[piniondna]

I think people think that shooting down ideas makes them sound intelligent and “in the know”, but in reality it just makes you sound rigid and not creative enough to see the merit in a idea.

This seems to be a common attitude on HN, but it’s less than useful. Genuine critical thinking is great... dogmatic cynicism is useless.

[vorpalhex]

I think there are some valid concerns here. Someone running a clicker is already common procedure at some busy places, and it's often a hostess or someone else who is already "doing stuff".

Likewise any sensor is going to open up some questions about the data it collects and it's method of action - what's the error margin?

I think there's arguments for systems like this as well, but it's on you to make them, not just complain about others being skeptical.

[afar]

Accuracy is fundamental. When installed properly, a 99%+ f1 score is achievable.

[pbourke]

First off - this is really neat, especially the focus on privacy and the use of AI at the edge.

It seems like the occupancy limit problem for small rooms is much more challenging than the building-density problem, since a single error could DOS the room.

How do you account for that?

[afar]

Def. We call that the OB1 problem (off-by-one). If either event detection (did something happen) or event classification (entry or entrance) is wrong, you can be off the whole day. To solve that, we have a different approach / non-threshold approach for boolean occupancy. Not implemented here.

[vorpalhex]

What data does the sensor collect? How visible is the data it sends back to the platform?

[afar]

It's a custom sensor in the lidar family. Uses infrared lasers as illumination and generates depth data. Essentially millions of height values. When depth is rendered to be human legible it look looks like greyscale silhouettes (dark grey is far away, lighter gray is nearer). Sensor processes those values on the edge and published +1/-1 and telemetry data (system health).

[_bxg1]

I think people think that criticizing others by over-applying perceived HN tropes makes them sound intelligent and "in the know".

I wasn't shooting it down, I was just expressing skepticism toward the complexity of the solution and opening it up for wider discussion.

[afar]

Skepticism on this stuff is valid. If we're going to distribute large scale infrastructure that measures human movement we ought to be critical of it. So many systems purport to work but don't. Others are way over engineered. And a lot market as if they're sensors when they're really just cameras taking pictures of behavior.

[alkqp10]

It is not creative to count the number of people in a room.

[piniondna]

I’m currently working on a similar proprietary system that is similar to the one described in this article, and I can tell you that there is much more involved here than “counting people in a room”. Claiming someone with a clicker in front of a door is a better solution misses dozens of other use cases where this isn’t at all possible or cost effective...

But you know, everyone on HN is an expert in everything.

[afar]

This. People are weird. They do strange stuff and it's really hard to count accurately.

[afar]

Definitely not creative just really, really hard. Took us nearly half a decade.