Surveillance Camera Autocalibration based on Pedestrian Height Distributions

@inproceedings{Liu2011SurveillanceCA,
  title={Surveillance Camera Autocalibration based on Pedestrian Height Distributions},
  author={Jingchen Liu and jingchen},
  year={2011}
}
We propose a new framework for automatic surveillance camera calibration by observing videos of pedestrians walking through the scene. Existing methods require accurate pedestrian detection and tracking [1, 2, 3] and have limited practical use in more challenging real-world environments (Fig. 1). Our method takes noisy foreground masks as input with no need to track or label correspondences of the same person between frames. Instead, we look for a camera model that recovers the most realistic… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS