Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring Accurate 3D Phenotyping in Greenhouse through Neural Radiance Fields

Junhong Zhao, Wei Ying, Yaoqiang Pan, Zhenfeng Yi, Chao Chen, Kewei Hu, Hanwen Kang

TL;DR

Experimental result shows that NeRF(Neural Radiance Fields) achieves competitive accuracy compared to the 3D scanning methods, and shows that the learning-based NeRF method achieves similar accuracy to 3D scanning-based methods but with improved scalability and robustness.

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 the Neural Radiance Field 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 NeRF(Neural Radiance Fields) achieves competitive accuracy compared to the 3D scanning methods. The mean distance error between the scanner-based method and the NeRF-based method is 0.865mm. This study shows that the learning-based NeRF method achieves similar accuracy to 3D scanning-based methods but with improved scalability and robustness.

Exploring Accurate 3D Phenotyping in Greenhouse through Neural Radiance Fields

TL;DR

Experimental result shows that NeRF(Neural Radiance Fields) achieves competitive accuracy compared to the 3D scanning methods, and shows that the learning-based NeRF method achieves similar accuracy to 3D scanning-based methods but with improved scalability and robustness.

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 the Neural Radiance Field 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 NeRF(Neural Radiance Fields) achieves competitive accuracy compared to the 3D scanning methods. The mean distance error between the scanner-based method and the NeRF-based method is 0.865mm. This study shows that the learning-based NeRF method achieves similar accuracy to 3D scanning-based methods but with improved scalability and robustness.
Paper Structure (25 sections, 11 equations, 10 figures, 5 tables)

This paper contains 25 sections, 11 equations, 10 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Plant Phenotyping
  4. Explicit Modelling Approaches
  5. Implicit Modelling Approaches
  6. Methodologies
  7. Data Acquisition System
  8. 3D modelling from NeRF
  9. Reconstruction from Neural Radiance Fields
  10. 3D modelling from Point Cloud Registration
  11. Post-processing for Phenotyping Measurement
  12. 3D Pepper Detection on Point Cloud
  13. Measurement of Phenotypic data
  14. Experiment and Discussion
  15. Experimental setup
  16. ...and 10 more sections

Figures (10)

  • Figure 1: Phenotyping results by respectively using the 3D scanner and NeRF reconstruction in the greenhouse by robots.
  • Figure 2: NeRF Scale Restoration Process Pipeline.
  • Figure 3: Neural Radiance Fields Method.
  • Figure 4: Illustration of our proposed 3D semantic segmentation method. (a) Input data are point cloud data extracted from 3D scanner reconstruction and NeRF reconstruction. (b) The input point cloud is segmented by the segmentation module. (c) Finally the segmentation result is obtained.
  • Figure 5: Illustrations of the standard scenarios for the agriculture and collection facilities.
  • ...and 5 more figures