Automated crowd flow estimation enhanced by crowdsourcing
Javier Ribera, Khalid Tahboub, Edward J. Delp · 2014
Video surveillance systems that contain a large number of cameras makes the continuous monitoring of the video feeds nearly an impossible task. If the information from these many cameras is to be exploited automatic video analytic techniques must be developed. In this paper, we present improvements to a previously developed crowd flow estimation method. We use crowdsourcing techniques to enhance the performance. An experimental evaluation is conducted using publicly available datasets.