Multi-label convolutional neural network based pedestrian attribute classification

Recently, pedestrian attributes like gender, age, clothing etc., have been used as soft biometric traits for recognizing people. Unlike existing methods that assume the independence of attributes during their prediction, we propose a multi-label convolutional neural network (MLCNN) to predict multiple attributes together in a unified framework. Firstly, a pedestrian image is roughly divided into multiple overlapping body parts, which are simultaneously integrated in the multi-label convolutional neural network. Secondly, these parts are filtered independently and aggregated in the cost layer. The cost function is a combination of multiple binary attribute classification cost functions. Experiments show that the proposed method significantly outperforms the SVM based method on the PETA database. Multi-label convolutional neural network for pedestrian attribute classification.The proposed MLCNN can simultaneously predict multiple pedestrian attributes.Experiments on the PETA database have shown the superiority of the proposed MLCNN.

[1]  J. Koenderink.  Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[2]  Xiaojing Chen,et al.  Improving person re-identification by soft biometrics based reranking , 2013, 2013 Seventh International Conference on Distributed Smart Cameras (ICDSC).

[3]  Huizhong Chen,et al.  Describing Clothing by Semantic Attributes , 2012, ECCV.

[4]  Chunxiao Liu,et al.  Person Re-identification: What Features Are Important? , 2012, ECCV Workshops.

[5]  Subhransu Maji,et al.  Describing people: A poselet-based approach to attribute classification , 2011, 2011 International Conference on Computer Vision.

[6]  Cordelia Schmid,et al.  TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Shuicheng Yan,et al.  Clothing Attributes Assisted Person Reidentification , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Shaogang Gong,et al.  Person Re-identification by Attributes , 2012, BMVC.

[9]  Mark S. Nixon,et al.  Soft biometrics for subject identification using clothing attributes , 2014, IEEE International Joint Conference on Biometrics.

[10]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[11]  Shengcai Liao,et al.  Multi-label CNN based pedestrian attribute learning for soft biometrics , 2015, 2015 International Conference on Biometrics (ICB).

[12]  Xiaoou Tang,et al.  Pedestrian Attribute Recognition At Far Distance , 2014, ACM Multimedia.

[13]  Shengcai Liao,et al.  Improve Pedestrian Attribute Classification by Weighted Interactions from Other Attributes , 2014, ACCV Workshops.

[14]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[15]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

[16]  Mark S. Nixon,et al.  Analysing Soft Clothing Biometrics for Retrieval , 2014, BIOMET.

[18]  Shengcai Liao,et al.  Pedestrian Attribute Classification in Surveillance: Database and Evaluation , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[19]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[20]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[21]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[22]  Jean-Luc Dugelay,et al.  Soft biometrics systems: Reliability and asymptotic bounds , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[23]  Mark S. Nixon,et al.  Soft Biometrics; Human Identification Using Comparative Descriptions , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[25]  Horst Bischof,et al.  Person Re-identification by Descriptive and Discriminative Classification , 2011, SCIA.

[26]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[27]  Shaogang Gong,et al.  Attributes-Based Re-identification , 2014, Person Re-Identification.

[28]  Jean-Luc Dugelay,et al.  Search pruning in video surveillance systems: Efficiency-reliability tradeoff , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[29]  Graham W. Taylor,et al.  TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2018 .

[30]  Marc'Aurelio Ranzato,et al.  Large Scale Distributed Deep Networks , 2012, NIPS.

[31]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.

[32]  Subhransu Maji,et al.  Classification using intersection kernel support vector machines is efficient , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Jean-Luc Dugelay,et al.  Person recognition using a bag of facial soft biometrics (BoFSB) , 2010, 2010 IEEE International Workshop on Multimedia Signal Processing.

[34]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[35]  Shree K. Nayar,et al.  Attribute and simile classifiers for face verification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[36]  Shaogang Gong,et al.  Re-id: Hunting Attributes in the Wild , 2014, BMVC.

[37]  Anil K. Jain,et al.  Soft Biometric Traits for Personal Recognition Systems , 2004, ICBA.

[38]  J. Gregory Trafton,et al.  Identifying people with soft-biometrics at Fleet Week , 2013, 2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI).