1,649
edits
Line 26: | Line 26: | ||
** This might fail if people spend the night there. AIUI this happens rarely enough that we may not care about the inaccuracy. | ** This might fail if people spend the night there. AIUI this happens rarely enough that we may not care about the inaccuracy. | ||
** We could also use some kind of probabilistic model with the 'door-open' and 'bell' data | ** We could also use some kind of probabilistic model with the 'door-open' and 'bell' data | ||
=====Location===== | |||
Thinking about possible mounting locations: | |||
* At either end of the entrance way | |||
** '''Good:''' Won't be blocked by coats, won't miscount people hanging coats etc. | |||
** ''Bad:''' Highly likely to misread people opening the door when the bell has rung - will need access to doorbell events and hence require processing off-board. | |||
* In close proximity in the middle of the entrance way | |||
** '''Good:''' Less susceptible to miscounts from people opening the door for others - simpler, count can be process on-board. | |||
** ''Bad:''' May be blocked by coats, may miscount people hanging coats. Use a cowling perhaps? | |||
edits