false_positives.md: expand definition of ratios

I found this thread pretty helpful: https://github.com/blakeblackshear/frigate/issues/8350#issuecomment-1782863838

I figured it'd be worth including in the docs themselves.
This commit is contained in:
Kevin David 2024-01-14 12:56:06 -05:00 committed by GitHub
parent 7b71c21c12
commit 8f3b4a548b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -9,6 +9,12 @@ The `min_area` and `max_area` values are compared against the area (number of pi
Similarly, the `min_ratio` and `max_ratio` values are compared against a given detected object's width/height ratio (in pixels). If the ratio is outside this range, the object will be ignored as a false positive. This allows objects that are proportionally too short-and-wide (higher ratio) or too tall-and-narrow (smaller ratio) to be ignored.
:::info
Conceptually, a ratio of 1 is a square, 0.5 is a "tall skinny" box, and 2 is a "wide flat" box. If `min_ratio` is 1.0, any object that is taller than it is wide will be ignored. Similarly, if `max_ratio` is 1.0, then any object that is wider than it is tall will be ignored.
:::
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 |