Towards Low-Cost Hyperspectral Single-Pixel Imaging for Plant Phenotyping

Abstract

Hyperspectral imaging techniques have been expanding considerably in recent years. The cost of current solutions is decreasing, but these high-end technologies are not yet available for moderate to low-cost outdoor and indoor applications. We have used some of the latest compressive sensing methods with a single-pixel imaging setup. Projected patterns were generated on Fourier basis, which is well-known for its properties and reduction of acquisition and calculation times. A low-cost, moderate-flow prototype was developed and studied in the laboratory, which has made it possible to obtain metrologically validated reflectance measurements using a minimal computational workload. From these measurements, it was possible to discriminate plant species from the rest of a scene and to identify biologically contrasted areas within a leaf. This prototype gives access to easy-to-use phenotyping and teaching tools at very low-cost.

Plant phenotyping relevance

低コスト単一画素ハイパースペクトル撮像プロトタイプを開発し、反射率測定を計量学的に検証して植物フェノタイピングへの利用を示しており、測定手法が研究の中心である。

Code and data availability

The paper's supplementary materials publicly host the two hyperspectral hypercube datasets (leaf discrimination and leaf health-state experiments) directly used for the paper's phenotyping measurements, and the authors' acquisition/reconstruction MATLAB scripts are publicly available on a GitHub repository. Both are on