Object Flow: Learning Object Displacement

Constantinos Lalos, Helmut Grabner, Luc Van Gool, Theodora A. Varvarigou

Abstract

Abstract. Modelling the dynamic behaviour of moving objects is one of the basic tasks in computer vision. In this paper, we introduce the Object Flow, for estimating both the displacement and the direction of an object-of-interest. Compared to the detection and tracking techniques, our approach obtains the ob-ject displacement directly similar to optical flow, while ignoring other irrelevant movements in the scene. Hence, Object Flow has the ability to continuously focus on a specific object and calculate its motion field. The resulting motion represen-tation is useful for a variety of visual applications (e.g., scene description, object tracking, action recognition) and it cannot be directly obtained using the existing methods. 1
BibTeX
@inproceedings{lalos2010object,
  author = {Constantinos Lalos and Helmut Grabner and Luc Van Gool and Theodora A. Varvarigou},
  title = {{Object Flow: Learning Object Displacement}},
  booktitle = {ACCV Workshops},
  year = {2010},
  doi = {10.1007/978-3-642-22822-3\_14},
}

Loading related content...

Figure