Automated Stem Angle Determination for Temporal Plant Phenotyping Analysis

Sruti Das Choudhury, Saptarsi Goswami, Srinidhi Bashyam, Ashok Samal, Tala Awada; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2022-2029

Extracting meaningful phenotypes for temporal plant phenotyping analysis by considering individual parts of a plant, e.g., leaves and stem, using computer vision techniques remains a critical bottleneck due to constantly increasing complexity in plant architecture with variations in self-occlusions and phyllotaxy. The paper introduces an algorithm to compute stem angle for use as a measure of plants' susceptibility to lodging. It involves the identification of leaf-tips and leaf-junctions based on graph theoretic analysis. The efficacy of the proposed method is demonstrated based on a public dataset called Panicoid Phenomap-1. A time-series clustering analysis is performed on stem angle values during vegetative stage life cycle of the maize plants. This analysis summarizes the temporal patterns of the stem angles into three main groups, and establishes that the temporal variation of the stem angles is likely to be regulated by genetic variation under similar environmental conditions.