Temporal filter based target detection and tracking using multiple filter bank

We propose a method to detect multiple point sized targets in an image sequence using temporal mutliscale decomposition. The proposed method uses motion as a cue to detect target, which-is independent of any feature. Along with detection, a method is proposed to track maneuvering or non-maneuvering targets simultaneously using multiple filter bank approach in an image sequence. The switch-over between the filters is based on a single-step decision logic and consequently, is computationally more efficient, and performance wise more robust.