Samba: A Real-Time Motion Capture System Using Wireless Camera Sensor Networks

Oh, Hyeong-Seok; Cha, Geonho; Oh, Songhwai

doi:10.3390/s140305516

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The human body is an important subject in nonrigid reconstruction since reconstruction of 3D human structures has broad applications, such as athletic training, computer animation and gait analysis. Using multi-camera systems [ 15 , 16 ] can easily resolve the ambiguities in non-rigid reconstruction problems, and the requirement for dedicated equipment prevents the methods from applying in more practical scenarios. Using a depth camera can also avoid the ambiguities in monocular 3D non-rigid reconstruction problems [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera

Wang

Chen

2017

Sensors

View full text Add to dashboard Cite

Recovering 3D structures from the monocular image sequence is an inherently ambiguous problem that has attracted considerable attention from several research communities. To resolve the ambiguities, a variety of additional priors, such as low-rank shape basis, have been proposed. In this paper, we make two contributions. First, we introduce an assumption that 3D structures lie on the union of nonlinear subspaces. Based on this assumption, we propose a Non-Rigid Structure from Motion (NRSfM) method with kernelized low-rank representation. To be specific, we utilize the soft-inextensibility constraint to accurately recover 3D human motions. Second, we extend this NRSfM method to the marker-less 3D human pose estimation problem by combining with Convolutional Neural Network (CNN) based 2D human joint detectors. To evaluate the performance of our methods, we apply our marker-based method on several sequences from Utrecht Multi-Person Motion (UMPM) benchmark and CMU MoCap datasets, and then apply the marker-less method on the Human3.6M datasets. The experiments demonstrate that the kernelized low-rank representation is more suitable for modeling the complex deformation and the method consequently yields more accurate reconstructions. Benefiting from the CNN-based detector, the marker-less approach can be applied to more real-life applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera

Wang

Chen

2017

Sensors

View full text Add to dashboard Cite

show abstract

“…Motion capture system is a non-invasive method for recording human movements [18][19][20]. Biomechanics Force Platforms can be used to collect kinetic data relating to ground reaction forces by detecting forces and moments applied to their top surface [21,22].…”

Section: Introductionmentioning

confidence: 99%

Difference in vertical jumping abilities, endurance and quickness of regeneration lower extremity muscle groups after physical effort between CrossFit and climbing athletes

Gawda

Ginszt

Smółka

et al. 2017

Polish Journal of Public Health

View full text Add to dashboard Cite

Introduction. Productive sporting performance in various sports disciplines often heavily depends on jumping abilities as well as on lower limb muscles power and endurance of the athletes involved. Both CrossFit, a popular high-intensity training program and sport climbing require lower extremity muscular power and endurance. Aim. The aim of this study was to compare vertical jumping abilities, endurance and quickness of the regeneration in gastrocnemius lateralis (GL), vastus medialis (VMO) and gluteus maximus (GM) muscles in CrossFit athletes and sport climbers. Material and methods. The study comprised 20 male athletes aged 24.3±4.7, divided into two equal groups: training CrossFit (CF) and sport climbers (SC). Vertical jump test was recorded by Vicon® motion capture system and AMTI® biomechanics force platforms. The myoelectric activity of the GL, VMO and GM muscles was recorded by myon®. Results. Significant difference in height of vertical jump in CrossFit athletes and sport climbers was observed (SC: 125.43 cm, 120.92 cm; CF: 110.42 cm, 110.86 cm; p<0.05). The endurance of the GL muscles in athletes using CrossFit training is significantly higher in comparison to sport climbers. Athletes training CrossFit have a better ability to recover GL, GM and VMO muscles than sport climbers. Conclusions. Sport climbers have better results in vertical jump tests than the athletes doing CrossFit. The endurance of the GL muscles in athletes doing CrossFit is higher in comparison to sport climbers. Athletes doing CrossFit have also better ability to muscles recover than sport climbers.

show abstract

3D articulated skeleton extraction using a single consumer-grade depth camera

Deng

Luo

et al. 2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Samba: A Real-Time Motion Capture System Using Wireless Camera Sensor Networks

Cited by 6 publications

References 20 publications

Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera

Capturing Complex 3D Human Motions with Kernelized Low-Rank Representation from Monocular RGB Camera

Difference in vertical jumping abilities, endurance and quickness of regeneration lower extremity muscle groups after physical effort between CrossFit and climbing athletes

3D articulated skeleton extraction using a single consumer-grade depth camera

Contact Info

Product

Resources

About