Abstract
Hyperspectral imaging has increasingly been used in high-throughput plant phenotyping systems. Rapid advancement in the field of phenotyping has resulted in a wide array of hyperspectral imaging systems. However, sharing the plant feature prediction models between different phenotyping facilities becomes challenging due to the differences in imaging environments and imaging sensors. Calibration transfer between imaging facilities is crucially important to cope with such changes. Spectral space adjustment methods including direct standardization (DS), its variants (PDS, DPDS) and spectral scale transformation (SST) require the standard samples to be imaged in different facilities. However, in real-world scenarios, imaging the standard samples is practically unattractive. Therefore, in this study, we presented three methods (TCA, c-PCA, and di-PLSR) to transfer the calibration models without requiring the standard samples. In order to compare the performance of proposed approaches, maize plants were imaged in two greenhouse-based HTPP systems using two pushbroom-style hyperspectral cameras covering the visible near-infrared range. We tested the proposed methods to transfer nitrogen content (N) and relative water content (RWC) calibration models. The results showed that prediction R2 increased by up to 14.50% and 42.20%, while the reduction in RMSEv was up to 74.49% and 76.72% for RWC and N, respectively. The di-PLSR achieved the best results for almost all the datasets included in this study, with TCA being second. The performance of c-PCA was not at par with the di-PLSR and TCA. Our results showed that the di-PLSR helped to recover the performance of RWC, and N models plummeted due to the differences originating from new imaging systems (sensor type, spectrograph, lens system, spatial resolution, spectral resolution, field of view, bit-depth, frame rate, and exposure time) or lighting conditions. The proposed approaches can alleviate the requirement of developing a new calibration model for a new phenotyping facility or to resort to the spectral space adjustment using the standard samples.
Highlights
IntroductionHigh-throughput plant phenotyping (HTPP) facilities are rapid and non-destructive sensing tools that have recently been widely used to assess multiple plant traits [1,2,3,4]
Introduction published maps and institutional affilHigh-throughput plant phenotyping (HTPP) facilities are rapid and non-destructive sensing tools that have recently been widely used to assess multiple plant traits [1,2,3,4].The hyperspectral camera has been one of the integral imaging components in HTPP facilities and is responsible for the non-invasive rapid measurement of various plant traits at different scales and times [5,6]
Applying the master relative water content (RWC) calibration model on master specachieved a coefficient of determination (R2 ) of 0.844, which was dropped to 0.683 and 0.756 tra achieved a coefficient of determination (R2) of 0.844, which was dropped to 0.683 and when the same model was used to obtain the predictions for slave–1 and slave–2 validation
Summary
High-throughput plant phenotyping (HTPP) facilities are rapid and non-destructive sensing tools that have recently been widely used to assess multiple plant traits [1,2,3,4]. The hyperspectral camera has been one of the integral imaging components in HTPP facilities and is responsible for the non-invasive rapid measurement of various plant traits at different scales and times [5,6]. As the hyperspectral images contain highly multicollinear data, multivariate models are indispensable for the prediction of phenotypic features [7,8]. One of the major issues with multivariate models developed from the spectral data is their inability to adjust to the new experimental or environmental conditions [10]. A calibration model becomes invalid because of the variations in instrumental response over iations
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have