Human Gait Recognition: A Single Stream Optimal Deep Learning Features Fusion.

Faizan Saleem,Muhammad Attique Khan,Seifedine Kadry,Usman Tariq,Majed Alhaisoni,Ammar Armghan,Fayadh Alenezi,Jung-In Choi

doi:10.3390/s21227584

Abstract

Human Gait Recognition (HGR) is a biometric technique that has been utilized for security purposes for the last decade. The performance of gait recognition can be influenced by various factors such as wearing clothes, carrying a bag, and the walking surfaces. Furthermore, identification from differing views is a significant difficulty in HGR. Many techniques have been introduced in the literature for HGR using conventional and deep learning techniques. However, the traditional methods are not suitable for large datasets. Therefore, a new framework is proposed for human gait recognition using deep learning and best feature selection. The proposed framework includes data augmentation, feature extraction, feature selection, feature fusion, and classification. In the augmentation step, three flip operations were used. In the feature extraction step, two pre-trained models were employed, Inception-ResNet-V2 and NASNet Mobile. Both models were fine-tuned and trained using transfer learning on the CASIA B gait dataset. The features of the selected deep models were optimized using a modified three-step whale optimization algorithm and the best features were chosen. The selected best features were fused using the modified mean absolute deviation extended serial fusion (MDeSF) approach. Then, the final classification was performed using several classification algorithms. The experimental process was conducted on the entire CASIA B dataset and achieved an average accuracy of 89.0. Comparison with existing techniques showed an improvement in accuracy, recall rate, and computational time.

Highlights

Human gait recognition has become an active research area in the past decade in computer vision [1,2]
AAnnewewfrfarmameweworokrkwwasasprporpoposoesdedfofrorhuhmumanangagiatirterceocgongintiotino,ni,nicnlculduidnigngmmanaynystsetpesps susuchchasasdadtaataauagumgmenetnattaitoinon, f,efaetauturereexetxrtarcatcitoinon, f,efaetauturerefufsuisoino,na, nadndfefaetautruereseslelcetciotino.nT. hTehe aracrhchitietcetcuturereoof fththeepprorpoposoesdedfrfarmamewewoorkrkisisshshowownnininFiFgiugurere2.2I.nInththeeauaugmgmenentattaitoionnstsetpep, ththrere eflfiplipopoepreartaitoinosnswwereereusuesde.d.InInththe efefaetauturereexetxrtarcatcitoinonstsetpe,pt,wtwo oprper-etr-tarianiendedmmodoedlesls were used named Inception-ResNet-V2 and NASNet Mobile. Both models were fine-tuned and trained using transfer learning on the CASIA B dataset
Were used named Inception-ResNet-V2 and NASNet Mobile. Both models were finetuned and trained using transfer learning on the CASIA B dataset

Summary

Introduction

Human gait recognition has become an active research area in the past decade in computer vision [1,2]. Biometrics is an important application of gait recognition, employed in many industrial areas such surveillance and healthcare systems [3,4]. A few biological signals are useful for gait analysis such as electromyography (EMG) [7,8,9], inertial sensors [10,11], and plantar pressure [12]. Through these methods, the human gait can be analyzed, for example, through muscle movement while walking. Gait recognition algorithms have progressed to the point that they can be used in a wide range of “real-world” applications, such as video monitoring, crime prevention, and forensic detection [13,14]

Methods

Results

Conclusion