太原理工大学学报2025，Vol.56Issue(3)：524-532,9.DOI:10.16355/j.tyut.1007-9432.20230210
基于GaitPart的跨视角步态识别方法
GaitPart-based Cross-view Gait Recognition Method
摘要
Abstract
[Purposes]To address the problem of sharp decrease in recognition accuracy caused by covariate factors such as camera view or pedestrian occlusion in gait recognition,an improved fea-ture enhancement GaitPart cross-view gait recognition method IFE-GaitPart(An Improved Feature Enhancement GaitPart)is proposed.[Methods]In the proposed method,the network model was im-proved into a two-path parallel form containing a spatial feature extraction branch and a significant tem-poral modeling branch.First,a convolutional network was used to extract shallow features from the original input sequence as the input of the two-path network.Then,a non-uniform convolutional ap-proach was proposed to extract fine-grained information of gait in spatial feature extraction and global features were fused to improve the information capacity of spatial features,while in the significant tem-poral modeling branch,an adaptive multi-scale temporal feature extraction module was proposed on the significant time modeling branch to obtain the short-term dependence and global time cues of the gait in the time dimension,and the complete temporal information was obtained after stitching.Fi-nally,the temporal features were stitched in the channel dimension and the gait features were output by using a fully connected layer.[Results]The experimental results show that the effectiveness of the method is demonstrated by achieving 97.6%,94.5%,and 81.1%Rank-1 accuracy on the CASIA-B dataset with normal walking,carrying luggage,and wearing outerwear,respectively.关键词
步态识别/特征融合/跨视角/行人遮挡/多尺度Key words
gait recognition/feature fusion/cross-view/pedestrian shelter/multiscale分类
信息技术与安全科学引用本文复制引用
刘健虎,刘星,谷淼,王浚瞩,张海龙,邓红霞..基于GaitPart的跨视角步态识别方法[J].太原理工大学学报,2025,56(3):524-532,9.基金项目
山西省中央引导地方科技发展资金项目(YDZJSX2022A016) （YDZJSX2022A016）
2022年浙江大学CAD&CG国家重点实验室开放课题(A2221) （A2221）
