Gait Recognition from Freestyle Walks Using Relative Coordinates and Random Subsequence-Based Sum-Rule Classification

Jianwattanapaisarn, Nitchan; Khamsemanan, Nirattaya; Nattee, Cholwich

doi:10.1109/scis-isis.2016.0016

Cited by 4 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another remarkable recognition performance with coordinate skeleton joints as features was also reported in [44]. In this study, relative coordinates of joints with hip center point as reference along with both left and right hip along with spine joints were extracted from each of the 90 subjects as gait features contributed to high recognition accuracy of 92.22%.…”

Section: B Human Gait Recognition With Kinectmentioning

confidence: 63%

“…Past researches findings found that low recognition performance were obtained using dynamic features for instance angle of body parts and step length were most commonly extracted as the dynamic features. However, higher recognition accuracy attained using dynamic features was based on combination of significant coordinates of skeleton joint as discussed in [31] and [44]. As for static features [30] and dynamic features derived from lower limbs as mentioned in [38], higher recognition performance was attained as reported in [31].…”

Section: B Human Gait Recognition With Kinectmentioning

confidence: 99%

See 1 more Smart Citation

Human Gait Recognition Using Skeleton Joint Coordinates with Orthogonal Least Square and Locally Linear Embedded Techniques

Sahak

Tahir

Yassin

et al. 2019

International Journal of Simulation: Systems, Science &Amp; Technology

View full text Add to dashboard Cite

This study investigated the skeleton points in the three dimensional (3D) space using Kinect sensor to be utilised as recognition of human based on their walking gait in frontal view. Firstly, walking gait of 30 subjects is captured using Kinect sensor. Next, all the twenty skeleton joints in the 3D space within one full gait cycle of each subjects are extracted as features. Further, the significant features amongst the skeleton joints are extracted using Orthogonal Least Square (OLS) technique followed by Locally Linear Embedded (LLE) as feature selection. The effectiveness of OLS as feature extraction along with LLE as feature selection is evaluated using Support Vector Machine as the machine classifier. Classification results attained for human gait recognition are 98.67% and 97% based on RBF and polynomial kernel respectively This proven that the significant gait features identified using OLS and LLE techniques are indeed suitable for gait recognition purpose.

show abstract

Section: B Human Gait Recognition With Kinectmentioning

confidence: 63%

Section: B Human Gait Recognition With Kinectmentioning

confidence: 99%

Human Gait Recognition Using Skeleton Joint Coordinates with Orthogonal Least Square and Locally Linear Embedded Techniques

Sahak

Tahir

Yassin

et al. 2019

International Journal of Simulation: Systems, Science &Amp; Technology

View full text Add to dashboard Cite

show abstract

“…They obtained the highest identification performance with 82 % accuracy using static and dynamic features together. Jianwattanapaisarn et al [13] have created their own data set of 90 individuals and performed identification using the gait features that they have obtained from individual's walking freely at separate times using the Kinect device. Detecting the gait subsequences with fixed length at random numbers and giving these gait subsequences to a group of extra-tree classifiers, they obtained predictions for an entire gait.…”

Section: Resultsmentioning

confidence: 99%

“…The data manipulation is achieved by assigning a virtual value to undefined data between any two defined data values by taking the average of the previous and next data values. The following features are also extracted based on the study of Jianwattanapaisarn et al [13] during the data collection process: (i) the real-time three dimensional X, Y and Z coordinate information of 25 joint points, (ii) the X, Y, and Z vectors of the joint points (except for the leaf node joint points representing the head, left foot, right foot, left hand tip, right hand tip, left thumb and right thumb) calculated from the orientation data in accordance with the joint points they are associated to, and (iii) the angles of refraction of the joint points with orientation data calculated in accordance with the joint points they are associated to. The orientation data herein are the rotation motion of the joint points they make with the subsequent joint points towards leaf points and provided by Kinect device in quaternion form.…”

Section: A Obtaining the Data Setmentioning

confidence: 99%

“…Singh and Jain [12] have obtained dynamic features by creating two triangles between three points to represent the human body. Jianwattanapaisarn et al [13] have achieved a high level of identification performance by using some joint coordinate points as a gait feature. Also, Sahak et al [5] have stated that while low identification performance is observed in studies using only dynamic features, in the studies using the combination of static and dynamic features high identification performance is observed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Identification from Gait Features Using Cascade Voting Method

Ercin

Karacı

2021

Applied Computer Systems

View full text Add to dashboard Cite

There are several biometric methods for identification. These are generally classified under two main groups as physiological and behavioural biometric methods. Recently, methods using behavioural biometric features have gained popularity. Identification made using gait pattern is also one of these methods. The present study proposes a machine learning based system performing identification in real time via gait features using a Kinect device. The data set is composed of 23 individuals’ skeleton model data obtained by the authors. From these data, 147 handcrafted features have been extracted. Deep Neural Network (DNN), Random Forest (RF), Gradient Boosting (GB), XG-Boost (XGB) and K-Nearest Neighbour (KNN) classifiers have been trained with these features. Furthermore, the output of these five machine learning models has been combined with a voting approach. The highest classification has been obtained with 97.5 % accuracy via a voting approach. The classification accuracies of the RF, DNN, XGB, GB and KNN classifiers are 95 %, 87.5 %, 85 %, 80 % and 65 %, respectively. The classification accuracy obtained via a voting approach is higher than in the previous studies. The developed system successfully performs real-time identification.

show abstract