For those of us less technical, wouldn't any face covering impede facial recognition? Hat and muzzle leave just your eyes. Plus shades, i don't see how facial recognition could work.
The newer types focus on measuring the eyes, distance between them, angles. Probably even ears, head size. I bet they can identify people on just their gait now.
We can’t be thaaat unique to be identified by gait. Now everyone’s iris however is unique like a fingerprint. I’m guessing that’s how they do the recognition. Maybe sunglasses super dark ones
Studies of sex offenders and serial killers revealed they sometimes pick their targets based on their gait as well. They can pick up on how vulnerable somebody is to assault just by watching them walk.
Psychopathy and Victim Selection: The Use of Gait as a Cue to Vulnerability
You're not wrong, outside of government scale there are not really many use cases.
I read the link, and one thing worth noting is that LSTM systems are 'deprecated' in terms of AI, the shift is to 'transformer' configurations because they are better able to determine context, where LSTMs have an issue where the 'forget' gates can easily 'learn' the wrong things. Consider, if you use a smartphone how the spellchecker eventually starts using common typos as the correct spelling?
Before I got lasik, when I didn't wear glasses I would recognize people by their gait. From how your arms move, to your shoulders, how stiff you are, how much you rotate your torso, length of your steps, fluidity of movement, stiffness of shoulders, tendency to be a ground-looker or facing ahead, etc.
It depends. If the AI was trained on maskless faces, then the coverings blocks the data it needs.
Add in masked and unmasked photos in the training set and the same AI would be able to learn to do with the missing data.
U/Baconofhope is mostly correct, except that these are separate systems. Like the vector distance between features is a distinct AI from one that looks for "features" of eyes, nose, mouth, etc.
Where AI IDing people from gait were made for drones that only see people from a top-down view.
You mean what we taught it, upload photos of your self yay. Now lets play upload photos of yourself as a child and we will show you what you look like when you're older(facebook did this to get your child photos to gage child + current age changes to train it). People fed the machine. Just like the captcha select photos with xyz or w/o xyz to show you arent a robot, we are teaching the borg.
Correct, and their rationale makes sense... because to train AI systems you need exponential amounts of data for it to learn, and why bother maintaining terrabytes of data in a database when you can create a format for people to send training data as a stream.
A common misconception with AI is that people only 'program' the 'structure' and then is just a matter of feeding it data until it starts generating accurate results. That's why AI often ends up racist, or has 'errors' like misgendering trannies.
For those of us less technical, wouldn't any face covering impede facial recognition? Hat and muzzle leave just your eyes. Plus shades, i don't see how facial recognition could work.
The newer types focus on measuring the eyes, distance between them, angles. Probably even ears, head size. I bet they can identify people on just their gait now.
That was in the news a few years back, and it was foreshadowed like 20 years ago in an episode of "Ghost in the Shell: Standalone Complex".
We can’t be thaaat unique to be identified by gait. Now everyone’s iris however is unique like a fingerprint. I’m guessing that’s how they do the recognition. Maybe sunglasses super dark ones
Everybody has their own unique gait. AI these days can even detect your mood based on your gait.
https://yellrobot.com/gait-recognition-ai-can-identify-mood-by-walk/
Studies of sex offenders and serial killers revealed they sometimes pick their targets based on their gait as well. They can pick up on how vulnerable somebody is to assault just by watching them walk.
Psychopathy and Victim Selection: The Use of Gait as a Cue to Vulnerability
https://journals.sagepub.com/doi/abs/10.1177/0886260512475315
Epic, like the lion looking for tell tell signs in the bounce of the gazelle.
We use to joke, " don't look at me mister lion (cough cough) look how high I can jum, (cough cough) jump...
It's amazing how primal some still are. Like your psyche knows what your brain forgot.
Great. I was hoping y’all would mention the gait fingerprint.
They’ve had it for at least 3 years publicly.
https://m.youtube.com/watch?v=R46cX0AjzT4
You're not wrong, outside of government scale there are not really many use cases.
I read the link, and one thing worth noting is that LSTM systems are 'deprecated' in terms of AI, the shift is to 'transformer' configurations because they are better able to determine context, where LSTMs have an issue where the 'forget' gates can easily 'learn' the wrong things. Consider, if you use a smartphone how the spellchecker eventually starts using common typos as the correct spelling?
Before I got lasik, when I didn't wear glasses I would recognize people by their gait. From how your arms move, to your shoulders, how stiff you are, how much you rotate your torso, length of your steps, fluidity of movement, stiffness of shoulders, tendency to be a ground-looker or facing ahead, etc.
It depends. If the AI was trained on maskless faces, then the coverings blocks the data it needs.
Add in masked and unmasked photos in the training set and the same AI would be able to learn to do with the missing data.
U/Baconofhope is mostly correct, except that these are separate systems. Like the vector distance between features is a distinct AI from one that looks for "features" of eyes, nose, mouth, etc.
Where AI IDing people from gait were made for drones that only see people from a top-down view.
You mean what we taught it, upload photos of your self yay. Now lets play upload photos of yourself as a child and we will show you what you look like when you're older(facebook did this to get your child photos to gage child + current age changes to train it). People fed the machine. Just like the captcha select photos with xyz or w/o xyz to show you arent a robot, we are teaching the borg.
Correct, and their rationale makes sense... because to train AI systems you need exponential amounts of data for it to learn, and why bother maintaining terrabytes of data in a database when you can create a format for people to send training data as a stream.
A common misconception with AI is that people only 'program' the 'structure' and then is just a matter of feeding it data until it starts generating accurate results. That's why AI often ends up racist, or has 'errors' like misgendering trannies.
Short answer is most likely no, synthetic fabrics can be seen thru when a camera's "ir" filter has been removed...
Good point, a mylar Balaclava maybe ?
Suffocate much lol
It would be warm, but cut like a skl mask breathing shouldn't be the problem.
The IR is something new to think about.
https://arstechnica.com/features/2020/04/some-shirts-hide-you-from-cameras-but-will-anyone-wear-them/
Check out this article - sometimes your clothes can be used to hide you in plain sight.
Cool, tks