Joint Flow: Temporal Flow Fields for Multi Person Tracking
share
In this work we propose an online multi person pose tracker which works on two consecutive frames I_t-1 and I_t. The general formulation of our temporal network allows to rely on any multi person pose estimation network as spatial network. From the spatial network we extract image features and pose features for both frames. These features compose as input for our temporal model that predicts Temporal Flow Fields (TFF). These TFF are vector fields which indicate the direction in which body joint is going to move from frame I_t-1 to frame I_t. This novel representation allows to formulate a similarity measure of detected joints. These similarities are used as binary potentials in an bipartite graph optimization problem in order to perform tracking of multiple poses. We show that these TFF can be learned by a relative small CNN network whilst achieving state-of-the-art multi person pose tracking results.
READ FULL TEXT