Computational complexity analysis for multiple hypothesis tracking

This paper presents a detailed analysis of computational complexity of Multiple Hypothesis Tracking (MHT). The result proves that the computational complexity of MHT is dominated by the number of hypotheses. Effects of track merging and pruning are analyzed also. Certain common design parameters of MHT, such as thresholds, are also discussed in detail. The results of this paper provide a guidance for selecting parameters in an MHT tracker and predicting its performance. the design parameters discussed in this paper, track merging appears to be the most important way for controlling the computational complexity of MHT. Thresholds for track deletion are also critical. If not all measurements are allowed to initiate new tracks, the number of new tracks can also be used for tuning the computation requirement of MHT, but it is not as significant as thresholds.