期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Gait Recognition via Cross Walking Condition Constraint
1
作者 Runsheng Wang Hefei Ling +3 位作者 Ping Li Yuxuan Shi Lei Wu Jialie Shen 《Computers, Materials & Continua》 SCIE EI 2021年第9期3045-3060,共16页
Gait recognition is a biometric technique that captures human walking pattern using gait silhouettes as input and can be used for long-term recognition.Recently proposed video-based methods achieve high performance.Ho... Gait recognition is a biometric technique that captures human walking pattern using gait silhouettes as input and can be used for long-term recognition.Recently proposed video-based methods achieve high performance.However,gait covariates or walking conditions,i.e.,bag carrying and clothing,make the recognition of intra-class gait samples hard.Advanced methods simply use triplet loss for metric learning,which does not take the gait covariates into account.For alleviating the adverse influence of gait covariates,we propose cross walking condition constraint to explicitly consider the gait covariates.Specifically,this approach designs center-based and pair-wise loss functions to decrease discrepancy of intra-class gait samples under different walking conditions and enlarge the distance of inter-class gait samples under the same walking condition.Besides,we also propose a video-based strong baseline model of high performance by applying simple yet effective tricks,which have been validated in other individual recognition fields.With the proposed baseline model and loss functions,our method achieves the state-of-the-art performance. 展开更多
关键词 Gait recognition metric learning cross walking condition constraint gait covariates
下载PDF
Evaluating the Effect of Various Walking Conditions on KINECT-based Gait Recognition
2
作者 LIU Ruixuan Marina L.GAVRILOVA 《Instrumentation》 2022年第2期13-25,共13页
Human gait is one of the unobtrusive behavioral biometrics that has been extensively studied for various commercial and government applications.Biometric security,medical rehabilitation,virtual reality,and autonomous ... Human gait is one of the unobtrusive behavioral biometrics that has been extensively studied for various commercial and government applications.Biometric security,medical rehabilitation,virtual reality,and autonomous driving cars are some of the fields of study that rely on accurate gait recognition.While majority of studies have been focused on achieving very high recognition performance on a specific dataset,different issues arise in the real-world applications of this technology.This research is one of the first to evaluate the effects of changing walking speeds and directions on gait recognition rates under various walking conditions.Dataset was collected using the KINECT sensor.To draw an overall conclusion about the effects of walking speed and di-rection to the sensor,we define distance features and angle features.Furthermore,we propose two feature fusion methods for person recognition.Results of the study provide insights into how walking speeds and walking di-rections to the KINECT sensor influence the accuracy of gait recognition. 展开更多
关键词 Gait Recognition Kinect Sensor Feature Fusion walking conditions Biometric Security
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部