administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-05 10:45:21 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Fix computations in false_positives.md

Browse Source 
1. The `Score History` values seem to have the wrong values from `Current Score`.   
2. Got rid of the initial 0.0 values for frames 1 and 2. In any case, I'd suggest something closer to NULL than a numeric value.  
3. Added two decimal values for visual homogeneity.  
4. Corrected the median for frame 4 (median of 0, .85, .9) and frame 6 (median of .9, .88, .95)
This commit is contained in:
Sergei 2023-05-23 16:43:59 -07:00 committed by GitHub
parent 1e17dbaa91
commit 3132fa1f39
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
docs/docs/guides/false_positives.md
View File

@ -11,13 +11,13 @@ Similarly, the `min_ratio` and `max_ratio` values are compared against a given d
For object filters in your configuration, any single detection below `min_score` will be ignored as a false positive. `threshold` is based on the median of the history of scores (padded to 3 values) for a tracked object. Consider the following frames when `min_score` is set to 0.6 and threshold is set to 0.85: For object filters in your configuration, any single detection below `min_score` will be ignored as a false positive. `threshold` is based on the median of the history of scores (padded to 3 values) for a tracked object. Consider the following frames when `min_score` is set to 0.6 and threshold is set to 0.85:
| Frame | Current Score | Score History | Computed Score | Detected Object | | Frame | Current Score | Score History | Computed Score | Detected Object |
| ----- | ------------- | --------------------------------- | -------------- | --------------- | | ----- | ------------- | -----------------------------------| -------------- | --------------- |
| 1 | 0.7 | 0.0, 0, 0.7 | 0.0 | No | | 1 | 0.70 | 0.70 | 0.0 | No |
| 2 | 0.55 | 0.0, 0.7, 0.0 | 0.0 | No | | 2 | 0.55 | 0.70, 0.00 | 0.0 | No |
| 3 | 0.85 | 0.7, 0.0, 0.85 | 0.7 | No | | 3 | 0.85 | 0.70, 0.00, 0.85 | 0.7 | No |
| 4 | 0.90 | 0.7, 0.85, 0.95, 0.90 | 0.875 | Yes | | 4 | 0.90 | 0.70, 0.00, 0.85, 0.90 | 0.85 | Yes |
| 5 | 0.88 | 0.7, 0.85, 0.95, 0.90, 0.88 | 0.88 | Yes | | 5 | 0.88 | 0.70, 0.00, 0.85, 0.90, 0.88 | 0.88 | Yes |
| 6 | 0.95 | 0.7, 0.85, 0.95, 0.90, 0.88, 0.95 | 0.89 | Yes | | 6 | 0.95 | 0.70, 0.00, 0.85, 0.90, 0.88, 0.95 | 0.90 | Yes |
In frame 2, the score is below the `min_score` value, so Frigate ignores it and it becomes a 0.0. The computed score is the median of the score history (padding to at least 3 values), and only when that computed score crosses the `threshold` is the object marked as a true positive. That happens in frame 4 in the example. In frame 2, the score is below the `min_score` value, so Frigate ignores it and it becomes a 0.0. The computed score is the median of the score history (padding to at least 3 values), and only when that computed score crosses the `threshold` is the object marked as a true positive. That happens in frame 4 in the example.