Automatic crowd analysis from airborne images

Abstract

Recently automatic detection of people and crowded areas from images became a very important research field, since it can provide crucial information especially for police departments and crisis management teams. Detection of crowd and measuring the density of people can prevent possible accidents or unpleasant conditions to appear. Understanding behavioral dynamics of large people groups can also help to estimate future states of underground passages, shopping center like public entrances, or streets which can also affect the traffic. In order to bring a solution to this problem, herein we propose a novel approach using airborne images. Although their resolutions are not enough to see each person in detail, we can still notice a change of color components in the place where a person exists. Therefore, we propose a color feature detection based probabilistic framework. First, we extract local features from invariant chroma bands of the image. Extracted local features behave as observations of the probability density function (pdf) of the crowd to be estimated. Using an adaptive kernel density estimation method, we estimate the corresponding pdf. The estimated pdf gives information about crowded regions, and also helps to extract quantitative measures about them. Our experimental results show that the proposed approach can provide crucial information to police departments and crisis management teams to achieve more detailed observations of crowds to prevent possible accidents or unpleasant conditions in robust and fast manner.