremental improvement by adapting existing methods to a new domain.
The paper tackles the problem of semantic labeling of 3D point clouds for plant phenotyping by employing a deep learning framework optimized for this specific task, achieving state-of-the-art results without the need for feature engineering.
Semantic labeling of 3D point clouds is important for the derivation of 3D models from real world scenarios in several economic fields such as building industry, facility management, town planning or heritage conservation. In contrast to these most common applications, we describe in this study the semantic labeling of 3D point clouds derived from plant organs by high-precision scanning. Our approach is optimized for the task of plant phenotyping with its very specific challenges and is employing a deep learning framework. Thereby, we report important experiences concerning detailed parameter initialization and optimization techniques. By evaluating our approach with challenging datasets we achieve state-of-the-art results without difficult and time consuming feature engineering as being necessary in traditional approaches to semantic labeling.