Accurate 3D maize ear phenotyping using voxel grids derived from RGB machine vision
Leon H. Oehme, Tobias Schrag, Peng Qi, Bastian Stürmer-Stephan, Khandoker T. Ahammad, Daniel Wanke, Tobias Würschum, Xiongkui He, Joachim Müller · 2026
Read Accurate 3D maize ear phenotyping using voxel grids derived from RGB machine vision by Leon H. Oehme, Tobias Schrag, Peng Qi, Bastian Stürmer-Stephan, Khandoker T. Ahammad, Daniel Wanke, Tobias Würschum, Xiongkui He, Joachim Müller (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13571493.txt.
Description
Leon Oehme and eight co-authors build a three-space maize ear scan flow from color photos. Their study appeared in twenty twenty-six. Hand ear reads are slow and oft kill the ear, while past photo tools use few flat views. Their flow takes one hundred views per ear and stacks them into a voxel grid.
Learn models cut kernels out of flat views with high truth, then a map step lifts those cuts to space voxels. Counts of kernels, rows, and ear size all read near hand reads. Each ear took half a minute to tape and near a minute to run. A food dose test showed ear size shifts clear. Breed and food work are the aims.
Catalog record
| CREATOR | Leon H. Oehme, Tobias Schrag, Peng Qi, Bastian Stürmer-Stephan, Khandoker T. Ahammad, Daniel Wanke, Tobias Würschum, Xiongkui He, Joachim Müller |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |