Deep Learning-Based Outlier Detection and Correction for 3D Pose Estimation


KIPS Transactions on Software and Data Engineering, Vol. 11, No. 10, pp. 419-426, Oct. 2022
https://doi.org/10.3745/KTSDE.2022.11.10.419,   PDF Download:
Keywords: Human Pose Estimation, Pose Refinement, Deep Learning
Abstract

In this paper, we propose a method to improve the accuracy of 3D human pose estimation model in various move motions. Existing human pose estimation models have some problems of jitter, inversion, swap, miss that cause miss coordinates when estimating human poses. These problems cause low accuracy of pose estimation models to detect exact coordinates of human poses. We propose a method that consists of detection and correction methods to handle with these problems. Deep learning-based outlier detection method detects outlier of human pose coordinates in move motion effectively and rule-based correction method corrects the outlier according to a simple rule. We have shown that the proposed method is effective in various motions with the experiments using 2D golf swing motion data and have shown the possibility of expansion from 2D to 3D coordinates.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
C. Ju, J. Park, D. Lee, "Deep Learning-Based Outlier Detection and Correction for 3D Pose Estimation," KIPS Transactions on Software and Data Engineering, vol. 11, no. 10, pp. 419-426, 2022. DOI: https://doi.org/10.3745/KTSDE.2022.11.10.419.

[ACM Style]
Chan-Yang Ju, Ji-Sung Park, and Dong-Ho Lee. 2022. Deep Learning-Based Outlier Detection and Correction for 3D Pose Estimation. KIPS Transactions on Software and Data Engineering, 11, 10, (2022), 419-426. DOI: https://doi.org/10.3745/KTSDE.2022.11.10.419.