Computational end-to-end and super-resolution methods to improve thermal infrared remote sensing for agriculture

Keyphrases

• Super-resolution Algorithm 100%
• Agricultural Data 100%
• Root Mean Square Error 100%
• Thermal Infrared Remote Sensing 100%
• Low Altitude 100%
• Remote Sensing for Agriculture 100%
• Computational Methods 50%
• High Temperature 50%
• Irrigation 50%
• Agriculture 50%
• Yield Improvement 50%
• Neural Network 50%
• Thermal Camera 50%
• Imaging Methods 50%
• Low Coverage 50%
• Super-resolution 50%
• Computational Imaging 50%
• Time Limits 50%
• Water Demand 50%
• High Spatial Resolution 50%
• Initial Preparation 50%
• Convolutional Neural Network 50%
• Radiometric Data 50%
• Image Mosaicking 50%
• Remote Sensing 50%
• Water Deficit 50%
• Long Waves 50%
• Sub-image 50%
• High-resolution Monitoring 50%
• Simulated Case 50%
• Ground Truth Measurement 50%
• Potential Capabilities 50%
• Temperature Accuracy 50%
• Global Water 50%
• Crop Water Stress 50%
• Radiometric Accuracy 50%
• Aerial Survey 50%
• Bicubic Interpolation 50%
• Image Sharpness 50%
• Thermal Infrared Camera 50%
• Joint Estimation Method 50%

Earth and Planetary Sciences

• Root-Mean-Square Error 100%
• Thermal Infrared Remote Sensing 100%
• Interpolation 50%
• Computational Method 50%
• Estimation Method 50%
• High Spatial Resolution 50%
• Imaging Method 50%
• Readout 50%
• Aerial Survey 50%
• Water Stress 50%
• Remote Sensing 50%