Hello Akiba, we are expanding Sparrow to 4G cameras and other devices through a web interfaces called sparrow studio. So if a place has gsm, there is no need for any Sparrow devices now. All can be directly connected to Sparrow Studio. Sparrow Studio can be hosted anywhere you want. 100% free of charge, open, no data embargo, and users own everything. We are currently updating our repo to reflect this. Please keep an eye on our Linkedin page for updates. Thanks! 

Sounds good. Thanks for the update. 
 

Hello Kim, as I replied to Akiba, we are expanding Sparrow to 4G cameras and other devices through a web interfaces called sparrow studio. So if a place has gsm, there is no need for any Sparrow devices now. All can be directly connected to Sparrow Studio. Sparrow Studio can be hosted anywhere you want. 100% free of charge, open, no data embargo, and users own everything, from devices to data. We are currently updating our repo to reflect this. Please keep an eye on our Linkedin page for updates. I will also write a new post in Wildlabs for our Sparrow updates. 

Hey I'm with you on the more power on the edge for greater gains 👍

I mentioned starlink because if you are okay with starlink then you are absolutely okay with 4G I would expect. There's quite a lot of hesitance to take this route, I'm just trying to understand how the thinking about this works. Of course, we want to have everything all at once on tiny platforms. However, in 2026 we can't have it all yet. Even the Jetson platform is using 4nm chip technology, which results in very low power. The carrier boards would use quite a bit more.  But making 4nm chips is very expensive, so the reality is if you want to have more effective models you have to address higher power.

And I personally think more effective models really is the way to go. And I say this with having experience in working with all of the models since yolov3 from 2019. So there's a reason for my perspective. So we are in the same space :-)

These are very helpful information, Kim. Also, we are moving away from Jetson Nano to Raspberry Pi 5 and Pi zeros. We have made a dedicated inference engine for these devices. Now, we can run megadetectorv6 (Yolov11 models) on the pi zero, and two Resnet18 models concurrently on the pi zero. I am specifically mentioning the pi zero here because it is the lowest level hardware we are working with, and it only cost ~20 usd. With two resnet18 and 4 threads, the power consumption is around 4-5W. If we are only using 2 threads, it is 2.8W. These data make the application of these lower end chips very feasible in the field. We have recently put a pi zero 2W sparrow on a bouy with gsm. the average power consumption with all sensors and modem together is around 7-9W. In terms of Pi 5, except for transformer based models, we can run most of the CNN models with a efficient power load.

Zhongqui, thank you for such a detailed and thoughtful response. What a impressive toolset! The local model harness especially is especially neat, and so cool to see the openess of your platform. Congratulations on such a great project.

Do you have a place dedicated to talking about success stores? I'd like to read more! 

In particular be interested to hear if there has been any use cases or interest for catching deforestation, like WCSs' project in Guatemala. (Or maybe that is using sparrow?)

As for the tooling question: I wanted to see if anyone in the community had thoughts they wanted to share on their experience with Sparrow Studio. I was just generally very curious about the interface, it looks amazingly versatile from those screenshots. 

Given your goals of openess, to what degree is parts of the software extensible? I'm thinking for example about how multi-microphone meshes are being used to track locations of sound signatures. It's a bit of a daunting idea for a plugin but the example is to emphasize I doubt the platform supports that kind of data analysis, but maybe someone (maybe me even) would be interested in working on it.

That would be an incredible addition to Sparrow Studio! You are free to fork the repo and add to it, and through a pull request we can even fold it into the one we're developing. 

@carterjandrew These are really good questions. For now, we do not have an independent website for Sparrow. The Linkedin page in my previous post is the best place for now. That is our main communication channel for updates and progress of projects like Sparrow, MegaDetector, and PytorchWildlife. Please follow us there. 

In terms of deforestation, we do have plans to add this functionalities in the future because we have a line of work specifically on deforestation assessment under the Project Guacamaya initiative. It will be very similar to the overhead animal detection professing but on forest segmentation. 

For people sharing thoughts, we will ask some of our partners who are currently using Sparrow to share some public feedback to us. It will also likely be on Linkedin. Please keep an eye on it. 

In terms of tooling, we are designing Sparrow to be as tool agnostic as possible, so it is reduced down to a simple data collection, management, and processing platform. How data are collected, managed, and processed is totally up to different users and projects. That's our end goal. 

Same as our software. We are it to be as open and extensible as possible. We want people to be able to create their own "Sparrow Studio" on top of our base Sparrow Studio. Once it is open sourced, it should be possible. 

Please let us know if there are any questions, and feel free to send us emails. Thanks!