Abstract
We present a method to estimate a human pose in videos considering temporal consistency. In addition to the kernel density approximation based pose estimation for flexible mixtures-of-parts model, we extend the idea to the temporal domain. We conducted experiments with our proposed method on three videos. As a result, we demonstrate that the accuracy of our proposed method is 3.4-5.0% greater than that of previous approaches.
Type
Publication
In ITE Winter Annual Convention
Shin Fujieda
Sr. Software Development Engineer
My research interests include computer graphics and machine learning.