In case someone. Find this totally out of place commemt… this is how I solved it, I've decided to use a IMX477 HQ Camera, building a *manual, heavy-duty optical rig* utilizing C/CS-mount lenses and physical macro extension tubes.

Hi there! Thanks @Adrien_Pajot for the call-out as I didn't see this. Sandro, I completely feel for you with the challenge! We had attempted to use the motion trigger feature of the cameras, but ended up just recording video and using an object detection approach within the video. I should mention too that our results were not perfect, but our aim was to mostly work out the process, not refine it so there's certainly room for improvement and increase in sample size and training development. But I did think that there was a bit better luck with the nighttime moth detection as compared to daytime (if you take a look at about minute 4:25 in the video at the bottom of this link https://www.oceanscienceanalytics.com/terrestrial-pollinators). I think if we were to continue development, nighttime monitoring would be an interesting route to go. I am not sure about the 850 nm for the Voopeak IR but it didn't seem to attract the insects in the data I reviewed (but I could certainly be wrong!). 

I'll be interested in learning more about how your project goes!  

Hello! The "MIB Paradox" is absolutely real, and PIR sensors are a dead end for insect detection due to their lack of thermal mass. However, falling back on a regular-interval time-lapse is a trap that will likely kill your battery and cost you the most interesting data.

Writing to an SD card is highly energy-intensive (causing current spikes often over 100mA). Doing this blindly every few minutes to save static pictures wastes a massive amount of power on empty frames. Worse, if a bug does show up, you only capture a single frozen moment and miss the entire temporal dynamic of its behavior.

Instead of a blind time-lapse, you can use your camera and a lightweight microcontroller (like an ESP32) as an Intelligent Optical Trigger. Here is how you can bypass the paradox:

• The Low-FPS Radar: Configure your camera to capture images at a very low framerate (1 or 2 frames per second) and in low resolution.
• The RAM Buffer: Do not write these interval images to your SD card. Keep them strictly ephemeral, stored only in the RAM.
• The Binary Judge: Run a tiny, highly optimized machine learning model (TinyML) on that low-res frame to answer a single question: "Is there an insect?"
• The Duty Cycle: If the frame is empty, the system discards the image and immediately drops into a fractional deep sleep for the remaining milliseconds of that second. The SD card is never powered on.
• The Action Trigger: If the AI detects a target, the system wakes up entirely. It triggers your MOSFET to turn on the IR lights, switches the camera to a higher framerate, and begins writing the full video stream directly to the SD card.

This architecture gives you the best of both worlds. You get the energy efficiency of a motion trigger by treating disposable low-res frames as a "virtual PIR," and you only pay the heavy energy cost of lighting and SD card writing when there is guaranteed action to record.

Hey @kimhendrikse , thanks for all these details. I just caught up. I like your approach of supporting multiple object detectors and using the python websockets wrapper! Is your code available somewhere?

Yep, here:

Currently it only installs on older Jetsons as in the coming weeks I’ll finish the install code for current jetsons.

Technically speaking, if you were an IT specialist you could even make it work in wsl2 Ubuntu on windows, but I haven’t published instructions for that. If you were even more of a specialist you wouldn’t need wsl2 either. One day I’ll publish instructions for that once I’ve done it. Though it would be slow unless the windows machine had an NVidia GPU and you PyTorch work with it.

Hey there @JakeBurton , sorry, I did not see your message! 

Why don't you shoot me an email with some tentative availability to luca.pegoraro (at) wsl.ch, and we take it from there? 

Again sorry for the delay! 

Hi @JakeBurton , sorry it has been ages (!), but we are finally prototyping the first version of our hardware database! 

Now would be an excellent time to briefly chat and make sure we are aligning efforts 👍

Would you mind sending me a few options to meet in the next two weeks perhaps? If you prefer, feel free to get in touch via email: [email protected]. 
 We (@LucaPego, @qgeissmann, @Graham_Smith) are based in Europe, FYI. 

Looking forward to meet! 

All the best, 

Luca. 

Hi @LucaPego! Hope all is good with you. I'll take a look who in my team is free and what times could line up and drop you an email later this week with some options. Interested to learn more about your database.

I'm currently considering either using fiftyone or possibly building something myself to validate my insect model predictions, would be really grateful if anyone else has experience using fiftyone or similar software and would share their thoughts and experience :)

Hi Andrew, 

thanks for your reply, good to know that fiftyone is not the perfect solution. Excited to see your data labeller when its finished :D