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

ABSTRACT 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.

[1]  Yu Tian-hong.  Overview of Worldwide Intelligent Vehicle Pedestrian Detection Technology , 2005 .

[2]  Yang Zhang,et al.  A novel pedestrian detection method based on Cost-Sensitive Support Vector Machine and Chaotic Particle Swarm Optimization with T mutation , 2012 .

[3]  J. Szymański,et al.  Well-distributed SIFT features , 2009 .

[4]  Hu-Lin Kuang,et al.  Two-stage Pedestrian Detection Based on Multiple Features and Machine Learning: Two-stage Pedestrian Detection Based on Multiple Features and Machine Learning , 2012 .

[5]  Xuelong Li,et al.  Transfer learning for pedestrian detection , 2013, Neurocomputing.

[6]  Fu Zhong.  Cost-sensitive AdaBoost Algorithm for Multi-class Classification Problems , 2011 .

[7]  Lei Wang,et al.  AdaBoost with SVM-based component classifiers , 2008, Eng. Appl. Artif. Intell..

[8]  Richard Bowden,et al.  Local binary patterns for multi-view facial expression recognition , 2011 .

[9]  Inés Couso,et al.  Linguistic cost-sensitive learning of genetic fuzzy classifiers for imprecise data , 2011, Int. J. Approx. Reason..

[10]  Wang Xin-an.  Real-time pedestrian detecting and warning system , 2012 .

[11]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Hong Qiao,et al.  An Efficient Tree Classifier Ensemble-Based Approach for Pedestrian Detection , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Chong Yan.  Two-stage Pedestrian Detection Based on Multiple Features and Machine Learning , 2012 .

[14]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[16]  Dariu Gavrila,et al.  Monocular Pedestrian Detection: Survey and Experiments , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Yan Liu,et al.  Discriminative deep belief networks for visual data classification , 2011, Pattern Recognit..

[18]  Yu Tian-hong.  Review on the Research of Intelligent Vehicle Safety Driving Assistant Technology , 2007 .

[19]  Sheng Yang,et al.  A Pedestrian Detection Method Based on the HOG-LBP Feature and Gentle AdaBoost , 2012 .