Stress Distribution Analysis on Hyperspectral Corn Leaf Images for Improved Phenotyping Quality

Abstract

<jats:p>High-throughput imaging technologies have been developing rapidly for agricultural plant phenotyping purposes. With most of the current crop plant image processing algorithms, the plant canopy pixels are segmented from the images, and the averaged spectrum across the whole canopy is calculated in order to predict the plant’s physiological features. However, the nutrients and stress levels vary significantly across the canopy. For example, it is common to have several times of difference among Soil Plant Analysis Development (SPAD) chlorophyll meter readings of chlorophyll content at different positions on the same leaf. The current plant image processing algorithms cannot provide satisfactory plant measurement quality, as the averaged color cannot characterize the different leaf parts. Meanwhile, the nutrients and stress distribution patterns contain unique features which might provide valuable signals for phenotyping. There is great potential to develop a finer level of image processing algorithm which analyzes the nutrients and stress distributions across the leaf for improved quality of phenotyping measurements. In this paper, a new leaf image processing algorithm based on Random Forest and leaf region rescaling was developed in order to analyze the distribution patterns on the corn leaf. The normalized difference vegetation index (NDVI) was used as an example to demonstrate the improvements of the new algorithm in differentiating between different nitrogen stress levels. With the Random Forest method integrated into the algorithm, the distribution patterns along the corn leaf’s mid-rib direction were successfully modeled and utilized for improved phenotyping quality. The algorithm was tested in a field corn plant phenotyping assay with different genotypes and nitrogen treatments. Compared with the traditional image processing algorithms which average the NDVI (for example) throughout the whole leaf, the new algorithm more clearly differentiates the leaves from different nitrogen treatments and genotypes. We expect that, besides NDVI, the new distribution analysis algorithm could improve the quality of other plant feature measurements in similar ways.</jats:p>

Development of a Target-to-Sensor Mode Multispectral Imaging Device for High-Throughput and High-Precision Touch-Based Leaf-Scale Soybean Phenotyping

“…The major source of error is the individual differences between each soybean canopy. As the soybeans are grown in the greenhouse, the microclimate will have effect on the growing of the canopy that could induce large variance to plant grow [ 25 ]. Another source of error is induced when inpainting the images as a small portion of the images are not the original leaf tissue.…”

“…Multiple studies have shown that SPAD readings are correlated with various crop traits [ 21 , 22 , 23 ]. However, since the SPAD meter only measures a small area of the leaf, different locations on the same leaf can yield different results [ 17 , 24 ] Additionally, studies have suggested that color distribution over the entire leaf is a better indicator of stress [ 25 , 26 ].…”

Developing a Modern Greenhouse Scientific Research Facility—A Case Study

“…Visual monitoring ranges from custom-made devices such as LeafSpec [26,27], the use of a normal camera combined with a microcontroller, a processor board [28][29][30] or a smartphone camera [31][32][33]. Papers propose monitoring plants with different types of cameras: standard spectral camera, infrared camera, thermal imaging camera, or color component camera.…”

Modeling of Diurnal Changing Patterns in Airborne Crop Remote Sensing Images

“…After data collection, standard imaging processing protocols were performed to extract the interested plant phenotyping features [5,31,32]. The raw hyperspectral images were firstly calibrated with the real-time white reference.…”