Comparative study on pose estimators such as MoveNet Lighting, MoveNet Thunder, and OpenPose (MobileNet) model for Human Pose Estimation over Real-Time Feed

Abstract

Human pose estimation is a crucial task in various domains, including fitness and motion analysis, and sports performance evaluation. Existing technologies have limitations in terms of accuracy and real-time performance, which highlights the need for advanced solutions. The aim of this paper is to display the comparison between models for human pose estimation over real-time feed, with high accuracy and real-time performance. The problem statement involves developing a model and testing it to check if it can handle multiple subjects, different poses, and various lighting conditions. The proposed methodology involves using state- of-the-art models, such as MoveNet Lightning and MoveNet Thunder, along with the comparison to pre-existing models such as OpenPose model, which are slow and inaccurate. The key findings of this work include real-time performance comparison, high accuracy, and applicability in various domains. Nevertheless, it is imperative to acknowledge and confront specific constraints, such the issue of pose ambiguity and the challenge of effectively controlling occlusion. The suggested study presents a potentially effective approach for real-time human pose assessment, which has the capacity to yield advantages for humans. Keywords: Human pose estimation, real-time feed, MoveNet Lightning, MoveNet Thunder, OpenPose.