Has anyone else experimented with iNaturalist in an Arduino or Raspberry Pi project?
If you haven’t heard of Arduino: Arduino is an open source electronics platform that provides a great way to learn about electronics and microcontroller programming. It’s accessible and really fun. There are many opportunities to create cool nature related projects with Arduino so I encourage checking it out if you have time!
Awesome, this looks great!
I do a bunch of Arduino stuff and have done some experiments with the iNat API, but not had chance to use the two together yet. This summer I have a project with pollinators which I’m thinking of using Raspberry Pi & PyNaturalist for, but we’ll see…
Maybe I can try and hook this up myself at some point too. Could be nice to attempt to make a LoRa version with an Esp32 or something that you could stick out in the middle of nowhere.
Thanks! Raspberry Pi pollinator project sounds cool, hope you get round to it. I’d be interested to know what that involves.
I love the idea of making a remote, power saving display. You could wire it into an information board in the hills somewhere and hikers could get a constantly updating feed of the species observed in that area.
Exactly :) could be great
I guess most places are anyway covered by a 3G signal in UK at least (?), that you could tap into with your own phone to figure this stuff out, but for a national park or something to advertise to hikers that these species are around them ( and that iNaturalist is a good place to learn more about them), a LoRa setup might be really nice.
I guess it would need some images though too ideally. Most hikers won´t know random latin binomials! So maybe it could also include photos of the species with some sort of eInk setup like this. Looks like you can grab photos from the iNaturalist API at least(?) and then would have to automate this conversion too. So maybe a lot of work haha, but could be a nice project. Maybe iNat will sponsor ;)
That eInk display is so cool, thanks for sharing. It would definitely suit this sort of project.
I agree that having images would make the project better. The problem would be downloading and decoding images from the iNat API with the limited memory capacity on an Arduino. I think the memory is too low on a Arduino board to decode images from jpeg or png to bmp on the fly. Downloading an image would also take a long time, especially with limited connectivity. There might be some clever ways to get around this, like storing a hundred or so reference bmp images on an SD card and indexing the species name returned from the iNat API call against this database. The image might not match the species exactly, but could give an idea of what kind of organism has been identified.
I love this kind of thing, so i’ll keep toying with some ideas when I have time. Of course if you get around to wiring something up please keep in touch about how you get on!
True. Maybe a Raspberry Pi setup might work better in that regard.
Otherwise I guess most of the heavy lifting could be run somehow in the background on an actual computer then just pinged out to the Arduino (?)
But yes, will let you know if I play around with similar setups this summer!
Really cool project. I have been really impressed by BirdNET (https://birdnet.cornell.edu) which uses machine learning to identify bird calls. There is an API in development so would theoretically be possible to build a remote bird species identifier using a raspberry Pi.
