Hi @abra_ash , @MaximilianPink, @Sarita , @Lars_Holst_Hansen. 

I'm looking to train a very compact (TinyML) model for flying pollinator detection on a static background. I hope a network small enough for microcontroller hardware will prove useful for measuring plant-pollinator interactions in the field. 

Presently, I'm gathering a dataset for training using a basic motion-triggered video-capture program on a raspberry pi. This forms a very crude insect camera trap. 

I'm wondering if anyone has any insights on how I might attract pollinators into my camera field of view?  I've done some very elementary reading on bee optical vision and currently trying the following: 

Purple and yellow artifical flowers are placed on a green background, the center of the flowers are lightly painted with a UV (365nm) coat. 

A sugar paste is added to each flower. 

The system is deployed in an inner-city garden (outside my flat), and I regularly see bees attending the flowers nearby. 

Here's a picture of the field of view: 

Does anyone have ideas for how I might maximise insect attraction? I'm particularly interested in what @abra_ash and @tom_august might have to say - are optical methods enough or do we need to add pheremone lures?

Thanks in advance!

Best, 

Ross

Hi Michelle,

it would be good to get some more information on your project. What question are you trying to answer? How many cameras did you have deployed? How many different study sites/haul-out areas are there?

For the more computationally-inclined, the Project Zamba software can also be used as a python package and the project codebase is fully available on GitHub.

@hikinghack @Nycticebus-scientia We just ran an open-source competition on this exact question! DrivenData is a small group of data scientists, and we partnered with the Max Planck Institute for Evolutionary Anthropology (MPI-EVA) and the Wild Chimpanzee Foundation (WCF) to compile enough hand-labeled data to apply machine learning to the depth problem. In your original post, this falls under the AI Prediction Based category. The code behind all of the top-performing models is freely available on GitHub. We're hoping to make these freely available in the future in the a more user-friendly way.

@JHughes to your point about motion sensor camera traps being continuously set off -our free, open-source web application called Zamba Cloud uses machine learning to automatically sort videos by either what animal they contain or whether they are blank. You just upload a set of videos, and the web application will output a list of labels for each video! This may not address the battery drainage problem, but can help with filtering out blank videos and identifying which actually captured animals.

(apologies for joining this thread late)  Has anyone tried using the LIDAR in one of the newer iPhones so-equipped as a trail cam trigger? (e.g. iPhone12 Pro), perhaps in conjunction with a nueral network that processes the depth map looking for animal triggers?  (I know this is liable to be a power-hungry trigger, for now, just looking at a proof of concept)