I turned my security cameras into an automatic bird identification system
jasontucker.blogThis is a lot more wholesome than my project. I detect birds and automatically spray them with a sprinkler to keep away from pool area.
I guess you can combine it? Identify what the bird was you sprayed away ..
I've been wanting to do something like this to stop cats shitting on my grass for ages, will have a look at this, thanks.
I did exactly this with BirdNet-Go and my Unifi doorbell cam. Unifi exposes an RTSP feed for each camera so it was easy for the tool to just "listen" to the doorbell and start classifying.
I have a spare e-ink display and my next weekend project to follow onto this is to wire it up so it shows some faux "woodcut" images of birds detected, or something like that.
> Unifi exposes an RTSP feed for each camera
Do you mean an RTSP audio only stream separate from the video+audio feed you might ingest to an NVR, or combined audio/video RTSP stream? Most manufacturers of security cameras with ordinary RTSP stream functions support provide both video and audio together. 'Frigate' for instance will auto detect audio stream on a reolink camera and it "just works" in the latest versions of Frigate.
Unifi provides local RTSP streams in different resolutions, birdnet will happily take a rtsp and strip it's audio out for processing (ffmpeg?)
Have you had any difficulty with simultaneously retrieving >1 RTSP stream from the camera at a time, 24x7? Such as full resolution video/audio to a NVR for security purposes and then a second stream to birdnet?
I did something similar with my BirdNET + e-ink screen, it's pulling images from wikipedia, dithering and rendering a summary with PIL.
https://i.imgur.com/5XbM6bb.png
Also if anyone is interested, here is the server for the e-ink screen https://github.com/koryk/inky-impression-server
and here is a MCP for birdnet that I've been using for a bit https://github.com/koryk/birdnetpi-mcp-local-server
Love your eink example! You’ve just sent me on a parts shopping trip :)
I’ve been unhappy with my little lcd board I’ve been using for the same here https://github.com/simonjgreen/OpenObservatory as the contrast is bad. I was considering using one of my trmnl displays, but it isn’t quite the right operating model for the frequency of updates I want.
I've also done basically the same this year, I just use a Raspberry pi + a usb mic. https://github.com/arnegiacomo/fugleramme
Its very popular with friends and family, especially with older people that dont enjoy traditional tech.
The e-ink display with woodcut birds sounds like the perfect final form of this project
just use trmnl it will make it super easy
I like my money to not go towards transphobes
I like my TRMLN it has been very solid.
Btw, Merlin Bird ID app by Cornell University is so good that I got some people interested that weren't into that topic at all.
Merlin's story is very interesting: https://www.birds.cornell.edu/home/the-magic-of-merlin/
The journey to a magical, free bird sound ID app involves some obvious steps (the NSF gave them money), but the amount of timeline offramps is really high. The NSF didn't think this app was educational ("it's just telling them the answer, they don't even have to work for it!"), the funding ran out so they were thinking of charging money, eBird happened to have five years of bird sound recordings they could use, a computer vision guy on the team happened to learn that spectrograms are basically the same as pictures...
And the result is tremendously useful! They get great signal on where birds are, and they're making people so much more interested in birds and nature and science. And I think charging $1 for the app or, shudder, some sort of subscription model might've ruined the whole thing.
Funnily enough I was in the bathroom (that's where I do my most random thinking) just yesterday evening thinking how template matching in computer vision, e.g. https://docs.opencv.org/5.0/py_tutorials/py_imgproc/py_templ... is basically audio signal processing but instead of being temporal it is spatial. Different signals but same principle.
But a warning for novice birders: Merlin's sound ID feature produces a lot of false positives.
For me, mostly a lot of false negatives. I have a Pixel 8, and I have no problems using the microphone normally, but somehow, Merlin requires the bird to be within a couple of meters of me and sing for quite a while before Merlin will even say “hearing a bird”. And of course, you have to be dead silent; if anyone talks or coughs, it will mess up the spectogram badly.
Given that it's colloquially “Shazam for birds” and Shazam is just amazingly resistant to noise, it's a bit disappointing :-)
I'm not sure why but this seems very phone dependent. I can stand next to another person, both running Merlin in silence, and mine will pick up much more than some people's phones. My phone is not particularly new (Zenfone 8).
I think what makes Shazam magically "just work" is that they are searching for the exact embedding of the recorded version of the song - it doesn't work for a cover version, acapella, etc even if it is very similar. (Everyone would want an app that you can hum into and it will ID the song, but I guess it's a very tough problem.)
Merlin is solving the more general problem so makes sense that it's much more finicky and less accurate.
> an app that you can hum into and it will ID the song
YouTube Music and Google Search do OK with these types. Sometimes if I know a song well enough, I will open YT Music, activate the mic search, and sing a few bars, instead of typing the song title.
According to Gemini, SoundHound is also a good app for song-hummers to try.
Merlin got me into birding, and I've found this to be true, at least in some regions, especially if there's lots of background noise.
Unless a species has a really, really unique call or song, I've made it my personal rule to get eyes on it and, if I'm still not convinced, to take a picture and cross reference with iNaturalist and what folks on there think of it.
I've learned to curse the species that differ from others by the sheen of the backs of the males' necks or the angle of a wingbar. Also, gulls that only differ by things like the color of their feet or beaks.
Indeed - background noise will tend to lead to a lot more false positives, but you should use it as a guide rather than inherently trusting results. Same goes for using BirdNET-go and other models, though these do allow you to be very strict with detections and reduce false positives more.
Occasionally I'll see a screenshot of Merlin with, I dunno, a dozen different birds, and in the middle of the list: a catbird. I never have the heart to tell people that they just heard one very creative bird.
You can usually tell, though. Rare birds in the wrong place or time that come up only once are problematic, but if the bird is detected repeatedly there's a better chance. You should also be on the lookout for birds that mimic other birds (like the northern mockingbird and the gray catbird.)
For info, there's a FOSS bird-call app, available on F-Droid, that's pretty decent: WhoBird
Cornell / Merlin / eBird publishes a global species frequency DB indexed by location and date (so, how likely is a species to appear in a place, on a day of the year)... In a project that I was working on, this helped a lot when used to influence the "raw" identification based on appearance alone.
I've not seen this personally, but maybe it's region specific.
Indeed. I use Merlin Bird ID all the time. I found it good across many countries.
Btw the btw Merlin ID and OP's Birdnet uses the same model
I call it Pokemon Go for grown ups. How many do you have in your life list? I finally managed to snag a Tawny Owl last week.
I've got 33. I don't know how that stacks up against other but a large percentage of them came just from my backyard. Just got added a Baltimore Oriole that showed up this week.
I've only been birdwatching since spring and I got 28 species already. Lots of seabirds because I spend a lot of the time at the beach.
I'm up to 71 thanks to the joys of taking it on holiday to other countries (less joy for my family), and occasionally going places just because I know there'll be new birds there.
Personal best for a single session is 23 birds in my back garden over the course of a couple of coffees. I have though spent a fair bit of time making the garden as attractive to different types of bird as possible - mainly through having a variety of different shaped feeders with different feed in. I can recommend the NatureSpy camera feeder too [0] - though I have had to modify it a little to make the food hole smaller otherwise magpies empty the thing in a single day just chucking all the seed on the floor. Dickheads.
[0] https://naturespy.org/collections/wifi-solar-bird-feeder-nes...
I tried that with my Aqara camera. The mic there has no windshield, though; wind noise was terrible. Also I couldn’t get Aqara support to enable higher sampling rates in the firmware than 16kHz; BirdNET expects 48kHz audio samples.
Ended up installing a better microphone attached to a RPi3A+ and using a RaspberyPi 4 which I already owned for hosting BirdNET-Go https://maciejb.me/posts/birdnet-go-setup/
Much better sound quality now!
I built an esp32 with 48khz mic soldered on, feeding rtsp stream to server in living room. Works amazing. Need to build more mics.
I like to know more about your project can you help with the details
How do you transmit the audio once captured?
I just wonder, wouldn't ornithologists be interested in a system in where people voluntarily upload bird photos from their camera, helping them with bird spitting? They do that by hand already, after all. Think something like FlightRadar and crowd-sourced ADB-S info?
Eerie how easy it is to leverage these always on network connected sensors we keep putting everywhere to get precise data profiles
DIY NSA.
Yeah, the bird use case is charming, but it's also a pretty good demonstration of how much information is sitting there waiting to be extracted from sensors that were installed for some completely different purpose.
With the arrival of H5 bird flu on Australian shores this would be an essential citizen science effort to roll these out.
Why wouldn’t Ring integrate this into their cameras or at least provide a “premium” device that includes it? Seems like a marketing no brainer!
Security is all about trade offs and if the public perceives they are getting additional benefits from their devices then the trade off over surveillance becomes less so.
I’m actually surprised Flock hasn’t done it to their cameras already. “Stop cutting down our bird monitoring devices! We are doing good science!” If they integrated actual positive benefits to their actions then society pushes back less
> I got a notification from Home Assistant that a fart was detected in the driveway. My neighbor was walking by my house on his nightly walk and ripped one as he passed by the driveway and the fart was detected.
I'd have to disable notifications for this in my neighbourhood to avoid alert fatigue.
Heads up. I noticed the screenshot of your markdown card has an ASCII block that goes below the baseline. `U+2588` (Full block) tends to do that depending on a lot of things.
I made a change to the markdown card sometime ago that uses only `U+2581` through `U+ 2587` instead to avoid that issue.
It's under a collapsed block here:
https://www.kyleniewiada.org/blog/2025/05/backyard-bird-trac...
Nice! I never thought about using my security cameras but ended up building a regular Birdnet-Pi with a microphone. I took it one step further to make it portable so that I can use it when we hike or travel to new places. Added a little e-ink display to the front and it allows me to see Top 3 for the day, last detected, and total number for the day.
Case I used to make it portable and fit the display https://makerworld.com/en/models/1336154-portable-pi-sdr-cas...
Now imagine those birds are humans and that guy is government. Terrifying.
The documentary 'Listers ' (about two brothers who go all in on birding for a year) on YouTube is so hilarious and got me into birding (and using Merlin) this year. Highly recommend.
Really enjoyed it as well. I watched so many documentaries in college (20-25 years ago) and it really harkens back to a 90s/early00’s style documentary, in a fun way.
Security cameras becoming a 24/7 backyard biodiversity monitor is already great. The fact that the same system eventually detected a neighbor farting in the driveway somehow makes it perfect.
I tried this with Birdnetpi (https://7ml.in/notes/on-to-birdnet/) with Avain Visitors (https://theodore.net/projects/AvianVisitors/) My camera's doesn't give out rtsp unfortunately
Maybe you could try go2rtc[0]? It can ingest multiple stream formats and output them in a different one.
Also has some other nice features, like I use it to ingest one RTSP stream and share that to multiple applications, and to push audio out to my Tapo camera
Scrypted would work
Nice! I've tried to build something similar with Unifi cameras (https://github.com/dewey/birdhomie) and it worked pretty well, the species detection wasn't that accurate but I'll continue on that project in the winter.
I run BirdNET-Go as an app on my Home Assistant i7 M710q. I use the GPU-enabled BirdNET model and Perch V2, and it works swimmingly.
Input is three RTSP streams from various Reolink PoE cameras around our house, and it is pretty cool to be able to find and listen to the birds/frogs that come.
I have a situation with a couple of hundred chimney swifts. I want to set-up cameras to differentiate between individual swifts.
Any advice on how to go about this.
My current plan is to put multiple cameras at the mouth of the chimney opening which is about 42"x42"(1mx1m).
Does this sound realistic to anyone with experience?
There's a growing literature on individual animal identification from sound!
Here's one example: https://github.com/sammlapp/ovenbird-individual-recognition
My impression is that the hardest part is knowing whether or not you're actually doing a good job. For vocal learners (like the ovenbird example linked above), it seems to be pretty easy using embeddings from existing models (like perch or birdnet). For non-learning species (possibly including your swifts), you can use timbre clues to differentiate many individuals, but may not be able to really nail down individual identity.
Have you found a way to identify frogs? I also have a BirdNET (the older -PI, not -Go) setup, but haven't seen a way to get anything other than birds identified.
The full Perch V2 model at https://huggingface.co/tphakala/Perch-v2 can do some frogs and cicadas and such, but it is not very good. It will certainly detect it, whether the species will be right is a whole other question.
The many frogs around my house are identified as black-crowned night heron. I was very excited for a while since that bird is not common where I live.
OHHHH! That explains it. Had not figured out why that false detection kept coming up.
The sound that a frog makes is 'kwak' in Dutch. And that is also the name of this bird which makes a similar sound. Onomatopoeia for the frog predator.
For birds (or animals) sound lovers i suggest Cosmo Sheldrake songs
I just turned my PTZ security camera into a VAR booth for my kid. Lawn (soccer) / Driveway (Floorball) / End. Live view, step back 10s, slowmo, frame step, scrubbing.
GLM 5.3 helped to root my camera so I could get proper endpoints for PTZ and stream. Claude built the api and frontend, hosted on Home Assistant.
I'm thinking of making one of these for my wife as a holiday present: https://theodore.net/projects/AvianVisitors/
I like the idea of doing something with the timestamp of the recording, or highlighting new (or recently unheard) visitors.
Cool project!
Inspired by AvianVisitors [1] I made a similar project [2] with an android app for bird detection using Perch, and then displays the birds detected during the last 24 hours with nice art on a samsung frame tv in "art mode".
If you dont want to repurpose an old android device, my app also supports bird detections from birdnet-go and birdweather. It should be plug and play with this project.
Have a look at [1] https://theodore.net/projects/AvianVisitors/ [2] https://github.com/simenf/birdframe
I don't know how this possibly worked for the northern mockingbird. One full moon I stood and listened to one call continuously for an hour and I couldn't remember hearing the same call twice. Every bird I'd ever heard in person and more mimicked...several car alarms..sirens... Do they even have their own distinctive call?
Merlin identifies them for me
I noticed the linked blog mentions birds and bats. I thought bat chirps required higher sample rates than the microphones normally use. I have an Audiomoth and to set it up for bats you need to use the highest sample rate for proper ID.
I like this project. I have been using security cams around my place to keep track of animals meandering across the property. It's the best use for an outdoor solar-powered webcam if you ask me. You can get a feel for which animal to expect based on time of day or other characteristics. You also recognize those who regularly visit. I have a one-eyed raccoon that has been showing up for almost two years now. It's a female and the last time she visited the monitored fountain she had 5 rambunctious raccoonlets.
Love this project, I did something similar. The next step is building a custom frontend for it that’s exactly how your wife wants!
https://alec.is/posts/building-a-solar-powered-bird-station/
Here is mine: https://birdymusic.com/
I'm also working on a little project that is a walnut frame with a waveshare eink display and esp32 that polls for latest detection and display the picture.
Wow kingfisher, lucky!
Has your observation record reached a steady state, or are you regularly seeing unusual species?
I’m at a very steady state now years into running a BirdNET-GO instance. Disclaimer: I’m a contributor to the project.
I’m a pretty unhinged sorta engineer, so I actually recently created a 24/7 weather TV channel that combines real-time bird alerts, weather radar, timelapses and a sky cam feed (just a UniFi camera mounted on my home’s roof PV).
https://www.youtube.com/live/sAC3o6KW2N0
Watchable from every TV in the house and shows the birds photo and name when it hears one. Whole thing is a single cursed FFMPEG command.
Thanks - this post reminded me to enter some sightings from yesterday into eBird (yes, another Cornell Lab birding app). A pair of rainbow bee eaters that I hadn't seen in the area before.
Came to say birdnet is fantastic but, at least in Australia, it regularly identifies calls with low probability (which are often wrong / skewed for location, but sometimes correct). Meaning you still need some wits about you. That said, it can correctly identify multiple birds in a single chorus which is cool. Just need to keep an eye out for those false positives.
I am imagining a Gary Larson strip about a flock of birds who are so not fond of this.
Xeno, you are my hero https://xeno-canto.org/
Been working on a similar project for doing animal behavioral analysis on cameras setup in a barn. I got YOLO running in real-time on several streams on a RTX4070. Managing the training data and doing DINO->YOLO distillation has me writing my own data management suite that I plan on OSing soon.
Core use-case : push a message every time my dog is eating my shoes.
Relevant: https://www.spoor.ai/
I have this too, I was looking to get more automated call recognition after we spotted a pheasant in my (suburban) back garden. I was going to buy a dedicated mike, but then realised that birdnet go works with any rtsp audio stream.
I do need to tune the false positives though.
> No waiting. No manual recording.
> No cloud services. No API calls.
> No subscription fees. No terms of service changes. No company shutting down the service in two years.
Wild that I could read this article, give DeepSeek about 4 sentences of prompts and have it running on my own homelab and unifi cameras in about 10 minutes.
The future mostly sucks but some parts are pretty cool.
how confident is it in the identification? i imagine sometimes the angle is or resolution is bad and it may detect a bird but not have a lot to go off of to say what kind. does it narrow the list down or just make a guess?
It looks like they are using audio. Even with poor audio on my phone I find that it works very well. Once in a blue moon I'll get an ID I am doubtful of from BirdNet but it's rare in my experience.
but the thing with AI is that it excels in creating things we would not doubt, regardless of the truth. in particular, i find it to be susceptible to avoiding doubt at the expense of truth.
though i would be hopeful for bird audio, as differentiating their calls is something the birds themselves excel at, so it could very well be a great usecase for ai
Related: https://www.birdweather.com/birdnetpi
I really gotta set mine up!
Really cool! The fart detector was a hilarious bonus
Really nice project! Expected a visual ID system, surprised it was using audio. "Flock" would be a great name for the project...oh well!
Incredible! I never realized these models are open, always used them via the app. Project is top also!
Brilliant idea and fantastic project. New use for security cameras. I love it.
Is it possible to run on macOS? I’m guessing docker
What an interesting and fun project. Now I want something similar too.
Super cool, could be plugged into https://www.earthcam.com/ for global bird tracking.
(i have a few https://www.birdweather.com/ devices strewn across North America and Europe because I am time poor and preferred a turnkey solution for those gifted to, but love the DIY efforts! no affiliation!)
Finally a good use for Flock cameras. They're even named appropriately.
How do you like the bird weather device? I’m interested in a more turnkey solution as well
I'm fairly satisfied with it and would recommend it to others who aren't interested in building their own solution. I like supporting the folks who are building it, although I'm unsure what the future looks like for the product. Could enshittify, could turn into Home Assistant Foundation [1] (which I also financially support). Time will tell. That's why I think its important to have open alternatives, similar to how one of the https://www.adsbexchange.com/ operators went rouge [2], sold to private equity, and others have filled the gap with new ADS-B network solutions.
[1] https://www.openhomefoundation.org/
[2] https://news.ycombinator.com/item?id=45582907 (citations)
I'm pretty sure you can do this with Frigate as well.
Finally, ATC for my garden
I’ve been working on a similar project for the last few weeks in spare time.
I’m using a AudioMoth USB mic so I can capture extremely high sample rate and also ultrasonic for bat detections.
https://github.com/simonjgreen/OpenObservatory
Disclaimer: I’m also using this to see how far I can push supervised pure AI coding before it turns to mega slop, so know that before you dive in with the disparaging comments :D
just don't use it to catch a congressman being murdered over a privacy bill.
I love this, much better than AngryBirds. Truly an amazing idea!
Little did he know in 2026 you can feed that cartoon into AI and it will build you that app
flock for family tracking and block for bird tracking may be !
can i turn this into a doorbell?
I got a little bit into birds when I met the Merlin app. And I have thought about making a bird identification station, but I'm under the impression mostly the same species of birds visit where I live. I may be wrong though.
Humans who hate being spied on by the government and FacebookSpyGlasses, now spy on birds. We begin to understand how Skynet won this war ...
This would be more interesting with video rather than audio, no? I guess it depends where your security cameras are. Are there options for that as well?
110 detections over 7 days? Here in Sydney I would expect >110 detections per day!
I've done essentially the same thing before (using my existing Go2RTC and Frigate setup) but the challenge I ran into is that the microphones on my cameras just aren't very good.
You can adjust which detections are accepted based on confidence level, so it might be that the settings are very strict.
Two rainbow lorikeets just had sex 2m from my breakfast table. I think there's a substantive distinction in avian fauna density.
Hell yeah a birdie over thirty, with a splash of tech!
(you either go the path of a burner or a birdie, I don't make the rules)
Alternative title: "My neighbour farted in my driveway, a technical overview"
I'm kinda disappointed there was no relevant xkcd linked in the article.
I love AI. Thank you for such great software, anybody can do it now! Just like making videos, songs, pictures, stories, etc. What a great time to be alive! Oh, and F China for trying to sabotage our data center buildouts by leveraging useful idiots.
Ot to rain on your parade. But I made videos, songs and pictures, wrote stories back in ca. 2006 when I was 16 and read my first AI book. Without AI.
I see AI as a useful tool, but doing art with it is extremely bland compared to the real thing. I can't eben begin to describe what people who let the machine do the art miss out on.
ha, now imagine some hacker changing all the Flock firmware nationwide to do bird identification too
would have been a great Mr. Robot episode
My cat wants to know who/where does one ask to request to have a specific bird located?
Sorry, no luck tracking down your ex-girlfriend, but we do have a line on an ivory-billed woodpecker.
Lol, nice. Does an audio recording of an ivory-billed exist?
Apparently, yes: https://birdsoftheworld.org/bow/species/ivbwoo/cur/multimedi...
Flock would live up to its name.
In the non-fucked up timeline where Hilary won in 2016, Flock cameras is a nationwide network of automatic bird identification cameras to track bird population and migration.
I get jealous of people that have the luxury of time to do things like this
My setup took maybe ~4-8h of initial work. All with the help of Codex: code, configuration, even figuring out which equipment to buy.
I just used AI(antigravity with gemini 3.6 flash, but i'm sure many others would work) to implement this and integrate it with my security cameras after reading the blog post 26 minutes ago. I suspect the author did the same thing. I also had it steal the idea from the AvianVisitors link in this thread and it displays a generated collage of the recently detected birds.