Remote Sensing Surveillance Using Multilevel Feature Fusion and Deep Neural Network

Computer Science

• Unmanned Aerial Vehicle 100%
• Deep Neural Network 100%
• Object Detection 100%
• Feature Fusion 100%
• YOLO 100%
• Feature Extraction 50%
• Distance Measure 50%
• Recognition Accuracy 50%
• image feature 50%
• Extracted Feature 50%
• Action Recognition 50%
• Image Quality 50%
• Point Cloud 50%
• Dynamic Nature 50%
• human action recognition 50%
• Geodesic Distance 50%
• Preprocessing Technique 50%
• Discriminant Analysis 50%
• Classification Action 50%

Engineering

• Deep Neural Network 100%
• Drone 100%
• Keypoints 100%
• Human Action 100%
• Unmanned Aerial Vehicle 66%
• Extracted Feature 33%
• Feature Extraction 33%
• State-of-the-Art Method 33%
• Dynamic Nature 33%
• Grayscale 33%
• Gaussian Blur 33%
• Recognition Accuracy 33%
• Point Cloud 33%