Pose-based Deep Gait Recognition

Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this paper, we present a new pose-based convolutional neural network model for gait recognition. Unlike many methods that consider the full-height silhouette of a moving person, we consider the motion of points in the areas around human joints. To extract motion information, we estimate the optical flow between consecutive frames. We propose a deep convolutional model that computes pose-based gait descriptors. We compare different network architectures and aggregation methods and experimentally assess various sets of body parts to determine which are the most important for gait recognition. In addition, we investigate the generalization ability of the developed algorithms by transferring them between datasets. The results of these experiments show that our approach outperforms state-of-the-art methods.

[1]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[2]  Rafael Medina Carnicer,et al.  Pyramidal Fisher Motion for Multiview Gait Recognition , 2014, 2014 22nd International Conference on Pattern Recognition.

[3]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[4]  A. Sokolova,et al.  GAIT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS , 2017 .

[5]  Xiaogang Wang,et al.  A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Shaogang Gong,et al.  Gait recognition using Gait Entropy Image , 2009, ICDP.

[7]  Tieniu Tan,et al.  A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[8]  Chen Wang,et al.  Multiple HOG templates for gait recognition , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[9]  Björn W. Schuller,et al.  The TUM Gait from Audio, Image and Depth (GAID) database: Multimodal recognition of subjects and traits , 2014, J. Vis. Commun. Image Represent..

[10]  Andrew Zisserman,et al.  Convolutional Two-Stream Network Fusion for Video Action Recognition , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Chao Li,et al.  DeepGait: A Learning Deep Convolutional Representation for Gait Recognition , 2017, CCBR.

[12]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[13]  Cordelia Schmid,et al.  Long-Term Temporal Convolutions for Action Recognition , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Yasushi Makihara,et al.  View Transformation Model Incorporating Quality Measures for Cross-View Gait Recognition , 2016, IEEE Transactions on Cybernetics.

[15]  Yasushi Makihara,et al.  Effective part-based gait identification using frequency-domain gait entropy features , 2015, Multimedia Tools and Applications.

[16]  Chao Li,et al.  Cross-view gait recognition using joint Bayesian , 2017, International Conference on Digital Image Processing.

[17]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[18]  Manuel J. Marín-Jiménez,et al.  Automatic Learning of Gait Signatures for People Identification , 2016, IWANN.

[19]  Yasushi Makihara,et al.  GEINet: View-invariant gait recognition using a convolutional neural network , 2016, 2016 International Conference on Biometrics (ICB).

[20]  Yasushi Makihara,et al.  The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition , 2012, IEEE Transactions on Information Forensics and Security.

[21]  Matthew J. Hausknecht,et al.  Beyond short snippets: Deep networks for video classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Cordelia Schmid,et al.  P-CNN: Pose-Based CNN Features for Action Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Jiansheng Liu,et al.  Average Gait Differential Image Based Human Recognition , 2014, TheScientificWorldJournal.

[24]  Chao Li,et al.  DeepGait: A Learning Deep Convolutional Representation for View-Invariant Gait Recognition Using Joint Bayesian , 2017 .

[25]  Xiang Li,et al.  Joint Intensity and Spatial Metric Learning for Robust Gait Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Yasushi Makihara,et al.  Cross-view gait recognition using view-dependent discriminative analysis , 2014, IEEE International Joint Conference on Biometrics.

[28]  Georgios Tzimiropoulos,et al.  Human Pose Estimation via Convolutional Part Heatmap Regression , 2016, ECCV.

[29]  Yasushi Makihara,et al.  Cross-view gait recognition by fusion of multiple transformation consistency measures , 2015, IET Biom..

[30]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[31]  Yasushi Makihara,et al.  Gait Recognition Using a View Transformation Model in the Frequency Domain , 2006, ECCV.