The Community for Technology Leaders
Computational Intelligence and Multimedia Applications, International Conference on (2005)
Las Vegas, Nevada
Aug. 16, 2005 to Aug. 18, 2005
ISBN: 0-7695-2358-7
pp: 303-308
Michael Blumenstein , Griffith University
Matthew Browne , Griffith University
Steve Green , Griffith University
Rodger Tomlinson , Griffith University
This paper presents an initial investigation into the detection and quantification of persons in real-world beach scenes for the automated monitoring of tourist sites. Aside from the obvious use of video and digital imagery for surveillance applications, this research focuses on the analysis of images for the purpose of predicting trends of tourist activities at beach sites in Australia. The proposed system uses image enhancement and segmentation techniques to detect objects in cluttered scenes. Following these steps, a newly proposed feature extraction technique is used to represent important information in the extracted objects for training of a neural network. The neural classifier is used to distinguish the extracted objects between "person" and "non-person" categories to assist in quantification. Encouraging results are presented for person classification on a database of real-word beach scenes.
Michael Blumenstein, Matthew Browne, Steve Green, Rodger Tomlinson, "The Detection and Quantification of Persons in Cluttered Beach Scenes Using Neural Network-Based Classification", Computational Intelligence and Multimedia Applications, International Conference on, vol. 00, no. , pp. 303-308, 2005, doi:10.1109/ICCIMA.2005.57
88 ms
(Ver 3.1 (10032016))