FRCNN-Based Reinforcement Learning for Real-Time Vehicle Detection, Tracking and Geolocation from UAS

Computer Science

• Reinforcement Learning 100%
• Vehicle Detection 100%
• Unmanned Aerial Vehicle 100%
• Adaptive Filter Design 50%
• Morphological Operations 50%
• Convolutional Neural Network 50%
• Final Decision 50%
• Motion Feature 50%
• Phase Detection 50%
• Motion Characteristic 50%
• Background Region 50%
• Potential Application 50%
• Traffic Monitoring 50%
• Policy Making 50%
• Detection Algorithm 50%
• Smaller Collection 50%

INIS

• detection 100%
• learning 100%
• vehicles 100%
• applications 57%
• algorithms 42%
• noise 42%
• motion 42%
• transport 14%
• size 14%
• capacity 14%
• accuracy 14%
• transformations 14%
• monitoring 14%
• density 14%
• images 14%
• sensors 14%
• surveillance 14%
• policy 14%
• neural networks 14%
• operation 14%
• trajectories 14%

Engineering

• Geolocation 100%
• Reinforcement Learning 100%
• Unmanned Aerial Vehicle 66%
• Potential Application 33%
• Detection Algorithm 33%
• Morphological Operations 33%
• Adaptive Filter Design 33%
• Induced Noise 33%
• Intelligent Transport 33%
• Target Vehicle 33%
• Feature Point 33%
• Urban Traffic 33%
• Policy Making 33%
• Background Region 33%
• Convolutional Neural Network 33%