Evaluation of grain yield based on digital images of rice canopy

Liu, Kailou; Li, Yazhen; Han, Tianfu; Yu, Xiang; Huicai, Ye; Hu, Huiwen; Hu, Zhihua

doi:10.1186/s13007-019-0416-x

Cited by 17 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…can describe plant color [28], which can reflect its nutrient status, especially N content and absorption. Several studies have shown that RGB color space parameters extracted from vegetation canopy images can be used to predict vegetation yield and nutrient status [15,19,20]. Among the models constructed with image parameters in this study, those constructed using NRI were unstable, possibly because the parameters of NRI were obtained by extracting RGB values from images.…”

Section: Comparison Of Methods To Estimate Rice N Statusmentioning

confidence: 91%

“…Digital cameras are a common and inexpensive piece of equipment. They can collect image and spectral information with sufficient quality to use in predictions of crop nutrition status [13,14] and yield [15] [16], and to monitor pests [17]. Li et al extracted the dark green color index (DGCI) of image features, and concluded that DGCI was significantly correlated with the SPAD value of rice leaves.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring the nitrogen nutrition status of rice plants using spectral and image technologies

Chun

Zhong

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: We aimed to investigate methods to estimate the nitrogen (N) nutrition status of rice plants using data obtained using a digital camera and a spectroradiometer. The overall aim was to compare the advantages and potential of image technology and spectral technology to monitor rice N indexes accurately, inexpensively, and in real time to optimize fertilization strategies. Realizing the technical selection of definite spectrum or image diagnosis aiming at different rice nitrogen nutrition indexes. We conducted field trials of rice plants grown with different levels of N fertilizer in 2018 to 2019. Spectral information and images of the rice canopy were obtained, various image and spectral characteristic parameters were selected to construct models to estimate rice N status.Results: The determination coefficients of the models constructed using the ratio vegetation index (RVI[800,550]) and cover canopy (CC) as dependent variables were most significant. Among the models using spectral parameters, those constructed using RVI[800,550] to estimate rice N indexes had the obviously coefficient of determination (R2) values, which were 0.69, 0.58, and 0.65 for the models to estimate leaf area index(LAI), aboveground biomass(AGB), and plant N accumulation(PNA). As for image parameter, those using CC to predict rice N indexes showed the highest R2 values (0.76, 0.65, and 0.71 for the models to estimate LAI, AGB, and PNA, respectively) (P < 0.01). The model using the spectral parameter RVI[800,550] had a good fit and stability in estimating plant nitrogen accumulation (R2 = 0.65, root mean square error (RMSE) = 1.35 g·m-2, relative RMSE (RRMSE) = 14.05%), and the model using the image parameter CC had a good fit in predicting leaf area index (R2 = 0.76, RMSE = 0.28, RRMSE = 7.26%) and aboveground biomass (R2 = 0.65, RMSE = 22.03 g·m-2, RRMSE = 7.52%). Different detection technology should be adopted for different rice varieties and rice N nutrition indexes. Conclusions: Spectral and image parameters can be used as technical parameters to estimate rice N status. The spectral parameter RVI[800,550] can be used to accurately estimate plant nitrogen accumulation, and the image parameter CC can be used to accurately estimate leaf area index and aboveground biomass.

show abstract

Section: Comparison Of Methods To Estimate Rice N Statusmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Monitoring the nitrogen nutrition status of rice plants using spectral and image technologies

Chun

Zhong

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…constructed a regression model of a maize N nutrition index using a dual-band spectral index (R710, R512) [24], and it was proven to be a can describe plant color [25], which can reflect its nutrient status, especially N content and absorption. Several studies have shown that RGB color space parameters extracted from vegetation canopy images can be used to predict vegetation yield and nutrient status [14,18,19]. Among the models constructed with image parameters, those constructed using NRI and GMR were unstable, possibly because the parameters of NRI and GMR were obtained by extracting RGB values from images.…”

Section: Comparison Of Methods To Estimate Rice N Statusmentioning

confidence: 99%

“…Digital cameras are a common and inexpensive piece of equipment. They can collect image and spectral information with sufficient quality to use in predictions of crop nutrition status [12,13] and yield [14] [15], and to monitor pests [16]. Li et al extracted the dark green color index (DGCI) of image features, and concluded that DGCI was significantly correlated with the SPAD value of rice leaves.…”

Section: Introductionmentioning

confidence: 99%

Monitoring the Nitrogen Nutrition Status of Rice Plants Using Spectral and Image Technologies

Chun

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: We aimed to investigate methods to estimate the nitrogen (N) nutrition status of rice plants using data obtained using a digital camera and a spectroradiometer. The overall aim was to compare the advantages and potential of image technology and spectral technology to monitor rice N indexes accurately, inexpensively, and in real time to optimize fertilization strategies. We conducted field trials of rice plants grown with different levels of N fertilizer in 2018 to 2019. Spectral information and images of the rice canopy were obtained at the jointing stage and the booting stage. Various image and spectral characteristic parameters were selected to construct models to estimate rice N status. Results: The determination coefficients of the models constructed using the ratio vegetation index (RVI[800,720]) and cover canopy (CC) as dependent variables were highly significant. The jointing stage was the best observation period. Among the models using spectral parameters, those constructed using RVI[800,720] to estimate rice N indexes had the highest coefficient of determination (R2) values (0.79, 0.60, and 0.61 for the models to estimate leaf area index(LAI), aboveground biomass(AGB), and plant N accumulation(PNA), respectively) (P < 0.01). Among the models using image data, those using CC to predict rice N indexes showed the highest R2 values (0.76, 0.66, and 0.73 for the models to estimate LAI, AGB, and PNA, respectively) (P < 0.01). The model using the spectral parameter RVI[800,720] had a good fit and stability in estimating leaf area index (LAI; R2 = 0.7989, root mean square error (RMSE) = 0.4427, relative RMSE (RRMSE) = 11.45), and the model using the image parameter CC had a good fit in predicting plant nitrogen accumulation (PNA; R2 = 0.6768, RMSE = 11.6925 g·m-2, RRMSE = 121.78). Conclusions: Spectral and image parameters can be used as technical parameters to estimate biomass. The spectral parameter RVI[800,720] can be used to accurately estimate LAI, and the image parameter CC can be used to accurately estimate PNA, although its stability is poor. These technical parameters can be used for fast and non-destructive monitoring of rice plant biomass.

show abstract

“…Instruments for N diagnosis include a chlorophyll meter, spectrometer, unmanned aerial vehicle, and digital camera 3 – 8 . However, the above methods and instruments have some limitations in N diagnosis, as they are time-consuming, destructive, and expensive 9 , 10 . Barbedo found that close-range images can be used to detect visual changes in plant color and morphology and machine learning techniques become an effective solution 11 .…”

Section: Introductionmentioning

confidence: 99%

A novel approach for nitrogen diagnosis of wheat canopies digital images by mobile phones based on histogram

Xin

Zhao

Huang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The accurate and nondestructive assessment of leaf nitrogen (N) is very important for N management in winter wheat fields. Mobile phones are now being used as an additional N diagnostic tool. To overcome the drawbacks of traditional digital camera diagnostic methods, a histogram-based method was proposed and compared with the traditional methods. Here, the field N level of six different wheat cultivars was assessed to obtain canopy images, leaf N content, and yield. The stability and accuracy of the index histogram and index mean value of the canopy images in different wheat cultivars were compared based on their correlation with leaf N and yield, following which the best diagnosis and prediction model was selected using the neural network model. The results showed that N application significantly affected the leaf N content and yield of wheat, as well as the hue of the canopy images and plant coverage. Compared with the mean value of the canopy image color parameters, the histogram could reflect both the crop coverage and the overall color information. The histogram thus had a high linear correlation with leaf N content and yield and a relatively stable correlation across different growth stages. Peak b of the histogram changed with the increase in leaf N content during the reviving stage of wheat. The histogram of the canopy image color parameters had a good correlation with leaf N content and yield. Through the neural network training and estimation model, the root mean square error (RMSE) and the mean absolute percentage error (MAPE) of the estimated and measured values of leaf N content and yield were smaller for the index histogram (0.465, 9.65%, and 465.12, 5.5% respectively) than the index mean value of the canopy images (0.526, 12.53% and 593.52, 7.83% respectively), suggesting a good fit for the index histogram image color and robustness in estimating N content and yield. Hence, the use of the histogram model with a smartphone has great potential application in N diagnosis and prediction for wheat and other cereal crops.

show abstract

Evaluation of grain yield based on digital images of rice canopy

Cited by 17 publications

References 33 publications

Monitoring the nitrogen nutrition status of rice plants using spectral and image technologies

Monitoring the nitrogen nutrition status of rice plants using spectral and image technologies

Monitoring the Nitrogen Nutrition Status of Rice Plants Using Spectral and Image Technologies

A novel approach for nitrogen diagnosis of wheat canopies digital images by mobile phones based on histogram

Contact Info

Product

Resources

About