Comparative study on pose estimators such as MoveNet Lighting, MoveNet Thunder, and OpenPose (MobileNet) model for Human Pose Estimation over Real-Time Feed
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".