The Development of a Stereo Vision System to Study the Nutation Movement of Climbing Plants.

Abstract

Climbing plants, such as common beans ( Phaseolus vulgaris L.), exhibit complex motion patterns that have long captivated researchers. In this study, we introduce a stereo vision machine system for the in-depth analysis of the movement of climbing plants, using image processing and computer vision. Our approach involves two synchronized cameras, one lateral to the plant and the other overhead, enabling the simultaneous 2D position tracking of the plant tip. These data are then leveraged to reconstruct the 3D position of the tip. Furthermore, we investigate the impact of external factors, particularly the presence of support structures, on plant movement dynamics. The proposed method is able to extract the position of the tip in 86-98% of cases, achieving an average reprojection error below 4 px, which means an approximate error in the 3D localization of about 0.5 cm. Our method makes it possible to analyze how the plant nutation responds to its environment, offering insights into the interplay between climbing plants and their surroundings.

Plant phenotyping relevance

クライミング植物の先端位置とナテーション運動を抽出するステレオビジョン手法を開発し、抽出率と3D定位誤差を評価しており、植物フェノタイピング手法が研究の中心である。

Code and data availability

The paper's stereo-vision plant phenotyping data (time-lapse videos and 3D tip position measurements of climbing bean plants) are not publicly deposited; the Data Availability Statement requires contacting the authors. No author analysis code, models, or public dataset URLs are provided. The seed supplier website and a

No evidence-backed public reproduction asset is currently recorded.