Counting people using video cameras

The paper is devoted to the problem of estimating the number of people visible in a camera. It uses as features a portion of foreground pixels in each cell of a rectangular grid. Using the above features and data mining techniques allowed reaching accuracy up to 85% for exact match and up to 95% for plus-minus one estimate for an indoor surveillance environment. The architecture of a real-time people counting estimator is suggested. The results of analysis of experimental data are provided and discussed. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning: I.5.2 [Pattern Recognition]: Design Methodology - classifier design and evaluation: I.5.5 [Pattern Recognition]: Implementation - special architectures. General Terms Algorithms, Experimentation. Keywords Multi-camera surveillance, video surveillance, counting people.

• Type: Journal
• Year: 2007
• Where: PAAPP
• Authors: Damian Roqueiro, Valery A. Petrushin
• Keywords: Indoor Surveillance Environment, Keywords Multi-camera Surveillance, PAAPP 2007, Pattern Recognition