vive-diy-position-sensor VS zero-shot-object-tracking

There is a project out there to utilize HTC Vive lighthouses with a diy sensor. Not sure if something like this is out there for the Steam VR stuff

https://github.com/ashtuchkin/vive-diy-position-sensor

I was considering (and still am considering) building slimeVR trackers. However, I do own steamvr basestations and I kind of want to take advantage of that if possible. So I was curious whether there is a cheap diy method to base station based trackers. I did come across this: https://github.com/ashtuchkin/vive-diy-position-sensor However I have no clue to how well this actually works. Any ideas of what to do?

Tundra hasn't accomplished much of anything novel with their tracker addon. You can go on GitHub and find the plans and the parts to build one yourself: https://github.com/ashtuchkin/vive-diy-position-sensor

I ve looked into the Lighthouse hackers community but can only find receiving sensor which are too big for my project, I m looking for a discreet system instead.

Found this, https://github.com/ashtuchkin/vive-diy-position-sensor

With steamvr, i assume you want to use the lighthouses for tracking? There are a few resources for that of people who did similar stuff: https://github.com/ashtuchkin/vive-diy-position-sensor

I’ve seen a bunch of drone-detection computer vision projects. Usually they’re detecting dromes from other drones though (Eg for autonomous racing[1] or drone-defense).

A challenge with doing it from the ground is that the drones will be quite small relative to the size of the image. With sufficient compute and several cameras a tiling-based approach[2] should work!

If you want to do unique-identification you’ll also need object tracking[3].

This is exactly the type of project Roboflow (our startup) is built to empower! Happy to chat/help further (Eg we might be able to help source a good dataset to start from). And if it’s for non-commercial use it should be completely free.

[1] https://blog.roboflow.com/drone-computer-vision-autopilot/

[2] https://blog.roboflow.com/detect-small-objects/

[3] https://blog.roboflow.com/zero-shot-object-tracking/

We use CLIP for object tracking with pretty good results (with no second model train required). https://blog.roboflow.com/zero-shot-object-tracking/

Zero Shot Object Tracking\ (4 comments)

It uses an object detection model (in our example code[1], we used one from Roboflow Universe[2] but you should be able to use any object detection model) and then sends a crop of each detected box to CLIP to get the feature vector that Deep SORT uses to differentiate between and track instances across frames.

[1] https://github.com/roboflow-ai/zero-shot-object-tracking

[2] https://universe.roboflow.com

Repo: https://github.com/roboflow-ai/zero-shot-object-tracking