A Pedestrian Detection Method Based on Hierarchical Tree Cascade Classification at NighttimeSource: Journal of Highway and Transportation Research and Development (English Edition):;2015:;Volume ( 009 ):;issue: 002DOI: 10.1061/JHTRCQ.0000444Publisher: American Society of Civil Engineers
Abstract: Illumination, for pedestrian detection at nighttime is weak, and detection is easily affected through variations in illumination. Thus, a bicharacteristic method of pedestrian detection at nighttime based on hierarchical tree cascade classification is presented according to “coarse-to-fine” principle. The proposed method consists of two stages of cascade classifiers. Coarse cascade classifiers are constructed in complete binary tree architecture. These classifiers use Haar-like features for the rapid identification of candidate pedestrian areas. By contrast, fine cascade classifiers have a parallel structure. Edgelet features are used for detection along three parts: the head-shoulder, trunk, and leg parts of candidate pedestrian areas. Bayesian decision-making is adopted to achieve pedestrian target detection and a comprehensive analysis of the detection results from these three parts. Experiments show that the proposed method has high accuracy, ideal real-time performance, and strong reliability. Research works, such as the present study, can serve as reference for vehicle safety driving technology.
|
Show full item record
contributor author | Zhang Rong-hui | |
contributor author | Zhou Jia-li | |
contributor author | You Feng | |
contributor author | Zhou Xi | |
contributor author | Pei Yu-long | |
date accessioned | 2017-05-08T22:33:46Z | |
date available | 2017-05-08T22:33:46Z | |
date copyright | June 2015 | |
date issued | 2015 | |
identifier other | 49745065.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl/handle/yetl/82674 | |
description abstract | Illumination, for pedestrian detection at nighttime is weak, and detection is easily affected through variations in illumination. Thus, a bicharacteristic method of pedestrian detection at nighttime based on hierarchical tree cascade classification is presented according to “coarse-to-fine” principle. The proposed method consists of two stages of cascade classifiers. Coarse cascade classifiers are constructed in complete binary tree architecture. These classifiers use Haar-like features for the rapid identification of candidate pedestrian areas. By contrast, fine cascade classifiers have a parallel structure. Edgelet features are used for detection along three parts: the head-shoulder, trunk, and leg parts of candidate pedestrian areas. Bayesian decision-making is adopted to achieve pedestrian target detection and a comprehensive analysis of the detection results from these three parts. Experiments show that the proposed method has high accuracy, ideal real-time performance, and strong reliability. Research works, such as the present study, can serve as reference for vehicle safety driving technology. | |
publisher | American Society of Civil Engineers | |
title | A Pedestrian Detection Method Based on Hierarchical Tree Cascade Classification at Nighttime | |
type | Journal Paper | |
journal volume | 9 | |
journal issue | 2 | |
journal title | Journal of Highway and Transportation Research and Development (English Edition) | |
identifier doi | 10.1061/JHTRCQ.0000444 | |
tree | Journal of Highway and Transportation Research and Development (English Edition):;2015:;Volume ( 009 ):;issue: 002 | |
contenttype | Fulltext |