Accurate Fruit Phenotype Reconstruction via Geometry-Smooth Neural Implicit Surface

Abstract

Accurate collection of plant phenotyping is critical to optimising sustainable farming practices in precision agriculture. Traditional phenotyping in controlled laboratory environments, while valuable, falls short in understanding plant growth under real-world conditions. Emerging sensor and digital technologies offer a promising approach for direct phenotyping of plants in farm environments. This study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments. To quantitatively evaluate the performance of this method, traditional point cloud registration on 3D scanning data is implemented for comparison. Experimental result shows that NIR (neural implicit surfaces reconstruction) achieves competitive accuracy compared to the 3D scanning method. The mean distance error between the scanner-based method and the NeRF (neural radiance fields)-based method is 0.811 mm. This study shows that the learning-based NeRF method has similar accuracy to the 3D scanning-based method but with greater scalability and faster deployment capabilities.

Plant phenotyping relevance

植物の3D表現型を取得するNeRFベース手法を開発し、3Dスキャン法と精度比較・検証しており、表現型取得法が研究の中心である。

Code and data availability

The supplied article blocks describe a pepper greenhouse dataset (30 scenes of 2D images and 3D point clouds), the GS-NIR model, and a segmentation/measurement pipeline, but contain no data availability statement, no public dataset deposit, and no code availability or repository URL for the authors' analysis code or GS

No evidence-backed public reproduction asset is currently recorded.