Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier

Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier
复制标题

多小波变换和多层感知器分类器的驾驶姿势识别

DOI:
10.1016/j.engappai.2012.09.018
复制
发表时间:
2012-12
影响因子:
8
通讯作者:
何杰
何杰
中科院分区:
计算机科学2区
文献类型:
--
作者:
赵池航;高永胜;何杰

文献摘要

参考文献

被引文献

相似文献

为了开发以人为中心的驾驶员辅助系统(HDAS)来自动理解和表征驾驶员行为,提出了一种基于 Geronimo-Hardin-Massopust(GHM)多小波变换的驾驶姿势的有效特征提取,然后利用三层多层感知器(MLP)分类器来识别四种预定义的驾驶姿势类别。利用东南大学(SEU)创建的驾驶姿势数据集提取的特征,通过MLP分类器进行驾驶姿势分类的保留和交叉验证实验,与交叉核支持向量机(IKSVM)、k近邻(kNN)分类器和Parzen分类器进行比较。实验结果表明,基于GHM多小波变换和MLP分类器的特征提取,在输出层使用softmax激活函数,在隐藏层使用双曲正切激活函数,与IKSVM、kNN和Parzen分类器相比,提供了最佳的分类性能。实验结果还表明,在四个预定义类别中,用手机通话是最难分类的类别,在保留实验和交叉验证实验中分别为 83.01% 和 84.04%。这些结果表明,使用 GHM 多小波变换和 MLP 分类器的特征提取方法在自动理解和表征以人为中心的驾驶员辅助系统 (HDAS) 的驾驶员行为方面的有效性。
To develop Human-centric Driver Assistance Systems (HDAS) for automatic understanding and charactering of driver behaviors, an efficient feature extraction of driving postures based on Geronimo–Hardin–Massopust (GHM) multiwavelet transform is proposed, and Multilayer Perceptron (MLP) classifiers with three layers are then exploited in order to recognize four pre-defined classes of driving postures. With features extracted from a driving posture dataset created at Southeast University (SEU), the holdout and cross-validation experiments on driving posture classification are conducted by MLP classifiers, compared with the Intersection Kernel Support Vector Machines (IKSVMs), the k-Nearest Neighbor (kNN) classifier and the Parzen classifier. The experimental results show that feature extraction based on GHM multwavelet transform and MLP classifier, using softmax activation function in the output layer and hyperbolic tangent activation function in the hidden layer, offer the best classification performance compared to IKSVMs, kNN and Parzen classifiers. The experimental results also show that talking on a cellular phone is the most difficult one to classify among four predefined classes, which are 83.01% and 84.04% in the holdout and cross-validation experiments respectively. These results show the effectiveness of the feature extraction approach using GHM multiwavelet transform and MLP classifier in automatically understanding and characterizing driver behaviors towards Human-centric Driver Assistance Systems (HDAS).
DOI: 10.1109/cvpr.2008.4587630
发表时间: 2008-06
期刊: 2008 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Subhransu Maji;A. Berg;Jitendra Malik
通讯作者: Subhransu Maji;A. Berg;Jitendra Malik
DOI: --
发表时间: 1998
期刊: --
影响因子: --
作者:
J. Platt
通讯作者: J. Platt
DOI: 10.1109/ivs.2007.4290191
发表时间: 2007-06
期刊: 2007 IEEE Intelligent Vehicles Symposium
影响因子: --
作者:
H. Eren;Ümit Çelik;M. Poyraz
通讯作者: H. Eren;Ümit Çelik;M. Poyraz
DOI: 10.1109/iccv.1998.710728
发表时间: 1998-01
期刊: Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)
影响因子: --
作者:
Gilles Simon;M. Berger
通讯作者: Gilles Simon;M. Berger
DOI: 10.1109/itsc.2005.1520169
发表时间: 2005-10
期刊: Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.
影响因子: --
作者:
H. Veeraraghavan;Stefan Atev;Nathaniel D. Bird;P. Schrater;N. Papanikolopoulos
通讯作者: H. Veeraraghavan;Stefan Atev;Nathaniel D. Bird;P. Schrater;N. Papanikolopoulos