<p>Hyperspectral imaging is widely used for obtaining optical information of light absorbers (e.g. biochemical composition) in a variety of specimens or tissues in a label-free manner. Acquiring and processing spectral data using hyperspectral imaging usually requires advanced instrumentation such as spectrometers, spectrographs or tunable color filters, which are not easily adaptable in developing instrumentation for field-based applications. Also, use of only RGB information from conventional cameras is not sufficient to obtain a reliable correlation with the actual content of the analyte of interest. We propose a new concept of ‘virtual hyperspectral imaging’ to reconstruct the full reflectance spectra from RGB image data. This allows us to use only RGB image data to determine detailed spatial distributions of analytes of interest. More importantly, it simplifies instrumentation without requiring bulky and expensive hardware. Using a data-driven approach, we apply multivariate regression to reconstruct hyperspectral reflectance image data from RGB images obtained using a conventional camera or a smartphone. </p> <p> </p> <p>In developing a reliable reconstruction matrix, it is critical to obtain a training data set of the specimen of study under the same optical geometry since the spectral reflectance and absorbance is sensitive to the detection and illumination parameters. We designed an image-guided hyperspectral system that can acquire both hyperspectral reflectance and RGB data sets under the same imaging configuration to minimize any discrepancies in the hyperspectral reflectance data acquired using different optical sensing geometries. In our technology development, a telecentric lens that is commonly used in machine vision systems but rarely in bioimaging, serves as a key component for reducing unwanted scattering in biological tissue due to its highly anisotropic scattering properties, by acting as a back-directional gating component to suppress diffuse light. We evaluate our spectrometer-less reflectance imaging method using RGB-based hyperspectral reconstruction algorithm for integration into a smartphone application for non-invasive hemoglobin analysis for anemia risk assessment in communities with limited access to central laboratory tests.</p>

Hyperspectral imaging has become one of the most popular technologies in plant phenotyping because it can efficiently and accurately predict numerous plant physiological features such as plant biomass, leaf moisture content, and chlorophyll content. Various hyperspectral imaging systems have been deployed in both greenhouse and field phenotyping activities. However, the hyperspectral imaging quality is severely affected by the continuously changing environmental conditions such as cloud cover, temperature and wind speed that induce noise in plant spectral data. Eliminating these environmental effects to improve imaging quality is critically important. In this thesis, two approaches were taken to address the imaging noise issue in greenhouse and field separately. First, a computational simulation model was built to simulate the greenhouse microclimate changes (such as the temperature and radiation distributions) through a 24-hour cycle in a research greenhouse. The simulated results were used to optimize the movement of an automated conveyor in the greenhouse: the plants were shuffled with the conveyor system with optimized frequency and distance to provide uniform growing conditions such as temperature and lighting intensity for each individual plant. The results showed the variance of the plants’ phenotyping feature measurements decreased significantly (i.e., by up to 83% in plant canopy size) in this conveyor greenhouse. Secondly, the environmental effects (i.e., sun radiation) on <a>aerial </a>hyperspectral images in field plant phenotyping were investigated and modeled. <a>An artificial neural network (ANN) method was proposed to model the relationship between the image variation and environmental changes. Before the 2019 field test, a gantry system was designed and constructed to repeatedly collect time-series hyperspectral images with 2.5 minutes intervals of the corn plants under varying environmental conditions, which included sun radiation, solar zenith angle, diurnal time, humidity, temperature and wind speed. Over 8,000 hyperspectral images of </a>corn (<i>Zea mays </i>L.) were collected with synchronized environmental data throughout the 2019 growing season. The models trained with the proposed ANN method were able to accurately predict the variations in imaging results (i.e., 82.3% for NDVI) caused by the changing environments. Thus, the ANN method can be used by remote sensing professionals to adjust or correct raw imaging data for changing environments to improve plant characterization.

<p>  </p> <p>Hyperspectral Imaging is one of the most popular technologies in plant phenotyping due to its ability to predict the plant physiological features such as yield biomass, leaf moisture, and nitrogen content accurately, non-destructively, and efficiently. Various kinds of hyperspectral imaging systems have been developed in the past years for both greenhouse and field phenotyping activities. Developing the plant physiological prediction model such as relative water content (RWC) using hyperspectral imaging data requires the adoption of machine learning-based calibration techniques. Convolutional neural networks (CNNs) have been known to automatically extract the features from the raw data which can lead to highly accurate physiological prediction models. Once a reliable prediction model has been developed, sharing that model across multiple hyperspectral imaging systems is very desirable since collecting the large number of ground truth labels for predictive model development is expensive and tedious. However, there are always significant differences in imaging sensors, imaging, and environmental conditions between different hyperspectral imaging facilities, which makes it difficult to share plant features prediction models. Calibration transfer between the imaging systems is critically important. In this thesis, two approaches were taken to address the calibration transfer from the greenhouse to the field. First, direct standardization (DS), piecewise direct standardization (PDS), double window piecewise direct standardization (DPDS) and spectral space transfer (SST) were used for standardizing the spectral reflectance to minimize the artifacts and spectral differences between different greenhouse imaging systems. A linear transformation matrix estimated using SST based on a small set of plant samples imaged in two facilities reduced the root mean square error (RMSE) for maize physiological feature prediction significantly, i.e., from 10.64% to 2.42% for RWC and from 1.84% to 0.11% for nitrogen content. Second, common latent space features between two greenhouses or a greenhouse and field imaging system were extracted in an unsupervised fashion. Two different models based on deep adversarial domain adaptation are trained, evaluated, and tested. In contrast to linear standardization approaches developed using the same plant samples imaged in two greenhouse facilities, the domain adaptation extracted non-linear features common between spectra of different imaging systems. Results showed that transferred RWC models reduced the RMSE by up to 45.9% for the greenhouse calibration transfer and 12.4% for a greenhouse to field transfer. The plot scale evaluation of the transferred RWC model showed no significant difference between the measurements and predictions. The methods developed and reported in this study can be used to recover the performance plummeted due to the spectral differences caused by the new phenotyping system and to share the knowledge among plant phenotyping researchers and scientists.</p>