Abstract

This Letter introduces an efficient human detection method in thermal images, using a center-symmetric local binary pattern (CS-LBP) with a luminance saliency map and a random forest (RF) classifier scheme. After detecting a candidate human region, we crop only the head and shoulder region, which has a higher thermal spectrum than the legs or trunk. The CS-LBP feature is then extracted from the luminance saliency map of a hotspot and applied to the RF classifier, which is an ensemble of randomized decision trees. We demonstrate that our detection method is more robust than conventional feature descriptors and classifiers in thermal images.

© 2012 Optical Society of America

Saliency detection using midlevel visual cues

Jin-Gang Yu and Jinwen Tian
Opt. Lett. 37(23) 4994-4996 (2012)

Saliency detection via textural contrast

Wonjun Kim and Changick Kim
Opt. Lett. 37(9) 1550-1552 (2012)

Saliency detection using regional histograms

Zhi Liu, Olivier Le Meur, Shuhua Luo, and Liquan Shen
Opt. Lett. 38(5) 700-702 (2013)

Saliency detection based on biological plausibility of hypercomplex Fourier spectrum contrast

Ce Li, Jianru Xue, Zhiqiang Tian, Lu Li, and Nanning Zheng
Opt. Lett. 37(17) 3609-3611 (2012)

Saliency model for object detection: searching for novel items in the scene

Zhenzhu Zheng, Tianxu Zhang, and Luxin Yan
Opt. Lett. 37(9) 1580-1582 (2012)