> 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.
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.
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.
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
I don’t know who designed this, but they were a master of the black art of Radio Frequency waveguide engineering. I am impressed. The PCB, itself, is a major component. Not only for the patch antennas but also several RF filters, the local oscillator, and the mixer are all largely made from peculiarly-shaped PCB tracks. Apart from the PCB, there are only five “components" on the board. Five passive components to implement a Doppler radar module. C’mon. You have to be impressed by that!
A little tangential, but are these things safe for humans? I have a couple of LD2410 devices and I’d like to use one of them with ESPHome in the bedroom. I did some research and they seem to be very low power and safe, but you know, before sleeping with a radar pointing at us all night long, I’m looking for as much feedback as possible.
Non-ionizing radio waves are generally safe for humans.
The only mechanism besides ionization that could harm humans is through the transfer of lots of power into the human body (think soldiers keeping themselves warm by stepping in front of a radar emitter).
So let's try to do a ballpark estimate of how much that could matter.
I haven't found (from a quick search) any data regarding the transmission power, but the data sheet at https://fcc.report/FCC-ID/2AD56HLK-LD2410B-P/6620025.pdf says the average current consumption is 79mA at 5V, which means it uses 0.4W.
How much of that is actually transmitted? I'd guess 10%-50% (likely much less, but let's go with this more conservative estimate, from a safety perspective), so now we're in the range of 40mW to 200mW.
If you absorb 1/4th of that (again, somewhat conservative estimate; you'll likely also reflect some, and most of it is going to pass you), we're at 10mW to 50mW extra power that is absorbed by your tissue.
Again, this is a super high (and thus for our purpose, conservative) estimate. Somebody else in this thread mentioned microwatts being absorbed, which sounds much more plausible.
To put this into context, the base level of power that an adult human operates on at rest is about 100W. This is a factor of 500 to 2500 more than the power absorbed from our millimeter wave radar. Unless all the absorption happens by a very specific and sensitive part of the body (like your eyes or so), this should just be background noise.
If you want another perspective, you could try to compare it with whatever radiation (both RF and heat) that your phone emits, that you likely carry in your pocket for hours at a time.
> The only mechanism besides ionization that could harm humans [is heat]
This claim is, IMO, too strong given available evidence.
There are many chemical interactions with characteristic energies well below 1eV, or any reasonable threshold for "ionizing". Photons can couple with these interactions without ionizing anything. 4GHz range is probably fine, because the per photon energy is a small fraction of a mEv, but even then I would not rule out the possibility of multiple photons coupling to a structure without the imparted energy immediately being dispersed as heat.
Any time you have EM with low entropy/etendue, it is always theoretically possible for interactions to occur outside of the thermal regime.
Some phones have a SAR of almost 2W/kg, compared to that milliwatts of 10GHz RF are nothing. Not to mention that with standard energy dissipation formula of E~R^(-2) you're getting into microwatts at any practical distance from the antenna.
I have these all around the house, but not in the bedrooms. I use weight sensors to detect that someone is in bed and traditional PIR for motion in bedrooms.
Probably overly careful, but I didn't want to point a radar at my sleeping kids (and myself) for 12 hours per day. Similar for the WiFi access point upstairs, it's only in the hallway and not at maximum power.
> Probably overly careful, but I didn't want to point a radar at my sleeping kids (and myself) for 12 hours per day.
While I understand the sentiment. It's very very unlikely to be dangerous and there are plenty of other environmental dangers.
The biggest being the sun. But the most common man-made ones are probably auditory. Like toys and TVs being too loud or high-frequency sounds blasted from speakers in malls or under bridges to avoid "loitering."
I agree with you, especially regarding children and anyone who hasn’t explicitly made this choice, which is why I asked the question. The only thing is, I suspect we get scared by certain words, like “radar” and “microwaves”, and then we might spend all day with our heads next to a Wi-Fi router or a phone constantly downloading files on 4G.
For example: maybe the ESP32 transmitting the bed weight exposes us to more danger than the radar sensor (that can also be placed very far from the bed)? Maybe with our smartphones charging on the nightstand too.
I’m not a big fan of fear-based, illogical decisions. But, again, I understand perfectly.
Readit News
> 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...
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.
1. https://github.com/Marsrocky/Awesome-WiFi-CSI-Sensing#vital-...
2. https://arxiv.org/abs/1908.05108
NIST, "Monitoring Respiratory Motion with Wi-Fi CSI" (2022), https://www.nist.gov/news-events/news/2022/12/wi-fi-could-he... & https://doi.org/10.1109/ACCESS.2022.3230003
Google: Nest Hub sleep sensing for one person, with Fitbit Premium, https://www.techradar.com/health-fitness/how-to-track-your-s...
The ESP32 can detect the difference between a cannibal and a vegan?
That's impressive.
— kool aid man
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
Deleted Comment
The only mechanism besides ionization that could harm humans is through the transfer of lots of power into the human body (think soldiers keeping themselves warm by stepping in front of a radar emitter).
So let's try to do a ballpark estimate of how much that could matter.
I haven't found (from a quick search) any data regarding the transmission power, but the data sheet at https://fcc.report/FCC-ID/2AD56HLK-LD2410B-P/6620025.pdf says the average current consumption is 79mA at 5V, which means it uses 0.4W.
How much of that is actually transmitted? I'd guess 10%-50% (likely much less, but let's go with this more conservative estimate, from a safety perspective), so now we're in the range of 40mW to 200mW.
If you absorb 1/4th of that (again, somewhat conservative estimate; you'll likely also reflect some, and most of it is going to pass you), we're at 10mW to 50mW extra power that is absorbed by your tissue.
Again, this is a super high (and thus for our purpose, conservative) estimate. Somebody else in this thread mentioned microwatts being absorbed, which sounds much more plausible.
To put this into context, the base level of power that an adult human operates on at rest is about 100W. This is a factor of 500 to 2500 more than the power absorbed from our millimeter wave radar. Unless all the absorption happens by a very specific and sensitive part of the body (like your eyes or so), this should just be background noise.
If you want another perspective, you could try to compare it with whatever radiation (both RF and heat) that your phone emits, that you likely carry in your pocket for hours at a time.
This claim is, IMO, too strong given available evidence.
There are many chemical interactions with characteristic energies well below 1eV, or any reasonable threshold for "ionizing". Photons can couple with these interactions without ionizing anything. 4GHz range is probably fine, because the per photon energy is a small fraction of a mEv, but even then I would not rule out the possibility of multiple photons coupling to a structure without the imparted energy immediately being dispersed as heat.
Any time you have EM with low entropy/etendue, it is always theoretically possible for interactions to occur outside of the thermal regime.
Holy, did people actually do this? A quick search yielded no results. Not sure if thankful or not.
Probably overly careful, but I didn't want to point a radar at my sleeping kids (and myself) for 12 hours per day. Similar for the WiFi access point upstairs, it's only in the hallway and not at maximum power.
While I understand the sentiment. It's very very unlikely to be dangerous and there are plenty of other environmental dangers.
The biggest being the sun. But the most common man-made ones are probably auditory. Like toys and TVs being too loud or high-frequency sounds blasted from speakers in malls or under bridges to avoid "loitering."
For example: maybe the ESP32 transmitting the bed weight exposes us to more danger than the radar sensor (that can also be placed very far from the bed)? Maybe with our smartphones charging on the nightstand too.
I’m not a big fan of fear-based, illogical decisions. But, again, I understand perfectly.
https://www.microwavenews.com
Priced between 11 and 20 bucks they are fairly feature rich...
If you want to roll your own check out what the folks over at ESP home have going on (google esp home mm wave).
That said, it doesn't work very well for me when sitting still 4-5m away, it thinks I've left.