This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Multi-View Tracking of Multiple Targets with Dynamic Cameras

T. Kroeger, R. Dragon, L. Van Gool
36th German Conference on Pattern Recognition


We propose a new tracking-by-detection algorithm for multiple tar- gets from multiple dynamic, unlocalized and unconstrained cameras. In the past tracking has either been done with multiple static cameras, or single and stereo dynamic cameras. We register several moving cameras using a given 3D model from Structure from Motion (SfM), and initialize the tracking given the regis- tration. The camera uncertainty estimate can be efficiently incorporated into a flow-network formulation for tracking. As this is a novel task in the tracking do- main, we evaluate our method on a new challenging dataset for tracking with multiple moving cameras and show that our tracking method can effectively deal with independently moving cameras and camera registration noise.

Download in pdf format
  author = {T. Kroeger and R. Dragon and L. Van Gool},
  title = {Multi-View Tracking of Multiple Targets with Dynamic Cameras},
  booktitle = {36th German Conference on Pattern Recognition},
  year = {2014},
  keywords = {}