The Effect of Noise on Contactless Heart Rate Measurement using Video Magnification
Bibliographic record
Abstract
Detecting heart rate via the non-contact method of Video Magnification (VM) is necessary when contact-based methods are overly cumbersome or not feasible, such as during a remote virtual consultation with a physician. The heart rate (HR) signal in video is best correlated with the miniscule change in skin colour associated with the presence and absence of capillary blood during the heart compression/recovery cycle. This change primarily affects the green colour channel in video at levels that are imperceptible to the human eye but can be detected by VM. However, there are many sources of noise that influence the performance of the VM algorithm, starting with the video capture process and ending with the algorithm parameters. In this paper, the VM algorithm performance in the absence and presence of noise was investigated under controlled conditions through the creation of artificial videos with set parameters to better assess algorithm performance. It was found that in the absence of noise, the VM algorithm can accurately detect the simulated HR frequency with a signal amplitude as small as ±1 quantization level. Moreover, it was also found that the algorithm can detect the simulated HR frequency with a signal amplitude as small as ±0.5 quantization level in the presence of a small level of noise. Lastly, it was found that although algorithm performance degraded with increased noise, the simulated HR results could be found in signals as low as ±1 quantization level even with noise at a power equivalent to ±32 quantization levels.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".