Elliptical Model-Based Robust Pedestrian Pose Tracking by LiDAR via Bi-Level Moving Horizon Random Sample Consensus

Abstract

Recent advancements in autonomous vehicle research have heightened the need for precise pedestrian pose tracking to ensure safe navigation. Utilizing LiDAR sensors, conventional bounding box (BB) methods are generally used but are sensitive to limb motion. The previous moving horizon-based maximum likelihood estimation sample consensus (MHESAC) study addressed this robustness limitation but suffered from extensive point cloud (PC) sampling, limiting real-time applications. This paper proposes an elliptical pedestrian model tracking within a sequential bi-level MHESAC (B-MHESAC) framework that combines random sampling consensus (RANSAC) for local model fitting per time step and maximum likelihood estimation sample consensus (MLESAC) for optimal model sequence selection throughout the horizon, significantly reducing PC sampling while preserving accuracy. Under significant outlier contamination, B-MHESAC requires less trials than MHESAC for multiple horizons and samples. Moreover, at long horizon lengths, B-MHESAC required trial’s exponential growth is at least reduced to the fifth root of MHESAC, allowing real-time estimations. The proposed method was evaluated in an indoor single pedestrian tracking experiment. Experimental results demonstrate that B-MHESAC is more robust than conventional RANSAC in model fitting. Additionally, the elliptical model-based B-MHESAC’s tracking performance is competitive with the MHESAC method’s and superior to other Kalman filter-based BB and circle model methods.

Keywords

• Light detection and ranging
• maximum likelihood estimation
• model fitting
• moving horizon estimation
• pedestrian tracking
• random sample consensus