How Pruning is done in trackerTOMHT?

12 次查看（过去 30 天）
Usman
Usman 2025-8-12，10:35
回答： Elad Kivelevitch 2025-8-12，15:37

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?

请先登录，再回答此问题。

采纳的回答

Elad Kivelevitch
Elad Kivelevitch 2025-8-12，15:37
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.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Multi-Object Trackers 的更多信息

标签

产品


版本

R2023b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by