Kinematic Analysis and Visualization of 3D Human Pose Estimation on the Web-app
Yi Fang Gan, King Hann Lim, Po Ken Pang, Nong Nurnie Mohd Nistah · 2022
Photogrammetry is one of the non-invasive markerless methods applied in postural assessment to measure the dynamical relation of body parts in terms of distance and angles. The use of camera sensing technology replaces visual inspectors to quantity the postural assessment in a more efficient way. To visualize a series of human motion, the proposed web-app automates the process of photogrammetry and generates the kinematic analysis. It allows three-dimensional joints visualization and an interactive kinematic graph for joints correlation. A preliminary postural assessment can be completed via uploading a video or a text file with postural information. The output of the web-app can be used to evaluate the posture of the human from the input data using 3D human joints, distance, and joint movement. In this work, the walking and running patterns were put into practise and examined. Results show that the kinematic analysis is made possible by the visualisation of 3D human joints in euclidean distance and joint angular characteristics.