一种基于多轮廓特征融合的步态识别方法

王 兵
民政职业大学 康复工程学院

摘要


步态特征类型多样,具有自然性、隐蔽性、非接触等优势。针对现有步态识别方法中特征使用单一、外观变化等因素,提出了一种特征融合的步态识别方法。本文根据步态识别的基本原理,将常见的两种步态轮廓特征进行融合,提升步态识别的准确率。同时对比了深度学习常用步态识别方法,验证了深度学习方法在步态识别研究上的优势。

关键词


步态特征;轮廓特征;步态识别

全文:

PDF


参考


[1]陈玲,杨天齐.基于质心和轮廓关键点的步态识别[J].计算机工程与应用,2015,51(19):173-188.

[2] Fan C, Peng Y, Cao C, et al. Gaitpart: Temporal partbasedmodel for gait recognition[C]. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Virtual, Online, United states, 2020.14225-14233.

[3] Chao H, He Y, Zhang J, et al. Gaitset: Regarding gait as a set for cross-view gait recognition[C]. Proceedings of the AAAI conference on artificial intelligence. Honolulu, HI, United states, 2019, 33(01): 8126-8133.

[4]丰明聪,葛洪伟.基于可变区域特征和SVM的步态识别研究[J].计算机应用,2007,27(12):3081-3083.

[5]柴艳妹,赵荣椿.一种新的基于区域特征的快速步态识别方法[J].中国图象图形学报,2006,11(9):1260-1265.

[6] Yoo J H, Nixon M S, Harris C J. Extracting human gait signatures by body segment properties[C]. Image Analysis and Interpretation, 2002. Proceedings. Fifth IEEE Southwest Symposium on. IEEE, 2002:35-39.

[7] Yu S, Tan D, Tan T. 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). IEEE, Hong Kong, China, 2006, 4:441-444.


Refbacks

  • 当前没有refback。