Three-level cascade of random forests for rapid human detection

Byoung Chul Ko; Deok-Yeon Kim; Ji-Hoon Jung; Jae-Yeal Nam

doi:10.1117/1.OE.52.2.027204

4 February 2013 Three-level cascade of random forests for rapid human detection

Byoung Chul Ko, Deok-Yeon Kim, Ji-Hoon Jung, Jae-Yeal Nam

Author Affiliations +

Optical Engineering, Vol. 52, Issue 2, 027204 (February 2013). https://doi.org/10.1117/1.OE.52.2.027204

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.

CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Citation Download Citation

Byoung Chul Ko, Deok-Yeon Kim, Ji-Hoon Jung, and Jae-Yeal Nam "Three-level cascade of random forests for rapid human detection," Optical Engineering 52(2), 027204 (4 February 2013). https://doi.org/10.1117/1.OE.52.2.027204

Published: 4 February 2013

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 21 scholarly publications.

Explore citations on Lens.org

KEYWORDS

Rutherfordium

Volume rendering

Wavelets

Detection and tracking algorithms

Binary data

Feature extraction

Optical engineering

Show All Keywords

RELATED CONTENT

Employing wavelet-based texture features in ammunition classification
Proceedings of SPIE (May 05 2017)

Change detection in high resolution SAR images based on multiscale...
Proceedings of SPIE (November 23 2011)

Ripplet-II transform for feature extraction
Proceedings of SPIE (August 04 2010)

Object recognition based on spatial active basis template
Proceedings of SPIE (December 02 2011)

Inspection of surface-mount device images using wavelet processing
Proceedings of SPIE (February 26 1997)

CW-SSIM kernel based random forest for image classification
Proceedings of SPIE (August 04 2010)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years