摘要
针对传统步态识别算法因服饰携带物变换、视角等协变量因素变化导致的识别能力下降问题,提出了一种基于改进深度卷积神经网络的步态识别算法。该算法利用分层处理机制从步态数据中提取步态特征,能够降低常见变化和遮挡等情况对识别精度的影响,同时,算法根据实验确定了网络中每层特征图的最佳数量、特征图的最佳尺寸以及要用于步态识别的输入特征的类型,能够处理相对较小的数据集而无需使用任何增强或微调技术。CASIA-B步态数据库仿真实验表明,所提出的卷积神经网络覆盖了交叉视图步态识别和无主题的步态识别问题,能够克服与步态识别相关的协变量因素问题,具有更优的步态识别精度。
Aiming at the problem of traditional gait recognition algorithm due to the change of clothing and the change of covariate factors such as perspective, this paper proposes a gait recognition algorithm based on improved deep convolutional neural network. The algorithm uses the layered processing mechanism to extract the gait features from the gait data, which can reduce the impact of common changes and occlusion on the recognition accuracy. At the same time, the algorithm determines the optimal number of features of each layer in the network according to experiments. The optimal size of the graph and the type of input features to be used for gait recognition can handle relatively small data sets without any enhancement or fine-tuning. CASIA-B gait database simulation experiments show that CNN proposed in this paper covering the gait recognition problem of cross view gait recognition and no subject, it can overcome the covariate factor problem related to gait recognition, and has better gait recognition accuracy.
引文
[1] SZEGEDY C, LIU W, JIA Y, et al.Going deeper with convolutions[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015,2(11):1-9.
[2] KARPATHY A, TODERICI G, SHETTY S, et al. Largescale video classification with convolutional neural networks[C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2015,3(9): 1725-1732.
[3] ALOTAIBI M, MAHMOOD A. Improved gait recognition based on specialized deep convolutional neural networks[J]. IEEE Applied Imagery Pattern Recognition Workshop, 2015,10(6):1-7.
[4] LIU Z, SARKAR S. Simplest representation yet for gait recognition: Averaged silhouette[J]. Pattern Recognition, 2004,23(6):211-214.
[5] HAN J, BHANU B. Individual recognition using gait energy image[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28 (2): 316-322.
[6] BASHIR K, XIANG T, GONG S. Feature selection for gait recognition without subject cooperation[C]. British Machine Vision Conference, 2006,11(6):1-10.
[7] IWAMA H, OKUMURA M, MAKIHARA Y. The ouisir gait database comprising the large population dataset and performance evaluation of gait recognition[J]. IEEE Transactions on Information Forensics and Security, 2012, 7 (5):1511-1521.
[8] XU D, YAN S, TAO D. Human gait recognition with matrix representation [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2006,16 (7):896-903.
[9] YAN S, XU D, YANG Q. Discriminant analysis with tensor representation[J].Computer Vision and Pattern Recognition, 2005,16(7):526-532.
[10] XU D, YAN S, ZHANG L. Reconstruction and recognition of tensor-based objects with concurrent subspaces analysis[J]. IEEE Transactions on Circuits and Systems for Video Technology,2008,18 (1):36-47.
[11] TAO D, LI X, WU X. General tensor discriminant analysis and Gabor features for gait recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29 (10):1700-1715.
[12] HUANG Y, XU D, CHAM T J. Face and human gait recognition using image-toclass distance[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010,20 (3): 431-438.
[13] HU M, WANG Y, ZHANG Z. View-invariant discriminative projection for multi-view gait-based human identification [J]. IEEE Transactions on Information Forensics and Security, 2013,8 (12):2034- 2045.
[14] WU Z, HUANG Y, WANG L. A comprehensive study on crossview gait based human identification with deep cnns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39 (2):209-226.
[15] DUPUIS Y, SAVATIER X, VASSEUR P. Feature subset selection applied to model-free gait recognition[J]. Computer Vision and Image Understanding, 2013,31 (8):580-591.