浏览全部资源
扫码关注微信
1.痕迹检验鉴定技术公安部重点实验室(中国刑事警察学院),辽宁 沈阳 110035
2.中国科学院 沈阳自动化研究所,辽宁 沈阳 110016
[ "高 毅(1978-),男,硕士,副教授,2006年于长春理工大学获得硕士学位,主要从事足迹检验,步态识别相关研究。E-mail:396406005@qq.com" ]
[ "何 淼(1992-),男,博士,助理研究员,2015年于南开大学获得学士学位,2021年于中国科学院沈阳自动化研究所获工学博士学位,主要从事图像处理、深度学习、目标检测、目标跟踪等方面的研究。Email: hemiao@sia.cn" ]
收稿日期:2022-09-11,
修回日期:2022-09-19,
纸质出版日期:2023-01-25
移动端阅览
高毅,何淼.密集遮挡条件下的步态识别[J].光学精密工程,2023,31(02):263-276.
GAO Yi,HE Miao.Gait recognition algorithm in dense occlusion scene[J].Optics and Precision Engineering,2023,31(02):263-276.
高毅,何淼.密集遮挡条件下的步态识别[J].光学精密工程,2023,31(02):263-276. DOI: 10.37188/OPE.20233102.0263.
GAO Yi,HE Miao.Gait recognition algorithm in dense occlusion scene[J].Optics and Precision Engineering,2023,31(02):263-276. DOI: 10.37188/OPE.20233102.0263.
步态识别算法主要依赖行人目标的时序轮廓进行特征提取和判别。在实际应用中行人具有结伴行走的特点,轮廓提取易受到其他行人的遮挡和干扰,大幅降低了步态识别算法的精度。为提高人员密集遮挡严重的场景下步态识别算法的鲁棒性,提出一种基于无序序列的深度步态识别算法。首先在Casia-B数据集的基础上进行仿真,建立遮挡情况下的目标轮廓仿真数据集,用于对算法进行遮挡鲁棒性验证;其次,提出基于随机二值膨胀的数据增广方法,同时通过理论和实验论证了HPP(Horizontal Pyramid Pooling)结构在步态识别问题中的局限性,提出退化水平金字塔结构DHPP,利用DHPP结构、CoordConv方法和联合训练裁剪方法的配合,在深度特征中增强绝对位置信息的感知能力,提升算法遮挡鲁棒性的同时减少目标特征表达维度。实验结果表明,所提方法对于步态识别的鲁棒性提升效果明显。
Gait recognition algorithms mainly rely on the contour sequence of pedestrian targets for feature extraction and recognition. In practical applications, pedestrians walk together, and the contour is easily occluded and interfered by other pedestrians, which significantly reduces the accuracy of gait recognition algorithm. To improve the robustness of gait recognition algorithm in dense occlusion scene, a deep-learning gait recognition algorithm based on unordered contour sequences is proposed. First, a simulation is conducted based on the Casia-B dataset, and the target contour simulation dataset for dense occlusion scene is established to verify the occlusion robustness of the algorithm. Second, a data augmentation method based on random binary expansion is proposed. However, owing to the limitations of horizontal pyramid pooling (HPP) structure in the area of gait recognition demonstrated through theory and experiment, a degenerated horizontal pyramid pooling (DHPP) structure is proposed. By combining the DHPP structure, CoordConv method, joint training, and pruning method, the perception ability of absolute position information in deep-learning features can be enhanced and the robustness of the algorithm for occlusion scene can be improved. In addition, the feature expression dimension of the target is reduced. The experimental results indicate that the proposed method is effective in improving the robustness of gait recognition algorithm.
DENG J K , GUO J , XUE N N , et al . ArcFace: additive angular margin loss for deep face recognition [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1520,2019 , Long Beach, CA, USA. IEEE , 2020 : 4685 - 4694 . doi: 10.1109/cvpr.2019.00482 http://dx.doi.org/10.1109/cvpr.2019.00482
YE M , SHEN J B , LIN G J , et al . Deep learning for person re-identification: a survey and outlook [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 6 ): 2872 - 2893 . doi: 10.1109/tpami.2021.3054775 http://dx.doi.org/10.1109/tpami.2021.3054775
高毅 . 基于步态识别的跨场景多目标跟踪算法 [J]. 控制工程 , 2021 , 28 ( 7 ): 1375 - 1381 .
GAO Y . Multi-camera multi-target tracking algorithm based on gait recognition [J]. Control Engineering of China , 2021 , 28 ( 7 ): 1375 - 1381 . (in Chinese)
ZHENG J K , LIU X C , LIU W , et al . Gait recognition in the wild with dense 3D representations and A benchmark [C]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 1824,2022 , New Orleans, LA, USA. IEEE , 2022 : 20196 - 20205 . doi: 10.1109/cvpr52688.2022.01959 http://dx.doi.org/10.1109/cvpr52688.2022.01959
SUN Y , BAO Q , LIU W , et al . Monocular, one-stage, regression of multiple 3D people [C]. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 1017,2021 , Montreal, QC, Canada. IEEE , 2022 : 11159 - 11168 . doi: 10.1109/iccv48922.2021.01099 http://dx.doi.org/10.1109/iccv48922.2021.01099
CHEN X , WENG J , LU W , et al . Multi-gait recognition based on attribute discovery [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 7 ): 1697 - 1710 . doi: 10.1109/tpami.2017.2726061 http://dx.doi.org/10.1109/tpami.2017.2726061
WU Z F , HUANG Y Z , WANG L , et al . A comprehensive study on cross-view gait based human identification with deep CNNs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 2 ): 209 - 226 . doi: 10.1109/tpami.2016.2545669 http://dx.doi.org/10.1109/tpami.2016.2545669
HE Y W , ZHANG J P , SHAN H M , et al . Multi-task GANs for view-specific feature learning in gait recognition [J]. IEEE Transactions on Information Forensics and Security , 2019 , 14 ( 1 ): 102 - 113 . doi: 10.1109/tifs.2018.2844819 http://dx.doi.org/10.1109/tifs.2018.2844819
LIAO R J , CAO C S , GARCIA E B , et al . Pose-based Temporal-spatial Network ( PTSN ) for Gait Recognition with Carrying and Clothing Variations [M]. Biometric Recognition . Cham : Springer International Publishing , 2017 : 474 - 483 . doi: 10.1007/978-3-319-69923-3_51 http://dx.doi.org/10.1007/978-3-319-69923-3_51
WOLF T , BABAEE M , RIGOLL G . Multi-view gait recognition using 3D convolutional neural networks [C]. 2016 IEEE International Conference on Image Processing (ICIP). 2528,2016 , Phoenix, AZ, USA. IEEE , 2016 : 4165 - 4169 . doi: 10.1109/icip.2016.7533144 http://dx.doi.org/10.1109/icip.2016.7533144
WU X H , AN W Z , YU S Q , et al . Spatial-temporal graph attention network for video-based gait recognition [M]. Cham : Springer International Publishing , 2020 . doi: 10.1007/978-3-030-41299-9_22 http://dx.doi.org/10.1007/978-3-030-41299-9_22
CHAO H Q , WANG K , HE Y W , et al . GaitSet: cross-view gait recognition through utilizing gait As a deep set [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 7 ): 3467 - 3478 .
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 [C]. 18th International Conference on Pattern Recognition (ICPR' 06 ). 2024,2006 , Hong Kong, China. IEEE , 2006: 441 - 444 . doi: 10.1109/icpr.2006.67 http://dx.doi.org/10.1109/icpr.2006.67
ZHONG Z , ZHENG L , KANG G L , et al . Random erasing data augmentation [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 7 ): 13001 - 13008 . doi: 10.1609/aaai.v34i07.7000 http://dx.doi.org/10.1609/aaai.v34i07.7000
LIU R , LEHMAN J , MOLINO P , et al . An intriguing failing of convolutional neural networks and the CoordConv solution [C]. Proceedings of the 32nd International Conference on Neural Information Processing Systems . 38,2018 , Montréal, Canada. New York : ACM , 2018 : 9628 - 9639 . doi: 10.1109/icinpro43533.2018.9096860 http://dx.doi.org/10.1109/icinpro43533.2018.9096860
韩东岳 , 桑海峰 . 利用动态步态图进行步态识别 [J]. 电子测量与仪器学报 , 2022 , 36 ( 2 ): 139 - 145 .
HAN D Y , SANG H F . Gait recognition based on dynamic gait image [J]. Journal of Electronic Measurement and Instrumentation , 2022 , 36 ( 2 ): 139 - 145 . (in Chinese)
曾维 , 何刚强 , 罗伟洋 , 等 . 基于ICNet模型的人体步态识别研究 [J]. 电子测量技术 , 2022 , 45 ( 4 ): 120 - 125 .
ZENG W , HE G Q , LUO W Y , et al . Research on gait recognition of human body based on ICNet model [J]. Electronic Measurement Technology , 2022 , 45 ( 4 ): 120 - 125 . (in Chinese)
周潇涵 , 王修晖 . 基于非对称双路识别网络的步态识别方法 [J]. 计算机工程与应用 , 2022 , 58 ( 4 ): 150 - 156 . doi: 10.3778/j.issn.1002-8331.2008-0355 http://dx.doi.org/10.3778/j.issn.1002-8331.2008-0355
ZHOU X H , WANG X H . Novel gait recognition method based on asymmetric two-path network [J]. Computer Engineering and Applications , 2022 , 58 ( 4 ): 150 - 156 . (in Chinese) . doi: 10.3778/j.issn.1002-8331.2008-0355 http://dx.doi.org/10.3778/j.issn.1002-8331.2008-0355
胡少晖 , 王修晖 , 刘砚秋 . 基于多支路残差深度网络的跨视角步态识别方法 [J]. 模式识别与人工智能 , 2021 , 34 ( 5 ): 455 - 462 .
HU SH H , WANG X H , LIU Y Q . Cross-view gait recognition method based on multi-branch residual deep network [J]. Pattern Recognition and Artificial Intelligence , 2021 , 34 ( 5 ): 455 - 462 . (in Chinese)
KOVAČ J , ŠTRUC V , PEER P . Frame-based classification for cross-speed gait recognition [J]. Multimedia Tools and Applications , 2019 , 78 ( 5 ): 5621 - 5643 . doi: 10.1007/s11042-017-5469-0 http://dx.doi.org/10.1007/s11042-017-5469-0
罗正平 , 刘延钧 , 杨天奇 . 光流分量分解的步态识别 [J]. 计算机科学 , 2016 , 43 ( 9 ): 295 - 300 . doi: 10.11896/j.issn.1002-137X.2016.09.059 http://dx.doi.org/10.11896/j.issn.1002-137X.2016.09.059
LUO ZH P , LIU Y J , YANG T Q . Gait recognition based on decomposition of optical flow components [J]. Computer Science , 2016 , 43 ( 9 ): 295 - 300 . (in Chinese) . doi: 10.11896/j.issn.1002-137X.2016.09.059 http://dx.doi.org/10.11896/j.issn.1002-137X.2016.09.059
0
浏览量
894
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构