Through-wall 2.4Ghz Wi-Fi CSI radar can be done with $20 ESP32 boards, https://github.com/Marsrocky/Awesome-WiFi-CSI-Sensing & https://www.cnx-software.com/2022/08/08/esp-wifi-csi-detects...
> Espressif claims it can also capture subtle movements caused by small movements such as breathing and chewing of people or animals in a static environment.. works with all ESP32 series microcontrollers including ESP32, ESP32-S2, and ESP32-C3, and does not require any changes to the hardware
2024 AI/NPU laptops with Wi-Fi 7 from Intel and Qualcomm can combine RF radar and on-device inference to identify human activity.
Related:
DIY Radio Telescope: Building a Camera That Can See WiFi (2019) https://www.youtube.com/watch?v=g3LT_b6K0Mc
Wi-Fi devices set to become object sensors by 2024 via IEEE 802.11bf standard (2021), https://news.ycombinator.com/item?id=40458766
How automotive radar measures the velocity of objects (2024) https://news.ycombinator.com/item?id=40768959
How Wi-Fi sensing of movement became usable (2024) https://www.technologyreview.com/2024/02/27/1088154/wifi-sen...
> chewing of people or animals
The ESP32 can detect the difference between a cannibal and a vegan?
That's impressive.
How can you tell someone is a vegan? Don't worry, this 1$ radar motion sensor can tell you.
I think you could go cheaper. A sound detection sensor is a bit cheaper, and it just needs to detect the word 'vegan.'
Strangely enough I've heard far more people make this "joke" than actual vegans speaking up. Even when living in LA.
The issue with this joke is that it's 100% confirmation bias. You know that all the vegans tell you they're vegan because you don't know about the ones that didn't.
I think it's also survivorship bias. All the people who tell you they're vegan being vegan does not mean that all the people who are vegan will tell you they're vegan, just like all the people who won the lottery probably having bought lots of tickets does not mean that buying lots of tickets will win you the lottery.
That's what I meant, maybe I used the wrong bias name.
I know this under "selection bias", so now we have three contenders.
Still, I'm not sure if it's a big factor. You likely know who is vegan in your circles, because veganism is unusual enough to be a good topic for gossip, you can easily see it when sharing a meal with someone, and it's also something you'd like to know when inviting people over, if you want to be a good host. So I think a more relevant estimate would be number of vegans you know vs. how many of them announce their veganism at the earliest opportunity.
I believe survivorship bias is a specific type of selection bias.
Confirmation bias typically refers to accepting very little evidence or rejecting disproofs. Survivorship bias is the one where you forget to account for the non-survivors of a particular selection criteria.
There are people that I discovered were vegans when discussing what to eat. And there are people that loudly announced they'd become vegans without any context.
The later group used to be larger, but I don't remember anybody doing that recently.
That's the trick, you invert the logic. If you hear the word vegan, assume the person saying it is not.
“Practically everyone knows what veganism is, but vegans are actually a very small minority.
There are more Americans with gambling addictions than there are people committed to vegan diets!”
Chart: https://x.com/cremieuxrecueil/status/1805367282270433791?s=4...
It made more sense 20 years ago when it was more generally true. Veganism seems to have spread beyond the merely self-righteous now. It's a very old joke (possibly from the 90?s).
Come on, that's simple, just use voice recognition since the vegan won't stop telling the sensor about it.
Wifi sensing is interesting, but you can combine a $3 ESP chip with one of these for a much easier project at lower cost: https://www.dfrobot.com/product-2795.html
I use those for presence detection in my house. 3D print a small case and for < $20 you have highly accurate presence detection that also works when sitting still. Ideal for automatic light and climate control.
My problem with similar sensors is that they don't work very well if you're sitting still around 3m away. Maybe my sensor isn't great, but when I'm sitting still at the computer, it frequently thinks I'm not there any more, which ruins any benefit.
A hack is to put a sensor on the chair
Hmmmmm that's not a bad idea, I'll have to see how to do that, though. I don't want cables restricting me.
If your fine with zigbee, I could see having one of these aqara door sensors in the cushion of the seat, triggering to closed when you sit on it: https://cloudfree.shop/product/aqara-door-and-window-sensors...
Seems like it'd be finicky though.
Zigbee is great, but my chair has a mesh :/ I'll see if I can print something below, so that the sensor is activated, but yes, it does seem that it would be pretty finicky...
I solved the issue by linking my lights to a switch that I turn on when needed. It has worked very well so far, with no false detection at all!
plz let us know how it goes after sufficient testi g
Pairing them with PIR detection should help to also detect stationary warm objects.
I did pair them, unfortunately PIR sensors are even worse at detecting stationary objects (less sensitive to body micromovements).
It's difficult to find good PIR sensors though. The commonly found cheap modules don't include a thermistor to compensate for room temperature. Finding one with analog output or continuous detection is even more difficult, most detect changes.
There are some that detect heartbeat, I guess those might work. But those are mmWave, not just cheap 2.4GHz radars or PIR.
I've got LD2410B, which are mmWave, so they should detect heartbeat (and do), but not from more than 2-3m away.
The “Vital Sign Detection & Healthcare”[1] section is very interesting, thank you! I am looking for a way to measure the heartbeat of a single person in a completely non-invasive manner (so without contact) and I see that it can be done with Wi-Fi (2019 Paper [2]). However, I’ve noticed that there are a lot of methods (video analysis, thermal camera, etc.), but they are hard to find as ready-made products at a reasonable price. The simplest solution is under-mattress sleep trackers, but unfortunately they are not an option for me.
1. https://github.com/Marsrocky/Awesome-WiFi-CSI-Sensing#vital-...
2. https://arxiv.org/abs/1908.05108
Interesting. I'd be interested in a breathing sensor that can work on someone working at a computer.
I’m sure it can be done with a normal camera and enough light, especially with the advancement of AI technologies in recent years. I haven’t had time to experiment, but if you have an iPhone, you can try this app [1] I installed yesterday to study its feasibility.
On the homepage, there is a video [2] explaining more as well, and their paper [3].
1. https://www.rouast.com/vitallens/
2. https://www.youtube.com/watch?v=_0HHjovI8hc
3. https://arxiv.org/pdf/2312.06892
These $1 boards also work through walls (I tried this).
I always go through walls.
— kool aid man
The gesture recognition sounds incredibly interesting. I work with vision based band tracking, and performance really isn't good enough for my application.
I wonder what kind of resolution you can reasonably achieve? Is it good enough to detect finger pose?
Aside: is there a way around IEEE paywall? I'd really love to read some of these papers
Great links! I recall seeing somewhere that AMEX was investing in WiFi object detection…can’t remember exactly for what or how…
You can also use a single ESP and your WiFi AP as a source of packets.