A Comparative Study of Pose Estimation

Abstract

In the past years, the vision of computers has been able to achieve massive momentum that could provide the absolute best of expectations among the many fields and sectors. A research paper on Human Pose Estimation would open new opportunities and help those who researched in finding the best techniques and methods for human pose detection. In this paper, we proposed that by using Open Pose 2D based pose estimation model technique to track and calculate every minute movement and perform analysis in real time. This technique which has been chosen has an amazing advantage of reasoning about pose in a comprehensive manner and has a straightforward but yet efficacious conceptualization which takes advantage of the recent advances in the Computer Vision Sector. We have presented an elaborate factual analysis with performance that is one step ahead based on four scholastic standards of varied real world representations.