Appearances can be deceiving
Learning visual tracking from few trajectory annotations

Santiago Manen, Junseok Kwon, Matthieu Guillaumin, Luc Van Gool

European Conference on Computer Vision 2014

Paper
Paper download
Dataset
Dataset

Overview

Visual tracking is the task of estimating the trajectory of an object in a video given its initial location. This is usually done by combining at each step an appearance and a motion model.

In this work, we learn from a small set of training trajectory annotations how the objects in the scene typically move. We learn the relative weight between the appearance and the motion model. We call this weight: visual deceptiveness. At test time, we transfer the deceptiveness and the displacement from the closest trajectory annotation to infer the next location of the object. Further, we condition the transference on an event model.

On a set of 161 manually annotated test trajectories, we show in our experiments that learning from just 10 trajectory annotations halves the center location error and improves the success rate by about 10%.

BibTex reference

@incollection{
year={2014},
isbn={978-3-319-10601-4},
booktitle={Computer Vision - ECCV 2014},
volume={8693},
series={Lecture Notes in Computer Science},
editor={Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne},
title={Appearances Can Be Deceiving: Learning Visual Tracking from Few Trajectory Annotations},
publisher={Springer International Publishing},
author={Manen, Santiago and Kwon, Junseok and Guillaumin, Matthieu and Van Gool, Luc},
pages={157-172},
language={English}
}

Acknowledgements

The authors gratefully acknowledge support by Toyota.
This work was supported by the European Research Council (ERC) under the project VarCity (#273940).

Please report problems with this page to Santiago Manen
Last updated on Wednesday, 30th October, 2013