Comparison and Analysis of Recursive-RANSAC for Multiple Target Tracking

In both simulated and real experiments, the recursive random sample consensus (R-RANSAC) algorithm has shown promise as an efficient multiple target tracking (MTT) filter. In this paper, we introduce a generalized and modular framework for the R-RANSAC algorithm, analyze the sensitivity of the R-RANSAC tuning parameters, and compare R-RANSAC to five well-known MTT algorithms. We show that R-RANSAC offers a unique balance between low computational complexity, excellent track continuity, and good performance in cluttered environments.