When to use
- For research protocol documentation and descriptive session summaries
- For preparing ConductVision Human Tracking video workflows
- For organizing export-ready methods text, filenames, or CSV quality checks
Inspect ConductVision, MMPose, or DeepLabCut-style keypoint exports for low-confidence frames, missing values, and QC flags.

Paste pose export CSV data with confidence or likelihood columns and produce a compact data quality report before analysis.
rows
5
confidence columns
3
confidence values
15
low confidence values
3
low confidence percent
20
missing values
0
Pose export QC summary rows: 5 confidence columns: 3 confidence values: 15 low confidence values: 3 low confidence percent: 20 missing values: 0 Pose export quality was summarized from confidence and missing-value fields before downstream research analysis. Research use only. This tool is for education, protocol documentation, and research workflow planning. It is not for care decisions, participant triage, or health advice.
When to use
Do not use for
Use participant, subject, trial, protocol, and research session language. Avoid care-directed interpretations.
Store source video, keypoint exports, confidence values, and session notes so outputs remain auditable.
Run one short pilot and inspect visibility, lighting, scale references, and keypoint confidence before collecting a full dataset.
The tool performs deterministic arithmetic, checklist generation, or CSV summary operations in the browser. It does not assess injuries, classify participants for care, or replace a protocol approved for research use.
Last validated 2026-06-02. Calculations are designed for planning and documentation support; verify procurement decisions against manufacturer specifications or institutional SOPs.
ConductScience Pose Export QC Inspector (v0.10.253). ConductScience, Inc. 2026. Available at: https://conductscience.com/tools/pose-export-qc-inspector
Podsiadlo D, Richardson S. The timed Up & Go: a test of basic functional mobility for frail elderly persons. J Am Geriatr Soc. 1991;39(2):142-148.
Duncan PW, Weiner DK, Chandler J, Studenski S. Functional Reach task reference. J Gerontol. 1990;45(6):M192-M197.
Mathis A et al. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nat Neurosci. 2018;21(9):1281-1289.
Learn how ConductVision exposes coordinates, confidence values, and overlays.
Open app AppHuman research video applications.
Open app AppPlan body points and training data.
Open app QuoteGet a quote on equipment or talk to the ConductScience team.
Request quote