A Hybrid Deep Learning Framework for Estimating Human 3D Pose from 2D Joint Positions

For computers to understand human activity or behavior in a variety of scenarios, reliable 3D human posture estimation is a prerequisite. Several difficulties have made such work more complex as it is influenced by various factors, including image quality, background, garment texture and diversity, body shape, and the presence of other objects alongside persons in the image which has depicted the necessity of adopting the technique of computer vision. While much work has been done on 2D human pose estimation, showing state-of-the-art performance, the objective of this research is to expand the capacity for 3D human pose estimation. We have investigated deep neural networks comprising of linear layers with residual blocks. And proposed a hybrid deep learning framework and raised the number of residual blocks to achieve this objective. The hybrid network comprises of two parallel models estimation and combines them to estimate 3D pose. This research also showed comparative training results. Finally, the proposed architecture was evaluated on H3WB dataset and presented the evaluation results considering the evaluation metrics of the mean per joint position error (MPJPE) and the percentage of correct keypoints (PCK). The proposed architecture performed about 50% better in terms of MPJPE and PCK@150mm for three residual blocks.