Three-dimensional branch segmentation and phenotype extraction of maize tassel based on deep learning

Abstract

Background The morphological structure phenotype of maize tassel plays an important role in plant growth, reproduction, and yield formation. It is an important step in the distinctness, uniformity, and stability (DUS) testing to obtain maize tassel phenotype traits. Plant organ segmentation can be achieved with high-precision and automated acquisition of maize tassel phenotype traits because of the advances in the point cloud deep learning method. However, this method requires a large number of data sets and is not robust to automatic segmentation of highly adherent organ components; thus, it should be combined with point cloud processing technology. Results An innovative method of incomplete annotation of point cloud data was proposed for easy development of the dataset of maize tassels,and an automatic maize tassel phenotype analysis system: MaizeTasselSeg was developed. The tip feature of point cloud is trained and learned based on PointNet + + network, and the tip point cloud of tassel branch was automatically segmented. Complete branch segmentation was realized based on the shortest path algorithm. The Intersection over Union (IoU), precision, and recall of the segmentation results were 96.29, 96.36, and 93.01, respectively. Six phenotypic traits related to morphological structure (branch count, branch length, branch angle, branch curvature, tassel volume, and dispersion) were automatically extracted from the segmentation point cloud. The squared correlation coefficients (R2) for branch length, branch angle, and branch count were 0.9897, 0.9317, and 0.9587, respectively. The root mean squared error (RMSE) for branch length, branch angle, and branch count were 0.529 cm, 4.516, and 0.875, respectively. Conclusion The proposed method provides an efficient scheme for high-throughput organ segmentation of maize tassels and can be used for the automatic extraction of phenotypic traits of maize tassel. In addition, the incomplete annotation approach provides a new idea for morphology-based plant segmentation.

Deep Learning-Based High-Throughput Phenotyping Of Maize (Zea maysL.) Tasseling From Uas Imagery Across Environments

“…Correlation (r 2 ) between DTT and DTA based on the data in Lima et al (2023) was found to be 0.71 (Figure 3). ANOVA was performed on trials all using the same genotypes (TXH1, TXH2, TXH3, and WIH2 datasets) for DTT and DTA (Table 3a), as well as for WIH1…”

“…Previous DL applications in automated phenotyping have primarily been limited to controlled environment or ground-based field image acquisitions, which are often stationary, manually operated, or otherwise impractical for adoption at scales needed in genetic and breeding studies (Ye et al 2012 Mirnezami et al 2021, Shao et al 2023). Studies employing deep learning techniques have shown promise in automating phenotyping tasks such as maize tassel morphology and development (Yu et al 2022, Zhang et al 2023), tassel counts (Lu et al 2017, Lu et al 2020, Zan et al 2020), and the effect of tassels on leaf area index estimation using vegetation indices (Shao et al 2023). However, these methods are constrained by either their destructive or non-scalable methodology or datasets to the thousands of diverse plots screened in field breeding and genetics programs (Alzadjali et al 2021).…”