1. Crowd detection in airborne images using spatial point statistics
- Author
-
Peter Reinartz, Abdullah H. Ozcan, Cem Unsalan, Özcan, A.H., Ünsalan, Cem, Reinartz, P., and Yeditepe Üniversitesi
- Subjects
Ocillators ,Photogrammetrie und Bildanalyse ,MATLAB ,Support vector machines ,Point (typography) ,Computer science ,business.industry ,Sample (statistics) ,Remote sensing ,Cameras ,computer.software_genre ,Correlation ,Image (mathematics) ,k-nearest neighbors algorithm ,Statistics ,Feature extraction ,Computer vision ,Data mining ,Artificial intelligence ,business ,Spatial analysis ,computer - Abstract
The crowd density in public places increases in social events. If an emergency occurs during such events, authorities should take urgent measures to prevent causalities. Therefore, crowd detection and analysis is a critical research area. Even though there are several studies on person detection from street or indoor cameras, these may not be directly used to detect or analyze the crowd formed from people. In this study, we approach the problem using aerial images. We propose two novel methods to detect the crowd using spatial statistics. The first novel method is based on the first-order statistics. It uses the nearest neighbor relations for each person in the image. The second novel method is based on the second-order statistics. Here, the spatial position of persons are checked whether they are clustered or randomly distributed. We test these two methods on a sample test image and provide performance measures. © 2015 IEEE. 2015 23rd Signal Processing and Communications Applications Conference, SIU 2015 -- 16 May 2015 through 19 May 2015 -- -- 113052
- Published
- 2015