Pedestrian detection for traffic safety based on Accumulate Binary Haar features and improved deep belief network algorithm

被引:5
作者
Zhang, Yang [1 ]
Xin, Dong-Rong [1 ]
Wu, Yi-Hu [2 ]
机构
[1] Fujian Univ Technol, Sch Transportat, Fuzhou, Fujian Province, Peoples R China
[2] Changsha Univ Sci & Technol, Sch Traff & Transportat Engn, Changsha, Hunan, Peoples R China
关键词
Traffic safety; pedestrian protection; deep belief network; ABH; RBM; T distribution; SVM; experiments;
D O I
10.1080/03081060.2016.1231898
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
In order to improve traffic safety and protect pedestrians, an improved and efficient pedestrian detection method for auto driver assistance systems is proposed. Firstly, an improved Accumulate Binary Haar (ABH) feature extraction algorithm is proposed. In this novel feature, Haar features keep only the ordinal relationship named by binary Haar features. Then, the feature brings in the idea of a Local Binary Pattern (LBP), assembling several neighboring binary Haar features to improve discriminating power and reduce the effect of illumination. Next, a pedestrian classification method based on an improved deep belief network (DBN) classification algorithm is proposed. An improved method of input is constructed using a Restricted Bolzmann Machine (RBM) with T distribution function visible layer nodes, which can convert information on pedestrian features to a Bernoulli distribution, and the Bernoulli distribution can then be used for recognition. In addition, a middle layer of the RBM structure is created, which achieves data transfer between the hidden layer structure and keeps the key information. Finally, the cost-sensitive Support Vector Machine (SVM) classifier is used for the output of the classifier, which could address the class-imbalance problem. Extensive experiments show that the improved DBN pedestrian detection method is better than other shallow classic algorithms, and the proposed method is effective and sufficiently feasible for pedestrian detection in complex urban environments.
引用
收藏
页码:791 / 800
页数:10
相关论文
共 16 条
[1]   Transfer learning for pedestrian detection [J].
Cao, Xianbin ;
Wang, Zhong ;
Yan, Pingkun ;
Li, Xuelong .
NEUROCOMPUTING, 2013, 100 :51-57
[2]  
[程如中 Cheng Ruzhong], 2012, [交通运输工程学报, Journal of Traffic and Transportation Engineering], V12, P110
[3]  
[种衍文 Chong Yanwen], 2012, [自动化学报, Acta Automatica Sinica], V38, P375
[4]   Monocular Pedestrian Detection: Survey and Experiments [J].
Enzweiler, Markus ;
Gavrila, Dariu M. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (12) :2179-2195
[5]  
Fu Zhong-Liang, 2011, Acta Automatica Sinica, V37, P973, DOI 10.3724/SP.J.1004.2011.00973
[6]  
Guo Lie, 2005, J HIGHWAY TRANSPORTA, V22, P137
[7]   AdaBoost with SVM-based component classifiers [J].
Li, Xuchun ;
Wang, Lei ;
Sung, Eric .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2008, 21 (05) :785-795
[8]   Discriminative deep belief networks for visual data classification [J].
Liu, Yan ;
Zhou, Shusen ;
Chen, Qingcai .
PATTERN RECOGNITION, 2011, 44 (10-11) :2287-2296
[9]   Local binary patterns for multi-view facial expression recognition [J].
Moore, S. ;
Bowden, R. .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2011, 115 (04) :541-558
[10]   Linguistic cost-sensitive learning of Genetic Fuzzy Classifiers for imprecise data [J].
Palacios, Ana M. ;
Sanchez, Luciano ;
Couso, Ines .
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2011, 52 (06) :841-862