The normalized difference vegetation index (NDVI) is widely used in remote sensing to monitor plant growth and chlorophyll levels. Usually, a multispectral camera (MSC) or hyperspectral camera (HSC) is required to obtain the near-infrared (NIR) and red bands for calculating NDVI. However, these cameras are expensive, heavy, difficult to geo-reference, and require professional training in imaging and data processing. On the other hand, the RGBN camera (NIR sensitive RGB camera, simply modified from standard RGB cameras by removing the NIR rejection filter) have also been explored to measure NDVI, but the results did not exactly match the NDVI from the MSC or HSC solutions. This study demonstrates an improved NDVI estimation method with an RGBN camera-based imaging system (Ncam) and machine learning algorithms. The Ncam consisted of an RGBN camera, a filter, and a microcontroller with a total cost of only $70 ~ 85. This new NDVI estimation solution was compared with a high-end hyperspectral camera in an experiment with corn plants under different nitrogen and water treatments. The results showed that the Ncam with two-band-pass filter achieved high performance (R2 = 0.96, RMSE = 0.0079) at estimating NDVI with the machine learning model. Additional tests showed that besides NDVI, this low-cost Ncam was also capable of predicting corn plant nitrogen contents precisely. Thus, Ncam is a potential option for MSC and HSC in plant phenotyping projects.

Hyperspectral sensors, especially the close-range hyperspectral camera, have been widely introduced to detect biological processes of plants in the high-throughput phenotyping platform, to support the identification of biotic and abiotic stress reactions at an early stage. However, the complex geometry of plants and their interaction with the illumination, severely affects the spectral information obtained. Furthermore, plant structure, leaf area, and leaf inclination distribution are critical indexes which have been widely used in multiple plant models. Therefore, the process of combination between hyperspectral images and 3D point clouds is a promising approach to solve these problems and improve the high-throughput phenotyping technique. We proposed a novel approach fusing a low-cost depth sensor and a close-range hyperspectral camera, which extended hyperspectral camera ability with 3D information as a potential tool for high-throughput phenotyping. An exemplary new calibration and analysis method was shown in soybean leaf experiments. The results showed that a 0.99 pixel resolution for the hyperspectral camera and a 3.3 millimeter accuracy for the depth sensor, could be achieved in a controlled environment using the method proposed in this paper. We also discussed the new capabilities gained using this new method, to quantify and model the effects of plant geometry and sensor configuration. The possibility of 3D reflectance models can be used to minimize the geometry-related effects in hyperspectral images, and to significantly improve high-throughput phenotyping. Overall results of this research, indicated that the proposed method provided more accurate spatial and spectral plant information, which helped to enhance the precision of biological processes in high-throughput phenotyping.

Airborne remote sensing technologies have been widely applied in field crop phenotyping. However, the quality of current remote sensing data suffers from significant diurnal variances. The severity of the diurnal issue has been reported in various plant phenotyping studies over the last four decades, but there are limited studies on the modeling of the diurnal changing patterns that allow people to precisely predict the level of diurnal impacts. In order to comprehensively investigate the diurnal variability, it is necessary to collect time series field images with very high sampling frequencies, which has been difficult. In 2019, Purdue agricultural (Ag) engineers deployed their first field visible to near infrared (VNIR) hyperspectral gantry platform, which is capable of repetitively imaging the same field plots every 2.5 min. A total of 8631 hyperspectral images of the same field were collected for two genotypes of corn plants from the vegetative stage V4 to the reproductive stage R1 in the 2019 growing season. The analysis of these images showed that although the diurnal variability is very significant for almost all the image-derived phenotyping features, the diurnal changes follow stable patterns. This makes it possible to predict the imaging drifts by modeling the changing patterns. This paper reports detailed diurnal changing patterns for several selected plant phenotyping features such as Normalized Difference Vegetation Index (NDVI), Relative Water Content (RWC), and single spectrum bands. For example, NDVI showed a repeatable V-shaped diurnal pattern, which linearly drops by 0.012 per hour before the highest sun angle and increases thereafter by 0.010 per hour. The different diurnal changing patterns in different nitrogen stress treatments, genotypes and leaf stages were also compared and discussed. With the modeling results of this work, Ag remote sensing users will be able to more precisely estimate the deviation/change of crop feature predictions caused by the specific imaging time of the day. This will help people to more confidently decide on the acceptable imaging time window during a day. It can also be used to calibrate/compensate the remote sensing result against the time effect.

During recent years, hyperspectral imaging technologies have been widely applied in agriculture to evaluate complex plant physiological traits such as leaf moisture content, nutrient level, and disease stress. A critical component of this technique is white referencing used to remove the effect of non-uniform lighting intensity in different wavelengths on raw hyperspectral images. However, a flat white tile cannot accurately reflect the lighting intensity variance on plant leaves, since the leaf geometry (e.g., tilt angles) and its interaction with the illumination severely impact plant reflectance spectra and vegetation indices such as the normalized difference vegetation index (NDVI). In this research, the impacts of leaf angles on plant reflectance spectra were summarized, and an improved image calibration model using the fusion of leaf hyperspectral images and 3D point clouds was built. Corn and soybean leaf samples were imaged at different tilt angles and orientations using an indoor desktop hyperspectral imaging system and analyzed for differences in the NDVI values. The results showed that the leaf’s NDVI largely changed with angles. The changing trends with angles differed between the two species. Using measurements of leaf tilt angle and orientation obtained from the 3D point cloud data taken simultaneously with the hyperspectral images, a support vector regression (SVR) model was successfully developed to calibrate the NDVI values of pixels at different angles on a leaf to a same standard as if the leaf was laid flat on a horizontal surface. The R-squared values between the measured and predicted leaf angle impacts were 0.76 and 0.94 for corn and soybean, respectively. This method has a potential to be used in any general plant imaging systems to improve the phenotyping quality.

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.

In agricultural weed management, herbicides are indispensable, yet innovation in their modes of action (MOA)—the general mechanisms affecting plant processes—has slowed. A finer classification within MOA is the site of action (SOA), the specific biochemical pathway in plants targeted by herbicides. The primary objectives of this study were to evaluate the efficacy of hyperspectral imaging in the early detection of herbicide stress and to assess its potential in accelerating the herbicide development process by identifying unique herbicide sites of action (SOA). Employing a novel SOA classification method, eight herbicides with unique SOAs were examined via an automated, high-throughput imaging system equipped with a conveyor-based plant transportation at Purdue University. This is one of the earliest trials to test hyperspectral imaging on a large number of herbicides, and the study aimed to explore the earliest herbicide stress detection/classification date and accelerate the speed of herbicide development. The final models, trained on a dataset with nine treatments with 320 samples in two rounds, achieved an overall accuracy of 81.5% 1 day after treatment. With the high-precision models and rapid screening of numerous compounds in only 7 days, the study results suggest that hyperspectral technology combined with machine learning can contribute to the discovery of new herbicide MOA and help address the challenges associated with herbicide resistance. Although no public research to date has used hyperspectral technology to classify herbicide SOA, the successful evaluation of herbicide damage to crops provides hope to accelerate the progress of herbicide development.