How Pruning is done in trackerTOMHT?

I want to know how pruning is done in trackerTOMHT, specifically: 1. In N-Scan pruning, I have seen that tracks are not pruned if their nodes are different from most likely branch at previous scan. Instead it pruning is done if nodes split in k-2 scan. Please clear this up. 2. How pruning works, if track branches become more than that specified in MaxNumTrackBranches Property? 3. Track Branches have revised scores in the end which is different from the scores in the field: analysisInfo.KeptBranchScores (outputted by tracker). Why they are different and how they are computed?

Answer 1

[Elad Kivelevitch]

This is all explained in the trackerTOMHT references (https://www.mathworks.com/help/fusion/ref/trackertomht-system-object.html):

[1] Werthmann, J. R.. "Step-by-Step Description of a Computationally Efficient Version of Multiple Hypothesis Tracking." In International Society for Optics and Photonics, Vol. 1698, pp. 228-301, 1992.

[2] Blackman, S., and R. Popoli. Design and Analysis of Modern Tracking Systems. Artech House Radar Library, Boston, 1999.