Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking
This addresses the problem of multi-target, multi-type visual tracking for applications like surveillance or autonomous systems, but it is incremental as it extends existing PHD filter methods.
The paper tackles the problem of tracking multiple targets with multiple types in video sequences by extending the Gaussian mixture PHD filter to handle N≥2 target types, accounting for both background clutter and inter-type detection confusions. The approach shows improved performance over raw detection and independent filters when evaluated on real video sequences using the Optimal Sub-pattern Assignment metric and discrimination rate.
We propose a new framework that extends the standard Probability Hypothesis Density (PHD) filter for multiple targets having $N\geq2$ different types based on Random Finite Set theory, taking into account not only background clutter, but also confusions among detections of different target types, which are in general different in character from background clutter. Under Gaussianity and linearity assumptions, our framework extends the existing Gaussian mixture (GM) implementation of the standard PHD filter to create a N-type GM-PHD filter. The methodology is applied to real video sequences by integrating object detectors' information into this filter for two scenarios. For both cases, Munkres's variant of the Hungarian assignment algorithm is used to associate tracked target identities between frames. This approach is evaluated and compared to both raw detection and independent GM-PHD filters using the Optimal Sub-pattern Assignment metric and discrimination rate. This shows the improved performance of our strategy on real video sequences.