3D Skeleton model derived from Kinect Depth Sensor Camera and its application to walking style quality evaluations

Arai, Kohei; Asmara, Rosa Andrie

doi:10.14569/ijarai.2013.020705

Cited by 23 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed method, we manually measured the distance between the right wrist and the horizontal ground [13], and the angle of the right knee joint to highlight potential issues. We not only considered the key-joint positions of hands or feet as quantitative measures [52], but also visualized reconstruction results for qualitative analysis.…”

Section: Resultsmentioning

confidence: 99%

Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

et al. 2019

View full text Add to dashboard Cite

Using video sequences to restore 3D human poses is of great significance in the field of motion capture. This paper proposes a novel approach to estimate 3D human action via end-to-end learning of deep convolutional neural network to calculate the parameters of the parameterized skinned multi-person linear model. The method is divided into two main stages: (1) 3D human pose estimation based on a single frame image. We use 2D/3D skeleton point constraints, human height constraints, and generative adversarial network constraints to obtain a more accurate human-body model. The model is pre-trained using open-source human pose datasets; (2) Human-body pose generation based on video streams. Combined with the correlation of video sequences, a 3D human pose recovery method based on video streams is proposed, which uses the correlation between videos to generate a smoother 3D pose. In addition, we compared the proposed 3D human pose recovery method with the commercial motion capture platform to prove the effectiveness of the proposed method. To make a contrast, we first built a motion capture platform through two Kinect (V2) devices and iPi Soft series software to obtain depth-camera video sequences and monocular-camera video sequences respectively. Then we defined several different tasks, including the speed of the movements, the position of the subject, the orientation of the subject, and the complexity of the movements. Experimental results show that our low-cost method based on RGB video data can achieve similar results to commercial motion capture platform with RGB-D video data.

show abstract

Section: Resultsmentioning

confidence: 99%

Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

et al. 2019

View full text Add to dashboard Cite

show abstract

“…From the depth map provided by kinect sensor, a single skeleton is obtained after the work proposed in [22], which uses decision random forests over millions of features extracted in order to estimate the position of the joints of the human body, in real time. Arai et al [29] present a non-real time way to compute the skeleton from depth maps.…”

Section: A System Setupmentioning

confidence: 99%

A proposal of a non-intrusive, global movement analysis of hemiparesis treatment

Vieira¹,

Carmo

Jovita³

et al. 2015

Journal of Communication and Information Systems

View full text Add to dashboard Cite

Hemiparesis is the most disabling condition after a stroke. Hemiparetic individuals suffer from a loss of muscle strength on one side of the body, resulting in a decreased capacity of performing movements. To assess the quality of Physiotherapy treatment, rating scales are commonly used but with the shortcoming of being subjective. With the aim of developing a system that objectively outcomes how a hemiparetic individual is responding to a Physiotherapy treatment, this paper proposes a method to analyze human functional movement by means of an apparatus comprised of multiple low-cost RGB-D cameras. After extrinsically calibrating the cameras, the setup system should be able to build a composite skeleton of the target patient, to globally analyze patient's movement according to a reachable workspace and specific energy. These latter both are proposed to be carried out by tracking the hand movements of the patient, and the movement volume produced. Here we present the concept of the proposed system, as well as, the idea of its parts.

show abstract

“…foot, ankle, knee, or hip) will influence and make different to the walking gait of a person. Usually, rehabilitation and physiotherapy assessment rely on therapist's observation and judgement [1] and it can be very subjective to evaluate the improvement of the therapies [2]. The lack of strict scientific measurements makes the therapists have difficulties to calculate the quality of improvement of the therapies and only can figure the function roughly [3].…”

Section: Introductionmentioning

confidence: 99%

Lower Limb Walking Gait Profiling Using Marker-less Motion Capture with GDL and R-GDL methods to Assist Physiotherapy Treatment

Hisham¹,

Jamal²,

Idris³

2020

IJETT

View full text Add to dashboard Cite

Physiotherapy includes specialised therapist conducting mechanical force and movement onto human body in order to heal and avoid further physical injuries. Therapists rely on subjective estimation in order to measure the performance improvements after physiotherapy treatments. An automated method to analyse and measure improvement is needed to calculate improvements based on patients' walking gait. This method would require a gait profile database in order to be able to calculate patients' improvement after physiotherapy treatments. The new technologies with low cost sensing devices could provide new opportunities and potential to assist the effectiveness of physiotherapy treatment. This research proposed a framework for walking gait profiling using marker-less motion capture to assist physiotherapy treatment. The framework consists of two major modules which are: Motion Template Module and Motion Evaluation Module. The Motion Template Module includes the motion capturing process where the human body is precisely tracked in order to generate skeleton information, focused target and record the movements before developing a script of motion called GDL scripts (GDLs) as a template. The template will be used for categorisation purposes using Reverse-Gesture Description Language (R-GDL). Evaluations of other respondents' walking gait have been done in Motion Evaluation Module using GDL and the created GDLs. The GDL output is then calculated to generate the walking gait profile. The system can differentiate the similarities between normal and abnormal walking gait. This study shows that the framework can compare the walking gait among normal and abnormal walking, based on the generated template. Using the proposed framework, the effectiveness for walking gait profiling has been proven and can be used to assist the physiotherapy treatment.

show abstract

3D Skeleton model derived from Kinect Depth Sensor Camera and its application to walking style quality evaluations

Cited by 23 publications

References 12 publications

Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

Motion Capture Research: 3D Human Pose Recovery Based on RGB Video Sequences

A proposal of a non-intrusive, global movement analysis of hemiparesis treatment

Lower Limb Walking Gait Profiling Using Marker-less Motion Capture with GDL and R-GDL methods to Assist Physiotherapy Treatment

Contact Info

Product

Resources

About