Table 4 Summary of key mathematical innovations and performance gains in advanced uav tracking.
From: Advanced algorithms for UAV tracking of targets exhibiting start-stop and irregular motion
Innovation | Mathematical Contribution | Performance Gain |
|---|---|---|
Innovation-based Model Switching | Confidence metric \(\:{C}_{i}\left(k\right)\) for automatic motion model selection | + 23.4% vs. Standard KF |
Jerk-compensated α-β-γ-δ Filter | Four-parameter state prediction with adaptive optimization | + 15–25% irregular motion |
Flow-guided Margin Loss | Motion-weighted loss function for the long-tail problem | + 18.7% large motion tracking |
3D-to-2D Uncertainty Propagation | Covariance projection for measurement guidance | 2.3s recovery time |
