Automated Video Quality Assessment for the Edinburgh Visual Gait Score (EVGS)
Bibliographic record
Abstract
This research addresses critical challenges in clinical gait analysis by developing an automated video quality assessment framework to support Edinburgh Visual Gait Score (EVGS) scoring. The proposed methodology uses the MoveNet Lightning pose estimation model to extract body keypoints from video frames, enabling detection of multiple persons, tracking the person of interest, assessment of plane orientation, identification of overlapping individuals, detection of zoom artifacts, and evaluation of video resolution. These components are integrated into a unified quality classification system using a random forest classifier. The framework achieved high performance across key metrics, with 96% accuracy in detecting multiple persons, 95% in assessing overlaps, and 92% in identifying zoom events, culminating in an overall video quality categorization accuracy of 95%. This performance not only facilitates the automated selection of videos suitable for analysis but also provides specific video improvement suggestions when quality standards are not met. Consequently, the proposed system has the potential to streamline gait analysis workflows, reduce reliance on manual quality checks in clinical practice, and enable automated EVGS scoring by ensuring appropriate video quality as input to the gait scoring system.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".