Discrete-Continuous Optimization for Multi-Target Tracking (CVPR 2012)





The interactive transcript could not be loaded.


Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Mar 1, 2012

Code available: http://goo.gl/rkKXN

The problem of multi-target tracking is comprised of two distinct, but
tightly coupled challenges: (i) the naturally discrete problem of data
association, \ie assigning image observations to the appropriate
target; (ii) the naturally continuous problem of trajectory
estimation, \ie recovering the trajectories of all targets. To go
beyond simple greedy solutions for data association, recent approaches
often perform multi-target tracking using discrete optimization. This
has the disadvantage that trajectories need to be pre-computed or
represented discretely, thus limiting accuracy. In this paper we
instead formulate multi-target tracking as a discrete-continuous
problem that handles each aspect in its natural domain and allows one
to leverage powerful algorithms for multi-model fitting. Data
association is performed using discrete optimization with label costs,
and can be solved to near optimality. Trajectory estimation is posed
as a continuous fitting problem with a simple closed-form solution,
which is used in turn to update the label costs. We demonstrate the
accuracy and robustness of our
approach with state-of-the-art performance on several standard


When autoplay is enabled, a suggested video will automatically play next.

Up next

to add this to Watch Later

Add to

Loading playlists...