Drought Stress Classification using 3D Plant Models

Abstract

Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner. In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images. In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study. To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants. The drought stress is characterized with a deep network based feature aggregation. We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods.

Plant phenotyping relevance

植物キャノピーの3D再構成、セグメンテーション、特徴抽出、乾燥ストレス評価を統合した画像ベースの表現型解析パイプラインが研究の中心であるため。

Code and data availability

The paper describes a wheat drought-stress dataset (3,200 images, 34 plants) and a fine-tuned PointNet pipeline, but contains no public dataset deposit, code release, or availability statement with an authors' URL. No qualifying paper-specific public asset is present in the supplied blocks.

No evidence-backed public reproduction asset is currently recorded.