A comparison of neural-based techniques investigating rotational invariance for upright people detection in low resolution imagery

Authors:
Steve Green;Michael Blumenstein
Affiliations:
Griffith University, Gold Coast, Queensland, Australia;Griffith University, Gold Coast, Queensland, Australia
Venue:
AI'07 Proceedings of the 20th Australian joint conference on Advances in artificial intelligence
Year:
2007

Citing 3
Cited 0

Advanced image-processing tools for counting people in tourist site-monitoring applications

Signal Processing
Real-time surveillance system detecting persons in complex scenes

Real-Time Imaging
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a neural-based technique for detecting upright persons in low-resolution beach imagery in order to predict trends of tourist activities at beach sites. The proposed system uses a structural feature extraction technique to represent objects of interest for training a selection of neural classifiers. A number of neural-based classifiers are compared in this study and a direction-based feature extraction technique is investigated in conjunction with a rotationally invariant procedure for the purpose of beach object classification. Encouraging results are presented for person detection using video imagery collected from a beach site on the coast of Australia.