AI Projects

Training An AI

See Project

This project uses AI and Image Recognition to collect data on how people occupy spaces. 

Here, we are able to extract position data from the image recognition network and plot it into 3d space.  

Space Utilization

See Project

In partnership with 100 State, a co-working and entrepreneurship space in Madison, WI, we are able to see how their clients occupy their workspace throughout the day with nothing but a GoPro.

Workspace Optimization

See Project

Using Tableau, we are able to visualize how often individuals experience interruptions throughout the day.

This project was built using Darknet, a creation of J Redmon accessible here. 

The original repository can be found here.

YOLO is a real-time neural network that is faster with similar accuracy to networks like Focal Loss, Google Tensorflow EfficientDET and Facebook Pytorch/Detectron.

 

You can find the whitepaper on YOLO v3 here.

 

The full network structure of YOLO v4 can be viewed here.

This network was trained using pre-labeled images from the COCO (Common Objects in COntext) database which can be found here.