Development of A Sitting Posture Health Detection System Based on the Centernet Model
Bibliographic record
Abstract
At present, health problems caused by poor sitting posture have attracted much attention, especially affecting specific groups such as students and office workers not only causing physical health problems such as spinal curvature and cervical pain, but also triggering psychological problems such as anxiety and fatigue. Compared with traditional sitting posture detection methods, this paper proposes non-contact sitting posture detection system based on machine vision, which can capture sitting posture information in real time, accurately and conveniently, and helps to improve sitting posture habits and prevent health. Based on the lightweight human pose estimation model MoveNet under the CenterNet model, this model classifies the pose information (the coordinates of the 17 key points of the body) output by MoveNet to judge which sitting posture state the person in the picture is in. The application of this technology can help people correct bad sitting habits in time, reducing the occurrence of problems such as myopia, spinal diseases, and muscle stiffness and fatigue, and improving physical health. This system verifies the feasibility, stability, and accuracy of sitting posture detection system based on the CenterNet model. The test results show that this system can recognize the user's sitting posture state in real time and accurately, and give corresponding and suggestions, which improves the user's physical and mental health problems, and provides a solution for the future sitting posture health monitoring field.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".