Boris Meden

  • Citations Per Year
Learn More
This article tackles the problem of automatic multipedestrian tracking in non-overlapping fields of view camera networks, using monocular, uncalibrated cameras. Tracking is locally addressed by a Tracking-by-Detection and re-identification algorithm. We propose here to introduce a notion of global identity into a multi-target tracking algorithm, qualifying(More)
We present a pedestrian tracking system that uses re-identification to monitor non-overlapping cameras. As tracking, re-identification is an assignment problem, the difficulties being to generate an accurate representation and to prune unlikely pairings. The assignments are realised in two stages. First, a Markovian multi-target tracking-by-detection(More)
  • 1