Browsing by Subject "Hyperspectral imaging"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Hyperspectral image dataset for salt stress phenotyping of wheat(2018-04-13) Moghimi, Ali; Yang, Ce; moghi005@umn.edu; Moghimi, Ali; Moghimi, AliThe dataset contains hyperspectral images of four wheat lines, each with a control and a salt (NaCl) treatment. Images were captured by a hyperspectral camera (PIKA II, Resonon) under natural light condition one day after salt application when there were no visual symptoms in wheat plants. The camera recorded the spectral response of both control and salt tanks of each line over 240 spectral channels in visible and near infrared region (400 nm to 900 nm) with about 2.1 nm spectral resolution, 640 spatial channels in the cross-track direction, and about 1 mm spatial resolution. Raw images were converted to radiance (Wm−2sr−1nm−1) using a vendor-provided calibration file, and then converted to reflectance (%) using a Spectralon panel. In total 25 spectral bands were disregarded due to high noise. Subsequent to noisy band removal, vegetation pixels were segmented from background using spectral vegetation indices and morphological operation. Although the goal of this study was plant phenotyping to rank salt tolerance of wheat lines, this dataset can be used for other research purposes, such as developing classification algorithms to discriminate healthy and stressed plants and developing methods for spectral feature selection to reduce the dimension of hyperspectral images.Item Integrating Hyperspectral Imaging and Artificial Intelligence to Develop Automated Frameworks for High-throughput Phenotyping in Wheat(2019-02) Moghimi, AliThe present dissertation was motivated by the need to apply innovative technologies, automation, and artificial intelligence to agriculture in order to promote crop production while protecting our environment. The main objective of this dissertation was to develop sensor-based, automated frameworks for high-throughput phenotyping of wheat to identify advanced wheat varieties based on three desired traits, including yield potential, tolerance to salt stress (an abiotic stress), and resistance to Fusarium head blight disease (a biotic stress). We leveraged the advantages of hyperspectral imaging, a sophisticated sensing technology, and artificial intelligence including machine learning and deep learning algorithms. Through integrating imaging and high-resolution spectroscopy, hyperspectral imaging provides valuable insights into the internal activity of plants, leaf tissue structure, and physiological changes of plants in response to their environment. Alternatively, advanced machine learning and deep learning algorithms are uniquely suited to extract meaningful features and recognize latent patterns associated with the desired phenotyping trait, and ultimately make accurate inferences and prediction. In the first study (Chapter 2), we focused on salt stress phenotyping of wheat in a hydroponic system. A novel method was proposed for hyperspectral image analysis to assess the salt tolerance of four wheat varieties in a quantitative, interpretable, and don-invasive manner. The results of this study demonstrated the feasibility of quantitative ranking of salt tolerance in wheat varieties only one day after applying the salt treatment. In the second study (Chapter 3), we developed an ensemble feature selection pipeline by integrating six supervised feature selection techniques to identify the most informative spectral bands from high-dimensional hyperspectral images captured for plant phenotyping applications. First, the spectral features were ranked based on their ability to discriminate salt-stressed wheat plants from healthy plants at the earliest stages of stress. The proposed method could drastically reduce the dimension of hyperspectral images from 215 to 15 while improving the accuracy of classifying healthy and stressed vegetation pixels by 8.5%. Second, a clustering algorithm was proposed to form six broad spectral bands around the most prominent spectral features to aid in development of a multispectral camera. In the third study (Chapter 4), we aimed to develop a phenotyping framework for Fusarium head blight (FHB), a devastating disease attacking small grain crops. The most informative spectral bands were identified to detect FHB-infected spikes. The results of this study revealed that a set of two broad spectral bands (766 nm and 696 nm) returns a classification accuracy of 99% in detecting FHB-infected spikes. In the fourth study (Chapter 5), we developed an autonomous robotic framework for high-throughput yield phenotyping of wheat in the field. The data were collected by a hyperspectral camera mounted on an unmanned aerial vehicle flying over three experimental fields containing hundreds of wheat plots during two consecutive growing seasons. A deep neural network was trained to predict the yield of wheat plots and estimate the yield variation at a sub-plot scale. The coefficient of determination for predicting the yield at sub-plot and plot scale were 0.79 and 0.41with normalized root-mean-square error of 0.24 and 0.14, respectively. In the fifth study (Chapter 6), we focused on developing a deep autoencoder network by leveraging a large unlabeled dataset (~ 8 million pixels) to learn an optimal feature representation of hyperspectral images in a low dimensional feature space for yield prediction. The result demonstrated that the trained autoencoder could substantially reduce the dimension of hyperspectral images onto a 3-, 5-, and 10-dimenionsal feature space with a mean squared error less than 7e-5, while retaining the relevant information for yield prediction. At a higher level, this dissertation contributes to improving economic, ecological, and social impacts by improving crop production, reducing pesticides use, and properly leveraging salt-affected farmlands. From an environmental perspective, a cultivar with high yield potential and a cultivar resistant to FHB disease both promote sustainability in crop production and environment by reducing the required fertilizer and pesticide to meet the anticipated farmers’ profit. The intelligent, automated phenotyping frameworks developed in this dissertation can help plant scientists and breeders identify crop varieties with the desired traits tailored around promoting crop production and mitigating food security concerns.Item Investigating the Capability of Hyperspectral Imaging for the Estimation of Wheat Leaf Rust Disease(2016-09-03) Crowell, Olivia LDetecting disease in crops increases yields and reduces economic loss. Traditional methods detect plant disease severity by hand, but it is a slow, time-consuming, and subjective process. Because there are physical, chemical, and physiological changes in plants with diseases, current research focuses on optical imaging as a more useful technique for monitoring disease. This experiment uses hyperspectral imaging (HSI) to investigate its capability as a diagnostic tool for wheat leaf rust disease. HSI has the potential to create more efficient High Throughput Phenotyping (HTP) methods to assist wheat breeders in the selection of a more resistant wheat variety. To collect data for this purpose, a HSI camera was attached to a ground vehicle that scanned wheat plots on an experimental field in St. Paul a month after the fungus was inoculated into the plots. White panels were laid out into the field to normalize the radiance based on the irradiance. Preprocessing techniques converted the pixels from their digital number to reflectance, which measures any physiological changes. The average spectral signatures of pixels were then compared to scoring data on a spectrum of R (resistant) to S (susceptible). Other categories include MR (moderately resistant), MS (moderately susceptible), etc. However, the spectral signatures that matched with R, MR, MRMS, MS, S, etc. varied unreasonably. R and S spectral lines were very similar to each other and did not exist as a maximum and minimum. This study is inconclusive which could be due to the calibration process since light cannot be controlled perfectly. It could also be because of the lack of control with varied wheat during data collection times.Item Provably Learning From Data: New Algorithms And Models For Matrix And Tensor Decompositions(2019-09) Rambhalta, SirishaLearning and leveraging patterns in data has fueled the recent advances in data driven services. As these solutions become more ubiquitous, and get incorporated into critical applications in healthcare and transportation, there is an increasing need to understand the limits of these learning algorithms and to develop algorithms with guarantees. Moreover, with data being generated at unprecedented rates, these algorithms need to be fast, learn on-the-fly (online), handle large volumes of data (scalable), and be computationally efficient, while possessing guarantees on their behavior. Furthermore, to make the learning-based products widely applicable there is also a need to make their reasoning and decision making process transparent (interpretable). These challenges inspire and motivate this dissertation. Specifically, we focus on analyzing various matrix/tensor demixing and factorization tasks, where we leverage the inherent interpretability endowed by the structure of problem (such as sparsity and low-rankness) to characterize the (theoretical) conditions for successful recovery, and analyze their performance in real-world settings. To this end, we make contributions on three fronts. First, we develop algorithm-aware theoretical guarantees for sparse matrix and tensor factorization tasks. Second, we establish algorithm-agnostic theoretical results for matrix demixing models and demonstrate their applications on real-world datasets. Lastly, we develop application-specific techniques for navigation and source separation. Bringing together Algorithms, Theory, and Applications, the techniques and theoretical results developed as part of this dissertation facilitate and motivate future explorations into the inner workings of learning algorithms for their safe use in critical applications.