A machine learning study highlighting the challenges of fidgety movement recognition using vision and inertial sensors. [PDF]
Sci RepLentzsch F +13 more
europepmc +1 more source
Hybrid vision-IMU deep learning framework with graph convolutional networks and attention for personalized yoga posture identification. [PDF]
Sci RepVallabhaneni N, Panneer P.
europepmc +1 more source
Quantitative Evaluation and Optimization of Museum Fatigue Using Computer Vision Human Pose Estimation. [PDF]
Sensors (Basel)Cheng Z, Zhang Y, Zhang L.
europepmc +1 more source
Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor. [PDF]
Biomimetics (Basel)Li H, Li H, Qin Y, Liu Y.
europepmc +1 more source
Assessment of basketball players' motion quality degradation by video-based virtual sensing and the AGCN-Mamba network. [PDF]
BMC Sports Sci Med RehabilYang Z, Zhao Y.
europepmc +1 more source
Promoting continuous rehabilitation with AI-based motion capture and biomechanical analysis: objective feedback as a catalyst. [PDF]
Front Rehabil SciMatsuura K +6 more
europepmc +1 more source
Enhanced keypoint recognition framework via multi-scale feature characteristics. [PDF]
Sci RepHuang M, Gao J, Ma L.
europepmc +1 more source
A markerless system for gait analysis based on OpenPose library
2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2020 The paper reports the performance of a low-cost markerless system for 3D human motion detection and tracking, consisting of the open-source library OpenPose, two webcams and a linear triangulation algorithm. OpenPose is able to identify anatomical landmarks with a commercial webcam, using Convolutional Neural Networks trained on data obtained from ...
Erika D'Antonio +2 more
exaly +3 more sources