melexis_VGA_ToF_camera VS megadetector-gui

I want to finish a Time Of Flight camera. My initial application was robotics, but this domain is very crowded. The start is here: https://github.com/lnsru/melexis_VGA_ToF_camera Hardware is not complete, current software is raspiraw with corresponding modified camera header file. Tweaked raspiraw can receive test pattern from sensor chip. I want to offer low cost camera commercially at the end, but have no problem open sourcing my early development. I am electrical engineer and I have all the pieces to finish this project alone, but it’s much nicer working together.

On (some) weekends I work on Megadetector GUI [0]. Megadetector [1] is an object detection model trained on millions of camera trap images and is widely used by conservationists. The issue is that it's rather technical to set up, so I made a GUI for it.

Currently working on a brand new version (not public just yet) that will use the latest MD version (v5 is way faster), better UI and most importantly GPU support out of the box.

[0] https://github.com/petargyurov/megadetector-gui

[1] https://github.com/microsoft/CameraTraps/blob/main/megadetec...

> ML to identify gorillas by their unique nose prints

Really cool stuff. I wonder if face detection is sufficient too? It has been proven to work for brown bears [0].

I have also been doing some open source work [1] to democratise object detection in this space but I haven't had the time to make improvements to the project in a while.

* [0] http://bearresearch.org/

* [1] https://github.com/petargyurov/megadetector-gui

In case any camera trap folk are here, I'm currently volunteering with the NZ Department of Conservation to build an AI-assisted image sorting tool that speeds up the weeding out of empty images.

https://github.com/petargyurov/megadetector-gui

This currently used to assist the conservation efforts of various endemic species such as the kakapo, kea and takahe. (The ML model used is not limited to just these species!)