If one of a paired item is detected, search for a second by decreasing corresponding confidence threshold

[aching1]

It's often possible to create a scenario whereby one of a paired item (breasts, feet etc) is detected. In such a case, we have an improved prior that a second is likely to be present, but wasn't meeting the confidence threshold, so we'd like to try searching to find it with lower threshold. Some possible approaches:

• scale threshold by distance: closer items (relative to the size of the detected item) are more likely to be the missing one of the pair
• in a video, it's possible that the missing item is detected earlier/later in the video, so we could look around in time too

[solarorb93]

Initial idea for implementation: add a config for "pairable" features. Add all raw boxes as an optional input to process_raw_box. During process_raw_box, if a label is pairable, calculate distance metric to nearest raw box above threshold, and if less than the critical distance, decrease the min_prob for promoting the raw box to a censorable box.

Better implementation would be to only deal in pairs, but that would require some much more complicated work and almost surely not worth it.