We are making autonomous systems which can run in real-time on cheap (~100$) hardware to detect and track objects.
Latest demo
We like to show the results each time we have progress, so this is latest demonstration.
Contact
Send me DM on X: @roman_koshchei. We would be interested to talk with:
- potential investors or partners
- cool engineers of any kind
Product
Module with installed software and AI model expected in range of 100-150$.
Module will find objects and operator will be able to select main one to focus on. Or use fully autonomous mode when best recognized object would be tracked as main without human intervention.
Tools
Here are some Open Source tools we developed for ourself. You can check them out:
-
YOLO Auto Annotation creates YOLO dataset from specified images using Moondream AI model to find bounding boxes for your classes. It reduces time required to go through images and annotate them yourself.
-
YOLO Dataset Visualizer allows to scroll through dataset and see bounding boxes on images. You can remove image from dataset if bounding boxes are incorrect. I use it after Auto Annotation to remove occasional mistakes.