Estimating finger postures by attaching an omnidirectional camera to the center of a user's palm

Yusuke Maruyama, Yasuyuki Kono · 2018

This research describes the development of a system that estimates the natural postures of a user's fingers from the images captured by an omnidirectional video camera attached to the center of the user's palm in real time. The finger postures can be estimated by detecting the fingertips on each image and referring to the following preset information: the positional relationship between the camera and the user's fingers/fingertips, the length between the finger joints, and the interdependencies between the finger joints.

Read the paper · More papers on PaperTik