Abstract
Automatic crowd detection in aerial images is certainly a useful source of information to prevent crowd disasters in large complex scenarios of mass events. A number of publications employ regression-based methods for crowd counting and crowd density estimation. However, these methods work only when a correct manual count is available to serve as a reference. Therefore, it is the objective of this paper to detect high-density crowds in aerial images, where counting– or regression–based approaches would fail. We compare two texture–classification methodologies on a dataset of aerial image patches which are grouped into ranges of different crowd density. These methodologies are: (1) a Bag–of–words (BoW) model with two alternative local features encoded as Improved Fisher Vectors and (2) features based on a Gabor filter bank. Our results show that a classifier using either BoW or Gabor features can detect crowded image regions with 97% classification accuracy. In our tests of four classes of different crowd-density ranges, BoW–based features have a 5%–12% better accuracy than Gabor.
Highlights
We show that crowded regions in aerial images can be regarded as a texture, and propose robust patch-based Bag-of-Words methods for the detection of these regions
We test the general ability of the proposed methods to detect crowded regions in aerial images and to discriminate patches with only small texture differences
We compare the classification accuracy of an SVM trained with Gabor features with an SVM trained with BoW-Local Binary Pattern (LBP) and BoW-Sorted Random Projections (SRP) features
Summary
A lot of research has been done to process this huge amount of data automatically [1,2,3,4], and most often with the goal of crowd counting [5,6,7,8], person tracking [9,10], or behavior understanding [11,12]. All these methods are tested on benchmark datasets containing terrestrial images or videos, and do not consider aerial images for crowd counting. Low flying platforms like helicopters or small drones could help, but these are either very loud or not well accepted in public
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
