Abstract In most existing gait recognition methods based on deep learning, global features are acquired by stacking convolutional layers, and local features beneficial to fine-grained classification are ignored. Aiming at this problem, a cross-view gait recognition method is proposed by combining non-local and part-level features. A pair of gait energy images(GEIs) is used as input to extract the non-local information of a single sample and the relative non-local information of the sample pairs. Then, human body regions are divided horizontally into static blocks, micro-dynamic blocks and strong dynamic blocks to extract better local features according to the geometric characteristics of GEI. Furthermore, the segmented regions are connected to three binary classifiers for training respectively. Finally, experiments on OU-ISIR-LP and CASIA-B gait datasets show that the proposed method produces a higher correct recognition rate.
Fund:Supported by National Natural Science Foundation of China (No.61602431,61303146)
Corresponding Authors:
WANG Xiuhui, Ph.D., associate professor. His research interests include pattern recognition, computer vision and computer graphics.
About author:: FENG Shiling, master student. His research interests include computer vision and pattern recognition.
[1] HAN J, BHANN B. Individual Recognition Using Gait Energy Image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(2): 316-322. [2] 何逸炜,张军平.步态识别的深度学习:综述.模式识别与人工智能, 2018, 31(5): 442-451. (HE Y W, ZHANG J P. Deep Learning for Gait Recognition: A Survey. Pattern Recognition and Artificial Intelligence, 2018, 31(5): 442-451.) [3] KUSAKUNNIRAN W, WU Q, LI H D, et al. Multiple Views Gait Recognition Using View Transformation Model Based on Optimized Gait Energy Image // Proc of the 12th IEEE International Confe-rence on Computer Vision Workshops. Washington, USA: IEEE, 2009: 1058-1064. [4] MURAMATSU D, MAKIHARA Y, YAGI Y. Cross-View Gait Re-cognition by Fusion of Multiple Transformation Consistency Measures // Proc of the 2nd International Workshop on Biometrics and Forensics. Washington, USA: IEEE, 2014. DOI: 10.1109/IWBF.2014.6914253. [5] MURAMATSU D, MAKIHARA Y,YAGI Y. View Transformation Model Incorporating Quality Measures for Cross-View Gait Recognition. IEEE Transactions on Cybernetics, 2016, 46(7): 1602-1615. [6] 王科俊,阎 涛,吕卓纹,等.核稀疏保留投影及在步态识别中的应用.中国图象图形学报, 2013, 18(3): 257-263. (WANG K J, YAN T, LÜ Z W, et al. Kernel Sparsity Preserving Projections and Its Application to Gait Recognition. Journal of Image and Graphics, 2013, 18(3): 257-263.) [7] WANG X H, WANG J, YAN K. Gait Recognition Based on Gabor Wavelets and (2D)2PCA. Multimedia Tools and Applications, 2018, 77(10): 12545-12561. [8] 王修晖,严 珂.基于连续密度隐马尔可夫模型的人体步态识别.模式识别与人工智能, 2016, 29(8): 709-716. (WANG X H, YAN K. Human Gait Recognition Using Continuous Density Hidden Markov Models. Pattern Recognition and Artificial Intelligence, 2016, 29(8): 709-716.) [9] BEN X Y, ZHANG P, LAI Z H, et al. A General Tensor Representation Framework for Cross-View Gait Recognition. Pattern Recognition, 2019, 90: 87-98. [10] WOLF T, BABAEE M, RIGOLL G. Multi-view Gait Recognition Using 3D Convolutional Neural Networks // Proc of the IEEE International Conference on Image Processing. Washington, USA: IEEE, 2016: 4165-4169. [11] LAM T H W, CHEUNG K H, LIU J N K. Gait Flow Image: A Silhouette-Based Gait Representation for Human Identification. Pa-ttern Recognition, 2011, 44(4): 973-987. [12] TONG S B, FU Y Z, YUE X W, et al. Multi-view Gait Recognition Based on a Spatial-Temporal Deep Neural Network. IEEE Access, 2018, 6: 57583-57596. [13] CHEN Q, WANG Y H, LIU Z, et al. Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images[C/OL]. [2019-02-22]. https://arxiv.org/pdf/1711.09358.pdf. [14] WU H M, WENG J, CHEN X, et al. Feedback Weight Convolutional Neural Network for Gait Recognition. Journal of Visual Communication and Image Representation, 2018, 55: 424-432. [15] SHIRAGA K, MAKIHARA Y, MURAMATSU D, et al. GEINet: View-Invariant Gait Recognition Using a Convolutional Neural Network // Proc of the International Conference on Biometrics. Wa-shington, USA: IEEE, 2016. DOI: 10.1109/ICB.2016.7550060. [16] WU Z F, HUANG Y Z, WANG L, et al. A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(2): 209-226. [17] KRIZHEVSKY A, SUTSKEVER J, HINTON G. ImageNet Classification with Deep Convolutional Neural Networks // Proc of the 25th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2012, I: 1097-1105. [18] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016, I: 770-778. [19] WANG X H, YAN W Q. Cross-View Gait Recognition through Ensemble Learning // Proc of the Thematic Workshops of ACM Multimedia. New York, USA: ACM, 2017: 385-392. [20] IWAMA H, OKUMURA M, MAKIHARA Y, et al. The OU-ISIR Gait Database Comprising the Large Population Dataset and Performance Evaluation of Gait Recognition. IEEE Transactions on Information Forensics and Security, 2012, 7(5): 1511-1521. [21] TAKEMURA N, MAKIHARA Y, MURAMATSU D, et al. Multi-view Large Population Gait Dataset and Its Performance Evaluation for Cross-View Gait Recognition[C/OL]. [2019-02-22]. https://link.springer.com/content/pdf/10.1186%2Fs41074-018-0039-6.pdf. [22] YU S Q, TAN D L, TAN T N. A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition // Proc of the 18th International Conference on Pattern Recognition. Washington, USA: IEEE, 2006, IV: 441-444.
2019, Vol. 32 
