Table 10.

Application of high-throughput phenotyping platforms and imaging sensors for improving abiotic stresses and agronomic traits in field crops during the last decade.

Crop	Phenotyping Platform Sensor or Techniques	Field/ Lab	Abiotic Stresses/ Agronomic Traits	Imaging Sensor	Description	Reference
Rice	Ground-based platforms	Lab	Salinity	Thermal imaging	Plant growth and transpiration rate was used to predict the salinity responses of plants	[214]
Rice	Ground-based platforms	Field	Nitrogen content	Hyperspectral imaging	Reflectance information and cumulative temperature data were used in the partial least square method for predicting nitrogen status	[210]
Rice	Ground-based platforms	Field	Drought stress	RGB imaging	Stay green-related feature were extracted for assessing drought-tolerance ability	[196]
Wheat	Ground-based platforms	Field	Drought	Passive and active hyperspectral reflectance sensors	Performances of different sensors were evaluated for predicting drought tolerance abilities of genotypes with water stress indices	[208]
Wheat	Manned helicopter	Field	Water and heat stress	Thermal imaging	Canopy temperature was measured in high-throughput way for avoiding the plot-to-plot variation with handheld infrared thermometers	[212]
Wheat	Ground-based platforms	Field	Nitrogen content	Hyperspectral imaging	Leaf nitrogen status was measured from spectral information with a calibrated model	[217]
Maize	Organ/tissue phenotyping	Lab	Drought stress	Hyperspectral imaging	Support vector machine classification method separated the water-stressed genotypes from healthy plants with information from vegetation indices	[218]
Maize	Unmanned aerial vehicle	Field	Water status in plants	Multispectral and thermal imaging	Crop water stress index was predicted from the multispectral images to decipher the plant water status	[219]
Maize	Unmanned aerial vehicle	Field	Weeds	RGB imaging	Loss of greenness from maize was used for separating weeds from the plants	[220]
Barley	Ground-based platforms	Field	Drought	Hyperspectral imaging	Linear ordinal support vector machine model was used to predict the drought responses in the plants	[209]
Barley	Organ/tissue phenotyping	Lab	Salinity	Thermal imaging	Infrared imaging was used to differentiate salt concentration among the genotypes	[191]
Barley	Unmanned aerial vehicle	Field	Nitrogen use efficiency	RGB, multispectral, and thermal imaging	UAV’s having RGB, multispectral, and thermal imaging was utilized for nitrogen use efficiency	[221]
Sorghum	Ground-based platforms	Field	Plant height	RGB, ultrasonic, and LIDAR sensor	A comparison was performed for predicting sorghum height, with the LIDAR sensor performing best	[222]
Sorghum	Unmanned aerial vehicle	Field	Drought stress	RGB imaging	Plant height, biomass, and leaf area were measured for assessing the drought-tolerant abilities of genotypes	[223]