Table 4.
Identification accuracy and agreement results for the explorative videos between human annotators and the computer vision algorithm using the Re-ID technique
| Video, condition | Duration of identity – manual (s) | Duration of identity – algorithm (s) | Δ (s) | Normalized Δ (%) | Cohen’s kappa | Re-ID Accuracy (%) | ||
|---|---|---|---|---|---|---|---|---|
| Patient Caregiver | Researchers | Patient Caregiver | Researchers | |||||
| #6 long duration, rectangular AOI | 173.84 | 0.08 | 183.4 | 0.12 | – 9.52 | 0.86 | 0.95 | 98.61 |
| #6 long duration, oval AOI | 173.56 | 0.04 | 183.4 | 0.12 | – 9.76 | 0.88 | 0.95 | 98.65 |
| #7 long duration, rectangular AOI |
195.6 33.52 |
0.04 |
189.72 49.16 |
0.52 | 22 | 2.90 | 0.87 | 93.92 |
| #7 long duration, oval AOI |
182.16 26.88 |
0.2 |
189.72 49.16 |
0.52 | 15.04 | 1.98 | 0.85 | 93.18 |
Note: Duration of identity: the time (in s) a specific individual is identified. The identities are patients and researchers, in video #7 additionally a caregiver is identified, the time (in s) the caregiver is identified is shown in italics