Constraint-Based Optimized Human Skeleton Extraction from Single-Depth Camera

Li, Ruotong; Si, Weixin; Weinmann, Michael; Klein, Reinhard

doi:10.3390/s19112604

Cited by 18 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A combination of a Kinect and several Inertial Measurement Units (IMUs) could also be used to reduce the upper limb position error by up to 20%, according to Jatesiktat et al [ 50 , 51 , 52 ]. Finally, a device-independent approach is to incorporate body constraints (such as human skeleton length conservation and temporal constraints) to enhance the continuity of the estimated skeleton [ 53 ]. These solutions have the potential to consequently improve the accuracy of the Kinect while remaining affordable, even if the solutions require a high technical level and might lengthen the duration of patient preparation.…”

Section: Discussionmentioning

confidence: 99%

Validity and Reliability of Kinect v2 for Quantifying Upper Body Kinematics during Seated Reaching

Faity¹,

Mottet²,

Froger

2022

Sensors

View full text Add to dashboard Cite

Kinematic analysis of the upper limbs is a good way to assess and monitor recovery in individuals with stroke, but it remains little used in clinical routine due to its low feasibility. The aim of this study is to assess the validity and reliability of the Kinect v2 for the analysis of upper limb reaching kinematics. Twenty-six healthy participants performed seated hand-reaching tasks while holding a dumbbell to induce behaviour similar to that of stroke survivors. With the Kinect v2 and with the VICON, 3D upper limb and trunk motions were simultaneously recorded. The Kinect assesses trunk compensations, hand range of motion, movement time and mean velocity with a moderate to excellent reliability. In contrast, elbow and shoulder range of motion, time to peak velocity and path length ratio have a poor to moderate reliability. Finally, instantaneous hand and elbow tracking are not precise enough to reliably assess the number of velocity peaks and the peak hand velocity. Thanks to its ease of use and markerless properties, the Kinect can be used in clinical routine for semi-automated quantitative diagnostics guiding individualised rehabilitation of the upper limb. However, engineers and therapists must bear in mind the tracking limitations of the Kinect.

show abstract

Section: Discussionmentioning

confidence: 99%

Validity and Reliability of Kinect v2 for Quantifying Upper Body Kinematics during Seated Reaching

Faity¹,

Mottet²,

Froger

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, one of the challenges of future work is the design and development of a robust intelligent layer which further incorporates the existing skeleton tracking data that can be used in enhancing or compensating for any missing information. Such missing tracking data can be caused by various cases of occlusions and self-occlusions of the body or the presence of another person or pieces of furniture in the scene [ 19 ].…”

Section: Discussionmentioning

confidence: 99%

Experimental Study of a Deep-Learning RGB-D Tracker for Virtual Remote Human Model Reconstruction

Payandeh

Wael

2021

International Journal of Telemedicine and Applications

View full text Add to dashboard Cite

Tracking movements of the body in a natural living environment of a person is a challenging undertaking. Such tracking information can be used as a part of detecting any onsets of anomalies in movement patterns or as a part of a remote monitoring environment. The tracking information can be mapped and visualized using a virtual avatar model of the tracked person. This paper presents an initial novel experimental study of using a commercially available deep-learning body tracking system based on an RGB-D sensor for virtual human model reconstruction. We carried out our study in an indoor environment under natural conditions. To study the performance of the tracker, we experimentally study the output of the tracker which is in the form of a skeleton (stick-figure) data structure under several conditions in order to observe its robustness and identify its drawbacks. In addition, we show and study how the generic model can be mapped for virtual human model reconstruction. It was found that the deep-learning tracking approach using an RGB-D sensor is susceptible to various environmental factors which result in the absence and presence of noise in estimating the resulting locations of skeleton joints. This as a result introduces challenges for further virtual model reconstruction. We present an initial approach for compensating for such noise resulting in a better temporal variation of the joint coordinates in the captured skeleton data. We explored how the extracted joint position information of the skeleton data can be used as a part of the virtual human model reconstruction.

show abstract

“…A combination of a Kinect and several Inertial Measurement Units (IMUs) could also be used to reduce the upper limb position error up to 20% according to Jatesiktat et al [48][49][50]. Finally, a device-independent approach is to incorporate body constraints (such as human skeleton length conservation and temporal constraints) to enhance the continuity of the estimated skeleton [51]. These solutions have the potential to consequently improve the accuracy of the Kinect while remaining affordable, even if the solutions require a high technical level and might lengthens the duration of patient preparation.…”

Section: Smoothing Out Kinect Errorsmentioning

confidence: 99%

Validity and reliability of Kinect v2 for quantifying upper body kinematics during seated reaching

Faity¹,

Mottet²,

Froger³

2022

Preprint

View full text Add to dashboard Cite

Background: Kinematic analysis of the upper limbs is a good way to assess and monitor recovery in individuals with stroke, but remains little used in clinical routine due to its low feasibility. The aim of this study is to assess the validity and reliability of the Kinect v2 for the assessment of 17 kinematic variables commonly used in the analysis of upper limb reaching in stroke. Methods: 26 healthy participants performed seated hand-reaching tasks while holding a dumbbell to induce a behaviour similar to that of a person with a stroke. 3D upper limb and trunk motion were simultaneously recorded with the Kinect v2 (Microsoft, USA) and with the VICON (OxfordMetrics, UK), the latter being the reference system. For each kinematic outcome, the validity of the Kinect was assessed with ICC, linear regression and Bland & Altman plots. Results: The Kinect assesses trunk compensations, hand range of motion, movement time and mean velocity with a moderate to excellent reliability. In contrast, elbow and shoulder range of motion, time to peak velocity and path length ratio have a poor to moderate reliability, indicating that these variables should be interpreted with caution. Finally, instantaneous hand and elbow tracking are not precise enough to reliably assess Cartesian and angular kinematics over time, rendering variables such as the number of velocity peaks and the peak hand velocity unusable. Conclusions: Thanks to its ease of use and markerless properties, the Kinect can be used in clinical routine for semi-automated quantitative diagnostics guiding individualised rehabilitation of the upper limb. However, engineers and therapists must bear in mind the limitations of the Kinect for the instantaneous tracking of the hand and elbow.

show abstract

Constraint-Based Optimized Human Skeleton Extraction from Single-Depth Camera

Cited by 18 publications

References 24 publications

Validity and Reliability of Kinect v2 for Quantifying Upper Body Kinematics during Seated Reaching

Validity and Reliability of Kinect v2 for Quantifying Upper Body Kinematics during Seated Reaching

Experimental Study of a Deep-Learning RGB-D Tracker for Virtual Remote Human Model Reconstruction

Validity and reliability of Kinect v2 for quantifying upper body kinematics during seated reaching

Contact Info

Product

Resources

About