Linear Trajectory Avoidance - A Pedestrian Motion Model


Object tracking typically relies on a dynamic model to predict the object's location from its past trajectory. In crowded scenarios a strong dynamic model is particularly important, because more accurate predictions allow for smaller search regions, which greatly simplifies data association. Traditional dynamic models predict the location for each target solely based on its own history, without taking into account the remaining scene objects. Collisions are resolved only when they happen. Such an approach ignores important aspects of human behavior: people are driven by their future destination, take into account their environment, anticipate collisions, and adjust their trajectories at an early stage in order to avoid them. Here we introduce a model of dynamic social behavior, inspired by models developed for crowd simulation. The model is trained with videos recorded from birds-eye view at busy locations, and applied as a motion model for multi-people tracking from a vehicle-mounted camera.

Paper

S. Pellegrini, A. Ess, K. Schindler, L. van Gool
You'll Never Walk Alone: Modeling Social Behavior for Multi-target Tracking
ICCV 2009
pdf

@INPROCEEDINGS{Pellegrini2009ICCV,
author = {Stefano Pellegrini and Andreas Ess and Konrad Schindler and Luc van Gool},
title = {You'll Never Walk Alone: Modeling Social Behavior for Multi-target Tracking},
booktitle = {ICCV},
year = {2009}
}


Datasets

Walking pedestrians in busy scenarios from a bird eye view. Manually annotated.

WARNING: on 17/09/2009 the dataset have been modified, the frame number in the obsmat had a wrong offset (Thanks for corrections to Paul Scovanner)


dataset link

Results

Here are the video sequences showing some results. Note that the pauses in the videos are used only to better show when, in one of the two motion priors (LTA and EKF), an ID-switch occurs. The arrow marks the person that undergoes an ID-switch. On the right hand side you have the reconstructed top view of the scene.

video sequence 1 - results
video sequence 2 - results