3209

Dense point trajectories by GPU-accelerated large displacement optical flow

Narayanan Sundaram, Thomas Brox, Kurt Keutzer
Electrical Engineering and Computer Sciences, University of California at Berkeley
In Proceedings of the 11th European conference on Computer vision: Part I (2010), pp. 438-451

@article{sundaram2010dense,

   title={Dense point trajectories by GPU-accelerated large displacement optical flow},

   author={Sundaram, N. and Brox, T. and Keutzer, K.},

   journal={Computer Vision–ECCV 2010},

   pages={438–451},

   year={2010},

   publisher={Springer}

}

Download Download (PDF)   View View   Source Source   

936

views

Dense and accurate motion tracking is an important requirement for many video feature extraction algorithms. In this paper we provide a method for computing point trajectories based on a fast parallel implementation of a recent optical flow algorithm that tolerates fast motion. The parallel implementation of large displacement optical flow runs about 78x faster than the serial C++ version. This makes it practical to use in a variety of applications, among them point tracking. In the course of obtaining the fast implementation, we also proved that the fixed point matrix obtained in the optical flow technique is positive semi-definite. We compare the point tracking to the most commonly used motion tracker – the KLT tracker – on a number of sequences with ground truth motion. Our resulting technique tracks up to three orders of magnitude more points and is 46% more accurate than the KLT tracker. It also provides a tracking density of 48% and has an occlusion error of 3% compared to a density of 0.1% and occlusion error of 8% for the KLT tracker. Compared to the Particle Video tracker, we achieve 66% better accuracy while retaining the ability to handle large displacements while running an order of magnitude faster.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: