Human gait identification using Kinect sensor

Sabir, Azhin Tahir; Ahmed, Mohammed Hussein; Al-Talabani, Abdulbasit K.; Maghdid, Halgurd S.

doi:10.24017/science.2017.3.37

Cited by 10 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They first calculated the canonical correlation between the input pressure image and the database to select the most appropriate camera images from the dataset, and then image matching was performed on the camera input for personal authentication. Sabir et al [7] employed human 3D posture information acquired by Kinect. They focused on several joints in the posture information and used the statistics of their distances and angles from the ground for one walking cycle as feature values.…”

Section: Background and Related Workmentioning

confidence: 99%

Privacy-Aware Gait Identification With Ultralow-Dimensional Data Using a Distance Sensor

2023

View full text Add to dashboard Cite

As one of the most natural user behaviors, walking has been widely focused on developing personal identification systems due to its unique biometric authentication features. Popular visual solutions are usually affected by various environmental conditions, and their redundant user information (e.g., body type and appearance) makes it more challenging for users to maintain privacy and security. This paper proposes a distance sensor-based gait identification system that uses only one-dimensional data with a simple system structure. Specifically, a time-of-flight sensor was placed in front of a walking person, and a time series of distances was acquired. We extracted gait features from the data by calculating the velocity and acceleration curves and identifying individuals using a random forest classifier. We evaluated our system on 10 users using leave-one-out cross-validation. The average identification accuracy was 91.05% for 10 users. This study shows that gait recognition is possible using only one-dimensional time-series data with a noncontact sensor. It can be used as a contactless identification, reducing the computational resources required for low-cost and low-power consumption edge computing.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Privacy-Aware Gait Identification With Ultralow-Dimensional Data Using a Distance Sensor

2023

View full text Add to dashboard Cite

show abstract

“…gait cycle frame number is different from one person to another), we need to apply statistical moments to generate feature vector. In this work we applied mean and standard deviation based on equations 6, and 7 respectively: Table 1 presents the comparisons between the proposed method with various related approaches suggested in [16] and [2]. The two compared methods are re-implemented based on the same database which is used in this paper.…”

Section: Fig 4: An Example Of a Generated Trianglementioning

confidence: 99%

“…They used their own database of 20 participants, with 10 records per participant, their proposed method achieved results reach a 92% accuracy rate. In[2] angle and distance features are generated to represent gait characteristics and used for gait identification. distance features deal with human body distance, while angle features deal with some of the angles in human body joints.…”

mentioning

confidence: 99%

Gait-based Biometric Identification System using Triangulated Skeletal Models (TSM)

Sabir

2021

ACAD J NAWROZ UNIV

View full text Add to dashboard Cite

Human gait identification is a behavioral biometric technology which can be used to monitor human beings without user interaction. Recent researches are more focused on investigating gait as one of the biometric traits. Further, gait recognition aims to analyze and identify human behavioral activities and may be implemented in different scenarios including access control and criminal analysis. However, using various techniques in relation to image processing and obtaining better accuracy are remaining challenges. In last decade, Microsoft has introduced the Kinect sensor as an innovative sensor to provide image characteristics, precisely. Therefore, this article uses a Kinect sensor to extract gait characteristics to be used in individual recognition. A set of Triangulated shape are generated as new feature vector and called Triangulated Skeletal Model (TSM). Nearest Neighbor technique is utilized to do the recognition issue based on leave-one-out strategy. The experimental outcomes indicated that the recommended technique provides significant results and outperforms other comparative similar techniques with accuracy of 93.46%.

show abstract

“…There are many types of research related to human gait recognition (3) (4) , but only a few recent works used gait for gender classification (5) . In this paper, we propose gender classification based on gait feature using neutral and non-neutral gait sequence.…”

Section: Introductionmentioning

confidence: 99%

Human gait-based gender classification using neutral and non-neutral gait sequences

Mawlood

Sabir

2019

innovaciencia

View full text Add to dashboard Cite

A biometric system offers automatic identification of an individual basedon characteristic possessed by the individual. Biometric identification systems are often categorized as physiological or behavioural characteristics.Gait as one of the behavioural biometric recognition aims to recognizean individual by the way he/she walk. In this paper we propose genderclassification based on human gait features using wavelet transform andinvestigates the problem of non-neutral gait sequences; Coat Wearing andcarrying bag condition as addition to the neutral gait sequences. We shallinvestigate a new set of feature that generated based on the Gait Energy Image and Gait Entropy Image called Gait Entropy Energy Image(GEnEI). Three different feature sets constructed from GEnEI basedon wavelet transform called, Approximation coefficient Gait EntropyEnergy Image, Vertical coefficient Gait Entropy Energy Image and Approximation & Vertical coefficients Gait Entropy Energy Image Finallytwo different classification methods are used to test the performance ofthe proposed method separately, called k-nearest-neighbour and SupportVector Machine. Our tests are based on a large number of experimentsusing a well-known gait database called CASIA B gait database, includes124 subjects (93 males and 31 females). The experimental result indicatesthat the proposed method provides significant results and outperform thestate of the art.

show abstract

Human gait identification using Kinect sensor

Cited by 10 publications

References 20 publications

Privacy-Aware Gait Identification With Ultralow-Dimensional Data Using a Distance Sensor

Privacy-Aware Gait Identification With Ultralow-Dimensional Data Using a Distance Sensor

Gait-based Biometric Identification System using Triangulated Skeletal Models (TSM)

Human gait-based gender classification using neutral and non-neutral gait sequences

Contact Info

Product

Resources

About