Detection of High-Density Crowds in Aerial Images Using Texture Classification
Monitoring the behavior of people in complex environments has gained much attention over the past years. Most of the current approaches rely on video cameras mounted on buildings or pylons and individuals are detected and tracked in these video streams. Our approach is intended to complement this work. We base the monitoring of people on aerial camera systems mounted on aircrafts, helicopters or airships. This imagery is characterized by a very large coverage so that the distribution of people over a large field of view can be analyzed. Yet, as the frame rate of such image sequences is usually much lower compared to video streams (only 3 up to 7Hz), tracking approaches different from optical flow or KLT-tracking need to be employed. We show that reliable information for the density of groups of people, their activity as well as their locomotion can be derived from these kind of data.