Share Email Print

Proceedings Paper

Pedestrian detection system based on HOG and a modified version of CSS
Author(s): Daniel Luis Cosmo; Evandro Ottoni Teatini Salles; Patrick Marques Ciarelli
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes a complete pedestrian detection system based on sliding windows. Two feature vector extraction techniques are used: HOG (Histogram of Oriented Gradient) and CSS (Color Self Similarities), and to classify windows we use linear SVM (Support Vector Machines). Besides these techniques, we use mean shift and hierarchical clustering, to fuse multiple overlapping detections. The results we obtain on the dataset INRIA Person shows that the proposed system, using only HOG descriptors, achieves better results over similar systems, with a log average miss rate equal to 43%, against 46%, due to the cutting of final detections to better adapt them to the modified annotations. The addition of the modified CSS increases the efficiency of the system, leading to a log average miss rate equal to 39%.

Paper Details

Date Published: 14 February 2015
PDF: 5 pages
Proc. SPIE 9445, Seventh International Conference on Machine Vision (ICMV 2014), 94450I (14 February 2015); doi: 10.1117/12.2180766
Show Author Affiliations
Daniel Luis Cosmo, Univ. Federal do Espírito Santo (Brazil)
Evandro Ottoni Teatini Salles, Univ. Federal do Espírito Santo (Brazil)
Patrick Marques Ciarelli, Univ. Federal do Espírito Santo (Brazil)

Published in SPIE Proceedings Vol. 9445:
Seventh International Conference on Machine Vision (ICMV 2014)
Antanas Verikas; Branislav Vuksanovic; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?