this post was submitted on 05 Dec 2023
17 points (87.0% liked)

No Stupid Questions

35409 readers
977 users here now

No such thing. Ask away!

!nostupidquestions is a community dedicated to being helpful and answering each others' questions on various topics.

The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:

Rules (interactive)


Rule 1- All posts must be legitimate questions. All post titles must include a question.

All posts must be legitimate questions, and all post titles must include a question. Questions that are joke or trolling questions, memes, song lyrics as title, etc. are not allowed here. See Rule 6 for all exceptions.



Rule 2- Your question subject cannot be illegal or NSFW material.

Your question subject cannot be illegal or NSFW material. You will be warned first, banned second.



Rule 3- Do not seek mental, medical and professional help here.

Do not seek mental, medical and professional help here. Breaking this rule will not get you or your post removed, but it will put you at risk, and possibly in danger.



Rule 4- No self promotion or upvote-farming of any kind.

That's it.



Rule 5- No baiting or sealioning or promoting an agenda.

Questions which, instead of being of an innocuous nature, are specifically intended (based on reports and in the opinion of our crack moderation team) to bait users into ideological wars on charged political topics will be removed and the authors warned - or banned - depending on severity.



Rule 6- Regarding META posts and joke questions.

Provided it is about the community itself, you may post non-question posts using the [META] tag on your post title.

On fridays, you are allowed to post meme and troll questions, on the condition that it's in text format only, and conforms with our other rules. These posts MUST include the [NSQ Friday] tag in their title.

If you post a serious question on friday and are looking only for legitimate answers, then please include the [Serious] tag on your post. Irrelevant replies will then be removed by moderators.



Rule 7- You can't intentionally annoy, mock, or harass other members.

If you intentionally annoy, mock, harass, or discriminate against any individual member, you will be removed.

Likewise, if you are a member, sympathiser or a resemblant of a movement that is known to largely hate, mock, discriminate against, and/or want to take lives of a group of people, and you were provably vocal about your hate, then you will be banned on sight.



Rule 8- All comments should try to stay relevant to their parent content.



Rule 9- Reposts from other platforms are not allowed.

Let everyone have their own content.



Rule 10- Majority of bots aren't allowed to participate here.



Credits

Our breathtaking icon was bestowed upon us by @Cevilia!

The greatest banner of all time: by @TheOneWithTheHair!

founded 1 year ago
MODERATORS
 

In Star Wars Rebels, there was an E-XD-series infiltrator droid that could quickly take inventory of everything in a rebel warehouse. With the advanced object recognition capabilities of modern AI, it’s only a matter of time before an app for Android can accurately and rapidly identify and store objects in real-time from video capture. This could be similar to a home inventory app where users only need to capture video and move around the house instead of taking pictures and labeling items. When do you think will there be an Android app for real-time visual inventory?

top 10 comments
sorted by: hot top controversial new old
[–] ryathal@sh.itjust.works 6 points 10 months ago

This sort of exists. Amazon had unmanned convenience stores that used cameras to track purchases. Sam's club had an inventory robot the last time I was there. It's not star wars level tracking, but it's somewhat close.

[–] Mamertine@lemmy.world 3 points 10 months ago

You don't want video capture. It'll use RFID chips.

It can happen as soon as there's a use for it.

[–] edgemaster72@lemmy.world 3 points 10 months ago

Have you posted about this before? I swear I've seen someone ask this question before. Anyway, my guess would be as soon as someone can figure out how to monetize and enshittify it.

[–] linearchaos@lemmy.world 2 points 10 months ago (1 children)

So, this is totally doable right now. The resolution and frame rates are there, AI being able to look at individual items on a screen and figure out what's in the picture is already a mostly solved problem. It would probably make the most sense to turn the space into a 3D representation so you don't accidentally double catch an item from a parallax error. It might not be able to tell the day TV is a frame versus a q LED, but it'll be able to tell that it's a 75-in TV and they can probably assign an average price to it.

The hard part is the horsepower required to do the AI work. It would need to be trained on pictures and sizes everything and of the things that are too complicated it would prompt you for what this item actually is. Lots of CPU, lots of GPU and would most likely need to head off to a beefy server farm where would need to spend a non-trivial amount of time sorting your stuff out.

Of course the real loser in all this is your insurance company. The less stuff you have on your inventory less stuff they pay out. To convince them too create the training data and host or pay for hosting the engines, There would have to be some clear advantage in it for them.

[–] NeoNachtwaechter@lemmy.world 2 points 10 months ago (1 children)

The hard part is the horsepower

The hard part is dealing with the numerous errors. Things that were accidentally not visible at that moment, that bottle with the label turned the other way etc.

Try and convince your bookkeeping department why your new and fancy inventory is only 93% complete when they are asking for 100% completeness and accuracy, like they have done the last 100 years :-)

[–] linearchaos@lemmy.world 0 points 10 months ago* (last edited 10 months ago) (1 children)

Volumetric likeness would make it pretty easy too generate a report of likely false positives., 3D spacial pictures of each individual item detected. 3D special pictures of items not detected.

The reports generated out of it would make it incredibly easy for human to adjust as long as the atoms weren't tucked away in a box or something.

Honestly for say fire purposes it's going to be able to detect your fridge, your oven, your TVs, your sound system your computers mostly. If they're off by a $10 drinking thermos or something they're not really going to care

[–] NeoNachtwaechter@lemmy.world 1 points 10 months ago (1 children)

Volumetric likeness

Let me guess: you are not living in a country where 99.5% of all beer bottles of all brands look the same (except the label) :-)

In addition, you seem to understand the term 'inventory' in a very different way...

[–] linearchaos@lemmy.world 1 points 10 months ago

Tell me, did you miss OP's actual post "This could be similar to a home inventory app where users only need to capture video and move around the house instead of taking pictures and labeling items. When do you think will there be an Android app for real-time visual inventory?"

Or are you just moving the goal posts to insult me?

[–] Num10ck@lemmy.world 2 points 10 months ago

our domestic robots will be awesome at keeping an eye on the top most lost items around the house. the hardware and software of the scanning and identifying exist now. people will complain that it makes them lazier and more stupid, and they will be right.

[–] rufus@discuss.tchncs.de 1 points 10 months ago* (last edited 10 months ago)

I think so, too. Object recognition is something that's already available. But it's probably not possible to determine for example the brand and model of your computer or television. Or how many forks are inside of your drawer.

That is without you picking every single item up and doing close-ups.

And you'd need to open all drawers, cupboards, boxes and your wardrobe anyways. And show it things that are buried beneath other stuff. Maybe even spread them out. Especially things that are hard to recognize in their stored form. Like folded pieces of clothing.