Share Email Print

Optical Engineering • Open Access

Three-level cascade of random forests for rapid human detection
Author(s): Byoung Chul Ko; Deok-Yeon Kim; Ji-Hoon Jung; Jae-Yeal Nam

Paper Abstract

We propose a novel human detection approach that combines three types of center symmetric local binary patterns (CS-LBP) descriptors with a cascade of random forests (RFs). To detect human regions in a low-dimensional feature space, we first extract three types of CS-LBP features from the scanning window of a downsampled saliency texture map and two wavelet-transformed subimages. The extracted CS-LBP descriptors are applied to a three-level cascade of RFs, which combines a series of RF classifiers as a filter chain. The three-level cascade of RFs with CS-LBPs delivers rapid human detection with higher detection accuracy, as compared with combinations of other features and classifiers. The proposed algorithm is successfully applied to various human and nonhuman images from the INRIA dataset, and it performs better than other related algorithms.

Paper Details

Date Published: 4 February 2013
PDF: 10 pages
Opt. Eng. 52(2) 027204 doi: 10.1117/1.OE.52.2.027204
Published in: Optical Engineering Volume 52, Issue 2
Show Author Affiliations
Byoung Chul Ko, Keimyung Univ. (Korea, Republic of)
Deok-Yeon Kim, Keimyung Univ. (Korea, Republic of)
Ji-Hoon Jung, Keimyung Univ. (Korea, Republic of)
Jae-Yeal Nam, Keimyung Univ. (Korea, Republic of)

© SPIE. Terms of Use
Back to Top