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.

[1]  A. Faraji.  FLOWER FORMATION AND POD/FLOWER RATIO IN CANOLA (BRASSICA NAPUS L.) AFFECTED BY ASSIMILATES SUPPLY AROUND FLOWERING , 2010 .

[2]  A. Soltani,et al.  Effect of High Temperature Stress and Supplemental Irrigation on Flower and Pod Formation in Two Canola (Brassica napus L.) Cultivars at Mediterranean Climate , 2008 .

[3]  A. Gitelson,et al.  Novel algorithms for remote estimation of vegetation fraction , 2002 .

[4]  F. Baret,et al.  Green area index from an unmanned aerial system over wheat and rapeseed crops , 2014 .

[5]  G. King,et al.  Disruption of a CAROTENOID CLEAVAGE DIOXYGENASE 4 gene converts flower colour from white to yellow in Brassica species. , 2015, The New phytologist.

[6]  Patrick Hostert,et al.  Estimating Fractional Shrub Cover Using Simulated EnMAP Data: A Comparison of Three Machine Learning Regression Techniques , 2014, Remote. Sens..

[7]  Hongxing Liu,et al.  Exploring the Potential of WorldView-2 Red-Edge Band-Based Vegetation Indices for Estimation of Mangrove Leaf Area Index with Machine Learning Algorithms , 2017, Remote. Sens..

[8]  M. Steven,et al.  Reflexion and absorption of solar radiation by flowering canopies of oil-seed rape (Brassica napus L.) , 1987, The Journal of Agricultural Science.

[9]  John J. Sulik,et al.  Spectral indices for yellow canola flowers , 2015 .

[10]  Hao Yang,et al.  Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives , 2017, Front. Plant Sci..

[11]  Ming-Der Yang,et al.  Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery , 2017, Remote. Sens..

[12]  K. Mclaren.  XIII—The Development of the CIE 1976 (L* a* b*) Uniform Colour Space and Colour‐difference Formula , 2008 .

[13]  Vanni Nardino,et al.  Estimation of canopy attributes in beech forests using true colour digital images from a small fixed-wing UAV , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[14]  Weixing Cao,et al.  Predicting grain yield in rice using multi-temporal vegetation indices from UAV-based multispectral and digital imagery , 2017 .

[15]  G. Meyer,et al.  Color indices for weed identification under various soil, residue, and lighting conditions , 1994 .

[16]  M. Renard,et al.  Stability of the cleistogamous trait during the flowering period of oilseed rape , 2010 .

[17]  Subashisa Dutta,et al.  Spatial variability of chlorophyll and nitrogen content of rice from hyperspectral imagery , 2016 .

[18]  César Fernández-Quintanilla,et al.  Discrimination of sterile oat (Avena sterilis) in winter barley (Hordeum vulgare) using QuickBird satellite images , 2011 .

[19]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[20]  Francisca López-Granados,et al.  Broad-scale cruciferous weed patch classification in winter wheat using QuickBird imagery for in-season site-specific control , 2013, Precision Agriculture.

[21]  Ned Horning,et al.  Random Forests : An algorithm for image classification and generation of continuous fields data sets , 2010 .

[22]  Guijun Yang,et al.  Winter wheat biomass estimation based on spectral indices, band depth analysis and partial least squares regression using hyperspectral measurements , 2014 .

[23]  W. Burton,et al.  Identification of variability in phenological responses in canola-quality Brassica juncea for utilisation in Australian breeding programs , 2008 .

[24]  Jan G. P. W. Clevers,et al.  Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3 , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[25]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[26]  F. López-Granados,et al.  Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV , 2014 .

[27]  J. Cavanaugh,et al.  The Bayesian information criterion: background, derivation, and applications , 2012 .

[28]  Lei Tian,et al.  Development of methods to improve soybean yield estimation and predict plant maturity with an unmanned aerial vehicle based platform , 2016 .

[29]  Fernando López-García,et al.  Fast Surface Grading Using Color Statistics in the CIE Lab Space , 2005, IbPRIA.

[30]  Z. Niu,et al.  Remote estimation of canopy height and aboveground biomass of maize using high-resolution stereo images from a low-cost unmanned aerial vehicle system , 2016 .

[31]  Min Jiang,et al.  Estimates of rice lodging using indices derived from UAV visible and thermal infrared images , 2018 .

[32]  R. Blackshaw,et al.  Alternative oilseed crops for biodiesel feedstock on the Canadian prairies , 2011 .

[33]  André Coy,et al.  Increasing the Accuracy and Automation of Fractional Vegetation Cover Estimation from Digital Photographs , 2016, Remote. Sens..

[34]  A. Ghulam,et al.  Unmanned Aerial System (UAS)-Based Phenotyping of Soybean using Multi-sensor Data Fusion and Extreme Learning Machine , 2017 .

[35]  S. Chapman,et al.  Dynamic monitoring of NDVI in wheat agronomy and breeding trials using an unmanned aerial vehicle , 2017 .

[36]  Jianxi Huang,et al.  Assimilating a synthetic Kalman filter leaf area index series into the WOFOST model to improve regional winter wheat yield estimation , 2016 .

[37]  Aleksandra Pizurica,et al.  Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[38]  Simon Bennertz,et al.  Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[39]  Jon Nielsen,et al.  Are vegetation indices derived from consumer-grade cameras mounted on UAVs sufficiently reliable for assessing experimental plots? , 2016 .

[40]  T. Kataoka,et al.  Crop growth estimation system using machine vision , 2003, Proceedings 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2003).

[41]  F. Baret,et al.  Estimates of plant density of wheat crops at emergence from very low altitude UAV imagery. , 2017 .

[42]  C. Jordan.  Derivation of leaf-area index from quality of light on the forest floor , 1969 .

[43]  Hoam Chung,et al.  Adaptive Estimation of Crop Water Stress in Nectarine and Peach Orchards Using High-Resolution Imagery from an Unmanned Aerial Vehicle (UAV) , 2017, Remote. Sens..

[44]  James Hansen,et al.  Assimilation of remotely sensed soil moisture and vegetation with a crop simulation model for maize yield prediction , 2013 .

[45]  E. Addink,et al.  Monitoring height and greenness of non-woody floodplain vegetation with UAV time series , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[46]  M. Schaepman,et al.  Angular sensitivity analysis of vegetation indices derived from CHRIS/PROBA data , 2008 .

[47]  D. Goodin,et al.  Application of unmanned aerial systems for high throughput phenotyping of large wheat breeding nurseries , 2016, Plant Methods.

[48]  S. Labbé,et al.  A light-weight multi-spectral aerial imaging system for nitrogen crop monitoring , 2012, Precision Agriculture.

[49]  Bo-Hui Tang,et al.  Inversion of the PROSAIL model to estimate leaf area index of maize, potato, and sunflower fields from unmanned aerial vehicle hyperspectral data , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[50]  Noboru Noguchi,et al.  Monitoring of Wheat Growth Status and Mapping of Wheat Yield's within-Field Spatial Variations Using Color Images Acquired from UAV-camera System , 2017, Remote. Sens..

[51]  Antonio Criminisi,et al.  Object Class Segmentation using Random Forests , 2008, BMVC.

[52]  Kan Liu,et al.  Remote Estimation of Vegetation Fraction and Flower Fraction in Oilseed Rape with Unmanned Aerial Vehicle Data , 2016, Remote. Sens..

[53]  N. D. Tillett,et al.  Automated Crop and Weed Monitoring in Widely Spaced Cereals , 2006, Precision Agriculture.