|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2021 Vol.22 No.5 P.709-719
A partition approach for robust gait recognition based on gait template fusion
Abstract: Gait recognition has significant potential for remote human identification, but it is easily influenced by identity-unrelated factors such as clothing, carrying conditions, and view angles. Many gait templates have been presented that can effectively represent gait features. Each gait template has its advantages and can represent different prominent information. In this paper, gait template fusion is proposed to improve the classical representative gait template (such as a gait energy image) which represents incomplete information that is sensitive to changes in contour. We also present a partition method to reflect the different gait habits of different body parts of each pedestrian. The fused template is cropped into three parts (head, trunk, and leg regions) depending on the human body, and the three parts are then sent into the convolutional neural network to learn merged features. We present an extensive empirical evaluation of the CASIA-B dataset and compare the proposed method with existing ones. The results show good accuracy and robustness of the proposed method for gait recognition.
Key words: Gait recognition, Partition algorithms, Gait templates, Gait analysis, Gait energy image, Deep convolutional neural networks, Biometrics recognition, Pattern recognition
哈尔滨工程大学智能科学与工程学院,中国哈尔滨市,150001
摘要:步态识别具备远程识别的巨大潜力,但这种方法很容易受到与身份无关的因素影响,例如穿衣、随身携带的物体和角度。目前基于步态模板的方法可以有效表示步态特征。每一种步态模板都有其优势以及表征不同的显著信息。本文提出一种步态模板融合方法,以避免经典的步态模板(例如步态能量图像方法)的不足--经典步态模板表征的不完整信息对轮廓变化很敏感。所提步态模板融合方法采取分块的方法,以表征行人不同身体部位的不同步态习惯。根据人体各部分特点将融合的步态模板为3个部分(头部、躯干和腿部区域),然后将这3部分的步态模板分别输入卷积神经网络学习从而获得融合的步态特征。采用CASIA-B数据集进行充分的实验评估,并将所提方法与现有方法比较。实验结果表明,所提步态识别方法具有良好准确性和鲁棒性。
关键词组:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.2000377
CLC number:
TP391.4
Download Full Text:
Downloaded:
6505
Download summary:
<Click Here>Downloaded:
1362Clicked:
4359
Cited:
0
On-line Access:
2021-05-17
Received:
2020-07-25
Revision Accepted:
2020-11-11
Crosschecked:
2021-02-03