[Establishment of The Crop Growth and Nitrogen Nutrition State Model Using Spectral Parameters Canopy Cover].

In order to explore a non-destructive monitoring technique, the use of digital photo pixels canopy cover (CC) diagnosis and prediction on maize growth and its nitrogen nutrition status. This study through maize canopy digital photo images on relationship between color index in the photo and the leaf area index (LAI), shoot dry matter weight (DM), leaf nitrogen content percentage (N%). The test conducted in the Chinese Academy of Agricultural Science from 2012 to 2013, based on Maize canopy Visual Image Analysis System developed by Visual Basic Version 6.0, analyzed the correlation of CC, color indices, LAI, DM, N% on maize varieties (Zhongdan909, ZD 909) under three nitrogen levels treatments, furthermore the indicators significantly correlated were fitted with modeling, The results showed that CC had a highly significant correlation with LAI (r = 0.93, p < 0.01), DM (r = 0. 94, p < 0.01), N% (r = 0.82, p < 0.01). Estimating the model of LAI, DM and N% by CC were all power function, and the equation respectively were y = 3.281 2x(0.763 9), y = 283.658 1x(0.553 6) and y = 3.064 5x(0.932 9); using independent data from modeling for model validation indicated that R2, RMSE and RE based on 1 : 1 line relationship between measured values and simulated values in the model of CC estimating LAI were 0.996, 0.035 and 1.46%; R2, RMSE and RE in the model of CC estimating DM were 0.978, 5.408 g and 2.43%; R2, RMSE and RE in the model of CC estimating N% were 0.990, 0.054 and 2.62%. In summary, the model can comparatively accurately estimate the LAI, DM and N% by CC under different nitrogen levels at maize grain filling stage, indicating that it is feasible to apply digital camera on real-time undamaged rapid monitoring and prediction for maize growth conditions and its nitrogen nutrition status. This research finding is to be verified in the field experiment, and further analyze the applicability throughout the growing period in other maize varieties and different planting density.

[Estimation of Winter Wheat Leaf Nitrogen Accumulation using Machine Learning Algorithm and Visible Spectral].

In order to study the feasibility of using digital image analysis and machine learning algorithm to estimate leaf nitrogen accumulation (LNA) of winter wheat at canopy level, digital images of winter wheat canopies grown under six levels of nitrogen application rate were taken for four times during the elongation stage. Meanwhile, wheat plants were sampled to measure LNA. The random forest method using CIEL*a*b* components was used to segment wheat plant from soil background and then extract canopy cover, RGB components of sRGB color space and compute five color indices derived from RGB components. Correlation analysis was carried out to identify the relationship between LNA and canopy cover (CC), RGB components, and five color indices. Two kinds of nonlinear least squares regression models (NLS) with different independent variables of color components and color indices, and three machine learning algorithmic of artificial neural network (ANN), support vector regression (SVR), and random forests method (RF) were used to estimate winter wheat leaf nitrogen accumulation. All three machine learning algorithm had four input variables of CC, R, G, and B. The results showed that, CC, R and G component of sRGB color space, and five color indices derived from RGB components showed significant correlations with LNA during the elongation stage. CC revealed the highest correlation with LNA. The lowest accuracy in estimation LNA was achieved by using nonlinear least square model with CC and color indices, and RF had showed the problem of overfitting. The other three methods of LNA with CC and RGB components, ANN, and SVR had showed good performance with higher R2 (0.851, 0.845, and 0.862) and lower RMSE (19.440, 19.820, and 18.698) for model calibration and validation, revealing good generalization ability.

[Estimation of Winter Wheat Biomass Using Visible Spectral and BP Based Artificial Neural Networks].

The objective of this study was to evaluate the feasibility of using color digital image analysis and back propagation (BP) based artificial neural networks (ANN) method to estimate above ground biomass at the canopy level of winter wheat field. Digital color images of winter wheat canopies grown under six levels of nitrogen treatments were taken with a digital camera for four times during the elongation stage and at the same time wheat plants were sampled to measure above ground biomass. Canopy cover (CC) and 10 color indices were calculated from winter wheat canopy images by using image analysis program (developed in Microsoft Visual Basic). Correlation analysis was carried out to identify the relationship between CC, 10 color indices and winter wheat above ground biomass. Stepwise multiple linear regression and BP based ANN methods were used to establish the models to estimate winter wheat above ground biomass. The results showed that CC, and two color indices had a significant cor- relation with above ground biomass. CC revealed the highest correlation with winter wheat above ground biomass. Stepwise multiple linear regression model constituting CC and color indices of NDI and b, and BP based ANN model with four variables (CC, g, b and NDI) for input was constructed to estimate winter wheat above ground biomass. The validation results indicate that the model using BP based ANN method has a better performance with higher R2 (0.903) and lower RMSE (61.706) and RRMSE (18.876) in comparation with the stepwise regression model.

[Segmentation of Winter Wheat Canopy Image Based on Visual Spectral and Random Forest Algorithm].

Digital image analysis has been widely used in non-destructive monitoring of crop growth and nitrogen nutrition status due to its simplicity and efficiency. It is necessary to segment winter wheat plant from soil background for accessing canopy cover, intensity level of visible spectrum (R, G, and B) and other color indices derived from RGB. In present study, according to the variation in R, G, and B components of sRGB color space and L*, a*, and b* components of CIEL* a* b* color space between wheat plant and soil background, the segmentation of wheat plant from soil background were conducted by the Otsu's method based on a* component of CIEL* a* b* color space, and RGB based random forest method, and CIEL* a* b* based random forest method, respectively. Also the ability to segment wheat plant from soil background was evaluated with the value of segmentation accuracy. The results showed that all three methods had revealed good ability to segment wheat plant from soil background. The Otsu's method had lowest segmentation accuracy in comparison with the other two methods. There were only little difference in segmentation error between the two random forest methods. In conclusion, the random forest method had revealed its capacity to segment wheat plant from soil background with only the visual spectral information of canopy image without any color components combinations or any color space transformation.