Hyperspectral Image-Based Variety Classification of Waxy Maize Seeds by the t-SNE Model and Procrustes Analysis

Predicting F v /F m and evaluating cotton drought tolerance using hyperspectral and 1D-CNN

The chlorophyll fluorescence parameter F_v/F_m is significant in abiotic plant stress. Current acquisition methods must deal with the dark adaptation of plants, which cannot achieve rapid, real-time, and high-throughput measurements. However, increased inputs on different genotypes based on hyperspectral model recognition verified its capabilities of handling large and variable samples. F_v/F_m is a drought tolerance index reflecting the best drought tolerant cotton genotype. Therefore, F_v/F_m hyperspectral prediction of different cotton varieties, and drought tolerance evaluation, are worth exploring. In this study, 80 cotton varieties were studied. The hyperspectral cotton data were obtained during the flowering, boll setting, and boll opening stages under normal and drought stress conditions. Next, One-dimensional convolutional neural networks (1D-CNN), Categorical Boosting (CatBoost), Light Gradient Boosting Machines (LightBGM), eXtreme Gradient Boosting (XGBoost), Decision Trees (DT), Random Forests (RF), Gradient elevation decision trees (GBDT), Adaptive Boosting (AdaBoost), Extra Trees (ET), and K-Nearest Neighbors (KNN) were modeled with F _v /F _m. The Savitzky-Golay + 1D-CNN model had the best robustness and accuracy (RMSE = 0.016, MAE = 0.009, MAPE = 0.011). In addition, the F _v /F _m prediction drought tolerance coefficient and the manually measured drought tolerance coefficient were similar. Therefore, cotton varieties with different drought tolerance degrees can be monitored using hyperspectral full band technology to establish a 1D-CNN model. This technique is non-destructive, fast and accurate in assessing the drought status of cotton, which promotes smart-scale agriculture.

A Pricing Model for Urban Rental Housing Based on Convolutional Neural Networks and Spatial Density: A Case Study of Wuhan, China

With the development of urbanization and the expansion of floating populations, rental housing has become an increasingly common living choice for many people, and housing rental prices have attracted great attention from individuals, enterprises and the government. The housing rental prices are principally estimated based on structural, locational and neighborhood variables, among which the relationships are complicated and can hardly be captured entirely by simple one-dimensional models; in addition, the influence of the geographic objects on the price may vary with the increase in their quantities. However, existing pricing models usually take those structural, locational and neighborhood variables as one-dimensional inputs into neural networks, and often neglect the aggregated effects of geographical objects, which may lead to fluctuating rental price estimations. Therefore, this paper proposes a rental housing price model based on the convolutional neural network (CNN) and the synthetic spatial density of points of interest (POIs). The CNN can efficiently extract the complex characteristics among the relevant variables of housing, and the two-dimensional locational and neighborhood variables, based on the synthetic spatial density, effectively reflect the aggregated effects of the urban facilities on rental housing prices, thereby improving the accuracy of the model. Taking Wuhan, China, as the study area, the proposed method achieves satisfactory and accurate rental price estimations (coefficient of determination (R2) = 0.9097, root mean square error (RMSE) = 3.5126) in comparison with other commonly used pricing models.

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Food quality and safety are strongly related to human health. Food quality varies with variety and geographical origin, and food fraud is becoming a threat to domestic and global markets. Visible/infrared spectroscopy and hyperspectral imaging techniques, as rapid and non-destructive analytical methods, have been widely utilized to trace food varieties and geographical origins. In this review, we outline recent research progress on identifying food varieties and geographical origins using visible/infrared spectroscopy and hyperspectral imaging with the help of machine learning techniques. The applications of visible, near-infrared, and mid-infrared spectroscopy as well as hyperspectral imaging techniques on crop food, beverage, fruits, nuts, meat, oil, and some other kinds of food are reviewed. Furthermore, existing challenges and prospects are discussed. In general, the existing machine learning techniques contribute to satisfactory classification results. Follow-up researches of food varieties and geographical origins traceability and development of real-time detection equipment are still in demand.

Prediction of Sweet Corn Seed Germination Based on Hyperspectral Image Technology and Multivariate Data Regression

Vigor identification in sweet corn seeds is important for seed germination, crop yield, and quality. In this study, hyperspectral image (HSI) technology integrated with germination tests was applied for feature association analysis and germination performance prediction of sweet corn seeds. In this study, 89 sweet corn seeds (73 for training and the other 16 for testing) were studied and hyperspectral imaging at the spectral range of 400-1000 nm was applied as a nondestructive and accurate technique to identify seed vigor. The root length and seedling length which represent the seed vigor were measured, and principal component regression (PCR), partial least squares (PLS), and kernel principal component regression (KPCR) were used to establish the regression relationship between the hyperspectral feature of seeds and the germination results. Specifically, the relevant characteristic band associated with seed vigor based on the highest correlation coefficient (HCC) was constructed for optimal wavelength selection. The hyperspectral data features were selected by genetic algorithm (GA), successive projections algorithm (SPA), and HCC. The results indicated that the hyperspectral data features obtained based on the HCC method have better prediction results on the seedling length and root length than SPA and GA. By comparing the regression results of KPCR, PCR, and PLS, it can be concluded that the hyperspectral method can predict the root length with a correlation coefficient of 0.7805. The prediction results of different feature selection and regression algorithms for the seedling length were up to 0.6074. The results indicated that, based on hyperspectral technology, the prediction of seedling root length was better than that of seed length.

Inferring Visual Biases in UAV Videos from Eye Movements

Unmanned Aerial Vehicle (UAV) imagery is gaining a lot of momentum lately. Indeed, gathered information from a bird-point-of-view is particularly relevant for numerous applications, from agriculture to surveillance services. We herewith study visual saliency to verify whether there are tangible differences between this imagery and more conventional contents. We first describe typical and UAV contents based on their human saliency maps in a high-dimensional space, encompassing saliency map statistics, distribution characteristics, and other specifically designed features. Thanks to a large amount of eye tracking data collected on UAV, we stress the differences between typical and UAV videos, but more importantly within UAV sequences. We then designed a process to extract new visual attention biases in the UAV imagery, leading to the definition of a new dictionary of visual biases. We then conduct a benchmark on two different datasets, whose results confirm that the 20 defined biases are relevant as a low-complexity saliency prediction system.

Hyperspectral imaging technology combined with deep forest model to identify frost-damaged rice seeds

In recent years, deep learning models have been widely used in the field of hyperspectral imaging. However, the training of deep learning models requires not only a large number of samples, but also the need to set too many hyper-parameters, which is time consuming and laborious for researchers. This study used hyperspectral imaging technology combined with a deep learning model suitable for small-scale sample data sets, deep forests (DF) model, to classify rice seeds with different degrees of frost damage. During the period, three spectral preprocessing methods (Savitzky-Golay first derivative (SG1), standard normal variate (SNV), and multivariate scatter correction (MSC)) were used to process the original spectral data, and three feature extraction algorithms (principal component analysis (PCA), successive projections algorithm (SPA), and neighborhood component analysis (NCA)) were used to extract the characteristic wavelengths. Moreover, DF model and three traditional machine learning models (decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM)) were built based on different numbers of sample sets. After multivariate data analysis, it showed that the pretreatment effect of MSC was the most excellent, and the characteristic wavelength extracted by NCA algorithm was the most useful. In addition, the performance of DF model was better than these three traditional classifier models, and it still performed well in small-scale sample set data. Therefore, DF model was chosen as the best classification model. The results of this study show that the DF model maintains good classification performance in small-scale sample set data, and it has a good application prospect in hyperspectral imaging technology.

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology

Hyperspectral imaging is a nondestructive testing technology that integrates spectroscopy and iconology technologies, which enables us to quickly obtain both internal and external information of objects and identify crop seed varieties. First, the hyperspectral images of ten soybean seed varieties were collected and the reflectance was obtained. Savitzky-Golay smoothing (SG), first derivative (FD), standard normal variate (SNV), fast Fourier transform (FFT), Hilbert transform (HT), and multiplicative scatter correction (MSC) spectral reflectance pretreatment methods were used. Then, the feature wavelengths and feature information of the pretreated spectral reflectance data were extracted using competitive adaptive reweighted sampling (CARS), the successive projections algorithm (SPA), and principal component analysis (PCA). Finally, 5 classifiers, Bayes, support vector machine (SVM), k-nearest neighbor (KNN), ensemble learning (EL), and artificial neural network (ANN), were used to identify seed varieties. The results showed that MSC-CARS-EL had the highest accuracy among the 90 combinations, with training set, test set, and 5-fold cross-validation accuracies of 100%, 100%, and 99.8%, respectively. Moreover, the contribution of spectral pretreatment to discrimination accuracy was higher than those of feature extraction and classifier selection. Pretreatment methods determined the range of the identification accuracy, feature-selective methods and classifiers only changed within this range. The experimental results provide a good reference for the identification of other crop seed varieties.

Maize Silage Kernel Fragment Estimation Using Deep Learning-Based Object Recognition in Non-Separated Kernel/Stover RGB Images

Efficient and robust evaluation of kernel processing from corn silage is an important indicator to a farmer to determine the quality of their harvested crop. Current methods are cumbersome to conduct and take between hours to days. We present the adoption of two deep learning-based methods for kernel processing prediction without the cumbersome step of separating kernels and stover before capturing images. The methods show that kernels can be detected both with bounding boxes and at pixel-level instance segmentation. Networks were trained on up to 1393 images containing just over 6907 manually annotated kernel instances. Both methods showed promising results despite the challenging setting, with an average precision at an intersection-over-union of 0.5 of 34.0% and 36.1% on the test set consisting of images from three different harvest seasons for the bounding-box and instance segmentation networks respectively. Additionally, analysis of the correlation between the Kernel Processing Score (KPS) of annotations against the KPS of model predictions showed a strong correlation, with the best performing at r(15) = 0.88, p = 0.00003. The adoption of deep learning-based object recognition approaches for kernel processing measurement has the potential to lower the quality assessment process to minutes, greatly aiding a farmer in the strenuous harvesting season.