Haiyan Cen

Optimization of the hyperspectral imaging-based spatially-resolved system for measuring the optical properties of biological materials.

This paper reports on the optimization and assessment of a hyperspectral imaging-based spatially-resolved system for determination of the optical properties of biological materials over the wavelengths of 500-1,000 nm. Twelve model samples covering a wide range of absorption and reduced scattering coefficients were created to validate the hyperspectral imaging system, and their true values of absorption and reduced scattering coefficients were determined and then cross-validated using three commonly used methods (i.e., transmittance, integrating sphere, and empirical equation). Light beam and source-detector distance were optimized through Monte Carlo simulations and experiments for the model samples. The optimal light beam should be of Gaussian type with the diameter of less than 1 mm, and the optimal minimum and maximum source-detector distance should be 1.5 mm and 10-20 mean free paths, respectively. The optimized hyperspectral imaging-based spatially-resolved system achieved good estimation of the optical parameters.

Chlorophyll Fluorescence Imaging Uncovers Photosynthetic Fingerprint of Citrus Huanglongbing

Huanglongbing (HLB) is one of the most destructive diseases of citrus, which has posed a serious threat to the global citrus production. This research was aimed to explore the use of chlorophyll fluorescence imaging combined with feature selection to characterize and detect the HLB disease. Chlorophyll fluorescence images of citrus leaf samples were measured by an in-house chlorophyll fluorescence imaging system. The commonly used chlorophyll fluorescence parameters provided the first screening of HLB disease. To further explore the photosynthetic fingerprint of HLB infected leaves, three feature selection methods combined with the supervised classifiers were employed to identify the unique fluorescence signature of HLB and perform the three-class classification (i.e., healthy, HLB infected, and nutrient deficient leaves). Unlike the commonly used fluorescence parameters, this novel data-driven approach by using the combination of the mean fluorescence parameters and image features gave the best classification performance with the accuracy of 97%, and presented a better interpretation for the spatial heterogeneity of photochemical and non-photochemical components in HLB infected citrus leaves. These results imply the potential of the proposed approach for the citrus HLB disease diagnosis, and also provide a valuable insight for the photosynthetic response to the HLB disease.

Combining UAV-Based Vegetation Indices and Image Classification to Estimate Flower Number in Oilseed Rape

Remote estimation of flower number in oilseed rape under different nitrogen (N) treatments is imperative in precision agriculture and field remote sensing, which can help to predict the yield of oilseed rape. In this study, an unmanned aerial vehicle (UAV) equipped with Red Green Blue (RGB) and multispectral cameras was used to acquire a series of field images at the flowering stage, and the flower number was manually counted as a reference. Images of the rape field were first classified using K-means method based on Commission Internationale de l’Éclairage (CIE) L*a*b* space, and the result showed that classified flower coverage area (FCA) possessed a high correlation with the flower number (r2 = 0.89). The relationships between ten commonly used vegetation indices (VIs) extracted from UAV-based RGB and multispectral images and the flower number were investigated, and the VIs of Normalized Green Red Difference Index (NGRDI), Red Green Ratio Index (RGRI) and Modified Green Red Vegetation Index (MGRVI) exhibited the highest correlation to the flower number with the absolute correlation coefficient (r) of 0.91. Random forest (RF) model was developed to predict the flower number, and a good performance was achieved with all UAV variables (r2 = 0.93 and RMSEP = 16.18), while the optimal subset regression (OSR) model was further proposed to simplify the RF model, and a better result with r2 = 0.95 and RMSEP = 14.13 was obtained with the variable combination of RGRI, normalized difference spectral index (NDSI (944, 758)) and FCA. Our findings suggest that combining VIs and image classification from UAV-based RGB and multispectral images possesses the potential of estimating flower number in oilseed rape.

Phenotyping of Arabidopsis Drought Stress Response Using Kinetic Chlorophyll Fluorescence and Multicolor Fluorescence Imaging

Plant responses to drought stress are complex due to various mechanisms of drought avoidance and tolerance to maintain growth. Traditional plant phenotyping methods are labor-intensive, time-consuming, and subjective. Plant phenotyping by integrating kinetic chlorophyll fluorescence with multicolor fluorescence imaging can acquire plant morphological, physiological, and pathological traits related to photosynthesis as well as its secondary metabolites, which will provide a new means to promote the progress of breeding for drought tolerant accessions and gain economic benefit for global agriculture production. Combination of kinetic chlorophyll fluorescence and multicolor fluorescence imaging proved to be efficient for the early detection of drought stress responses in the Arabidopsis ecotype Col-0 and one of its most affected mutants called reduced hyperosmolality-induced [Ca2+]i increase 1. Kinetic chlorophyll fluorescence curves were useful for understanding the drought tolerance mechanism of Arabidopsis. Conventional fluorescence parameters provided qualitative information related to drought stress responses in different genotypes, and the corresponding images showed spatial heterogeneities of drought stress responses within the leaf and the canopy levels. Fluorescence parameters selected by sequential forward selection presented high correlations with physiological traits but not morphological traits. The optimal fluorescence traits combined with the support vector machine resulted in good classification accuracies of 93.3 and 99.1% for classifying the control plants from the drought-stressed ones with 3 and 7 days treatments, respectively. The results demonstrated that the combination of kinetic chlorophyll fluorescence and multicolor fluorescence imaging with the machine learning technique was capable of providing comprehensive information of drought stress effects on the photosynthesis and the secondary metabolisms. It is a promising phenotyping technique that allows early detection of plant drought stress.

Near ground platform development to simulate UAV aerial spraying and its spraying test under different conditions

Abstract Aerial spraying using UAV has gained great interest worldwide. UAV spraying can overcome crop height limits and is unlikely to crust soil or damage crop plants. More experiments concerning spraying are needed, such as spraying method tests, spraying droplet analysis, variable rating spraying tests, etc. These experiments either take a long time for real flights or have an unrecognized danger to UAV in real flights. To address this problem, an indoor spraying platform, which consists of X-Y direction movement and wind field generation was developed to simulate UAV aerial spraying. The maximum moving speed in the horizontal direction was 3.5 m/s and 0.25 m/s in the vertical direction. The horizontal moving distance was 11 m and the vertical moving distance was 0.5 m. The platform consists of 4 parts: upper machine software, central controller, X-Y moving part and far end spraying structure. CAN bus was used for communication between the central control board and far end controller. An experiment was carried out to test how the platform performs with different moving speeds and different wind strength. The wind strength test shows that wind forces the deposit down to the ground when droplets were equally affected by 2 wind forces. The result shows that the platform can meet the requirement of UAV aerial spraying.

Detection of Moisture, Soluble Solids, and Sucrose Content and Mechanical Properties of Sugar Beet by Hyperspectral Scattering Imaging

Abstract. Sucrose, soluble solids, and moisture content and mechanical properties are important quality/property attributes of sugar beet. In this study, hyperspectral scattering imaging technique was used to measure these attributes of sugar beet. Hyperspectral scattering images for the spectral region of 500-1,000 nm were acquired from 398 beet slices and relative mean reflectance spectra were calculated. The sucrose, soluble solids and moisture content of beet samples were measured using high performance liquid chromatography, refractometry, and vacuum freeze drying, respectively, while the compressive mechanical properties of beet tissue specimens were measured using a Texture Analyzer. Partial least squares (PLS) models were developed and tested for predicting these quality/property parameters of beet samples. The results showed that using relative mean reflectance spectra gave good predictions for the moisture, soluble solids and sucrose content of beet slices with the correlations of 0.75-0.88 and the standard errors of prediction of 0.95-1.08 based on full-spectrum PLSR models. PLS models based on using wavelengths selection with the uninformative variable elimination method produced similar prediction results. However, both modeling approaches gave poor predictions for the mechanical properties of beets with the correlation values of 0.46-0.63. This research demonstrated the potential of hyperspectral scattering imaging for measuring quality attributes of sugar beet.

Hyperspectral Imaging-based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers

Abstract. Hyperspectral imaging is useful for detecting internal defect of pickling cucumbers. The technique, however, is not yet suitable for high-speed online implementation due to the challenges for analyzing large-scale hyperspectral images. This research was aimed to select the optimal wavebands from the hyperspectral image data, so that they can be deployed in either a hyper- or multi-spectral imaging-based inspection system for automatic detection of internal defect of pickling cucumbers. Hyperspectral reflectance (400-700 nm) and transmittance (700-1,000 nm) images were acquired, using an in-house developed hyperspectral imaging system running at two conveyor speeds of 85 and 165 mm/s, for 300 ‘Journey’ pickling cucumbers before and after they were induced internal damage by mechanical load. Minimum redundancy-maximum relevance (MRMR) and principal component analysis (PCA) were used for the optimal wavebands selection. Discriminant analysis with Mahalanobis distances classifier was performed for the two-class (i.e., normal and defective) and three-class classifications (i.e., normal, slightly defective, and severely defective) using mean spectra and textural features (energy and variance) from the region of interests in the spectral images at selected waveband ratios. MRMR wavebands selection generally outperformed PCA in the classification performance. The two-band ratio of 887/837 nm from MRMR gave the best overall classification results with the accuracy of 95.1% and 94.2% at the conveyor speeds of 85 mm/s and 165 mm/s, respectively, for the two-class classification. The highest classification accuracies for the three-class classification based on the optimal two-band ratio of 887/837 nm were 82.8% and 81.3% at the conveyor speeds of 85 mm/s and 165 mm/s, respectively. The mean spectra-based classification achieved better results than the textural feature-based classification except in the three-class classification for the higher conveyor speed. The overall classification accuracies for all selected waveband ratios at the low conveyor speed were slightly higher than those at the higher conveyor speed, since the low speed resulted in more scan lines, thus higher spatial-resolution hyperspectral images. The identified two-band ratio of 887/837 nm in transmittance mode could be applied for fast real-time internal defect detection of pickling cucumbers.

Optimization of the hyperspectral imaging-based spatially-resolved system for measuring the optical properties of biological materials

Hyperspectral imaging-based spatially-resolved technique provides a new means to determine the optical properties of biological materials. However, several critical technical issues must be properly addressed in order to achieve desired measurement accuracies. This paper reports on the optimization and assessment of a hyperspectral imaging-based spatially-resolved system for determination of the optical properties of biological materials over the wavelengths of 500-1,000 nm. Twelve model samples were created using three absorbing dyes and fat emulsion scatters to validate the hyperspectral imaging system, and their true values of absorption and reduced scattering coefficients [THESE SYMBOLS ARE NOT AVAILABLE IN THML, SEE PDF FOR COMPLETE VERSION] (&) were determined and then cross-validated using three commonly used methods (i.e., transmittance, integrating sphere, and empirical equation). The optical properties of the model samples were then extracted from the spatially-resolved reflectance profiles, acquired by the hyperspectral imaging system, based on the diffusion model with a nonlinear least squares inverse algorithm. Light beam and source-detector distance were quantified and optimized through Monte Carlo simulations and experiments. The optimized hyperspectral imaging system was evaluated for accuracy, precision/reproducibility and sensitivity. The results suggested that the optimal light beam should be of circular shape and Gaussian type with the diameter of less than 1 mm, the optimal minimum source-detector distance should be about 1.5 mm, and the optimal maximum source-detector distance should be 10-20 mean free paths [1 mean free path =[THESE SYMBOLS ARE NOT AVAILABLE IN THML, SEE PDF FOR COMPLETE VERSION]] or be determined by the minimum signal-to-noise ratio of 20 (or 150 CCD counts for the system). The hyperspectral imaging-based spatially-resolved system had average measurement errors of 23% and 7% for[THESE SYMBOLS ARE NOT AVAILABLE IN THML, SEE PDF FOR COMPLETE VERSION] and, respectively, for the model samples, which are smaller than, or comparable to those obtained using other techniques (i.e., frequency-domain, time-resolved, and spatially-resolved but with other sensing configurations). The research provides a systematic guide for the development and optimization of spatially-resolved technique to measure the optical properties of biological materials like food and agricultural products.