Three-dimensional morphological reconstruction of potato leaf from a single image

Abstract

In the domain of plant morphological studies, three-dimensional scanning technologies have brought about a paradigm shift in the field of leaf structure modelling. Nevertheless, the high cost and operational complexity of these systems act as significant barriers to widespread adoption. To address this issue, a single-image 3D reconstruction pipeline was developed, focusing on potato leaves and optimized for use with mobile phone cameras. The algorithm begins with image preprocessing to enhance quality, followed by leaf instance segmentation to isolate the target leaf. Subsequently, a precise 2D leaf contour is extracted to capture planar geometry. Subsequently, 3D spatial features are recovered from a single image to infer depth information. Contour back-projection is a process that Links the extracted 2D contour to the estimated 3D space. The discretization of the 3D contour is enabled by boundary sampling, thereby facilitating the generation of an initial 3D polygonal mesh. Finally, mesh surface refinement is applied to optimize model accuracy and visual fidelity. The methodology employed in this study successfully reconstructed potato and other crop leaves, demonstrating minimal deviation in key morphological shape descriptors and negligible error in surface area measurements in comparison to the ground truth. The reconstructed models exhibited high geometric congruence with the original leaves. This demonstrates the potential of our technique to broaden the accessibility of conventional modelling approaches and to advance methodologies within the field of crop phenotyping.

Plant phenotyping relevance

単一画像から葉の3D形状を再構成し、形態形状記述子や表面積を推定・検証する手法開発であり、植物フェノタイピングが中心である。

Code and data availability

The paper's datasets are under embargo: the authors state they will be made publicly available on GitHub only after ongoing research concludes, with access requests directed to the corresponding author in the meantime. Code availability is declared 'not applicable', and no public URL, repository, or identifier for the

No evidence-backed public reproduction asset is currently recorded.