Blob motion statistics for pedestrian detection

Borges, Paulo Vinicius Koerich (2011). Blob motion statistics for pedestrian detection. In: DICTA 2011 : 2011 International Conference on Digital Image Computing: Techniques and Applications, proceedings. International Conference on Digital Image Computing: Techniques and Applications, Noosa Head, Queensland, Australia, (442-447). 6-8 December 2011. doi:10.1109/DICTA.2011.81

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Borges, Paulo Vinicius Koerich
Title of paper Blob motion statistics for pedestrian detection
Conference name International Conference on Digital Image Computing: Techniques and Applications
Conference location Noosa Head, Queensland, Australia
Conference dates 6-8 December 2011
Proceedings title DICTA 2011 : 2011 International Conference on Digital Image Computing: Techniques and Applications, proceedings
Place of Publication Los Alamitos, CA United States
Publisher I E E E Computer Society
Publication Year 2011
Sub-type Fully published paper
DOI 10.1109/DICTA.2011.81
ISBN 9780769545882
Start page 442
End page 447
Total pages 6
Collection year 2012
Language eng
Formatted Abstract/Summary
Video analysis aiming at efficient pedestrian detection is an important research area in computer vision and robotics. Although this is a well studied topic, successful detection still remains a challenge in outdoor, low resolution images. We present efficient detection metrics which consider the fact that human movement presents some characteristic patterns. Unlike many methods which perform an intra-blob  analysis based on motion masks, we approach the problem without necessarily considering the pixel distribution inside the blob. Therefore, we apply periodicity analysis not to the pixel luminances inside the blob, but by analyzing the motion statistics of the tracked blob as a whole. We propose the use of three cues: (i) a cyclic behavior in the blob trajectory, (ii) an in-phase relationship between the change in blob size and position, and (iii) a correlation between blob size and vertical position, assuming that the camera is set up sufficiently high. These features are combined according to the Bayes classifier for improved performance. Experiments presentv numerical error rates and comparisons with other methods, illustrating the applicability of the proposed method.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 3 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 25 Jun 2012, 10:01:13 EST by Paulo Borges on behalf of School of Information Technol and Elec Engineering