Realtime Multilevel Crowd Tracking using Reciprocal Velocity Obstacles
This work addresses the problem of efficient crowd tracking for applications like surveillance or robotics, though it is incremental as it builds on existing particle filtering and velocity obstacle methods.
The paper tackles real-time pedestrian tracking in moderately dense crowds by introducing an adaptive particle filtering algorithm that uses a multi-agent motion model based on velocity obstacles, achieving speeds 4-5 times faster than prior methods with similar accuracy at 27-30 frames per second.
We present a novel, realtime algorithm to compute the trajectory of each pedestrian in moderately dense crowd scenes. Our formulation is based on an adaptive particle filtering scheme that uses a multi-agent motion model based on velocity-obstacles, and takes into account local interactions as well as physical and personal constraints of each pedestrian. Our method dynamically changes the number of particles allocated to each pedestrian based on different confidence metrics. Additionally, we use a new high-definition crowd video dataset, which is used to evaluate the performance of different pedestrian tracking algorithms. This dataset consists of videos of indoor and outdoor scenes, recorded at different locations with 30-80 pedestrians. We highlight the performance benefits of our algorithm over prior techniques using this dataset. In practice, our algorithm can compute trajectories of tens of pedestrians on a multi-core desktop CPU at interactive rates (27-30 frames per second). To the best of our knowledge, our approach is 4-5 times faster than prior methods, which provide similar accuracy.