Real-time Crowd Tracking using Parameter Optimized Mixture of Motion Models

Abstract

We present a novel, real-time algorithm to track the trajectory of each pedestrian in moderately dense crowded scenes. Our formulation is based on an adaptive particle-filtering scheme that uses a combination of various multi-agent heterogeneous pedestrian simulation models. We automatically compute the optimal parameters for each of these different models based on prior tracked data and use the best model as motion prior for our particle-filter based tracking algorithm. We also use our "mixture of motion models" for adaptive particle selection and accelerate the performance of the online tracking algorithm. The motion model parameter estimation is formulated as an optimization problem, and we use an approach that solves this combinatorial optimization problem in a model independent manner and hence scalable to any multi-agent pedestrian motion model. We evaluate the performance of our approach on different crowd video datasets and highlight the improvement in accuracy over homogeneous motion models and a baseline mean-shift based tracker. In practice, our formulation can compute trajectories of tens of pedestrians on a multi-core desktop CPU in in real time and offer higher accuracy as compared to prior real time pedestrian tracking algorithms.

The Emotionally Intelligent Robot: Improving Social Navigation in Crowded Environments

“…Given a pedestrian tracker [8], [6] that works well on low-to medium-density crowds, we extract pedestrian trajectories. We use Bayesian inference to compensate for noise in the trajectories extracted by the pedestrian trackers.…”

The Socially Invisible Robot Navigation in the Social World Using Robot Entitativity

“…Many approaches have been applied towards the navigation of socially-aware robots [31], [7], [3], [15], [25], [29], [18], [26], [24]. This type of navigation can be generated by predicting the movements of pedestrians and their interactions with robots [26], [4], [40], [33], [2].…”