Skip to content

Changes

View changes from to


On November 8, 2023 at 3:29:45 PM UTC, Gravatar Marija Knezevic:
  • Updated description of Traffic Camera Tracking (SAVeNoW) from

    Main goals of this project is to detect, track and obtain velocity information of seven different traffic actors (Escooter, Pedestrians, Cyclists, Motorcycle, Car, Truck, Bus) from a video footage of a traffic intersection in Ingolstadt. This project is a part of SaveNoW, where all these data are used to create a digital twin of Ingolstadt for simulation purposes. <img src="https://raw.githubusercontent.com/savenow/Traffic_Camera_Tracking/main/readme_photos/Overview.png" alt="B3" width="800px"> <img src="https://github.com/savenow/Traffic_Camera_Tracking/blob/main/readme_photos/sample_inference.gif" alt="B3" width="800px"> This algorithm has been specially trained to distinguish between cyclists, e-scooter riders and pedestrians. This data is important to better study the traffic density and the behavior of e-scooters. The weights of the Network are currently not part of the Github repo. If you are interessted in the weights, please contact Pascal Brunner.
    to
    Main goals of this project is to detect, track and obtain velocity information of seven different traffic actors (Escooter, Pedestrians, Cyclists, Motorcycle, Car, Truck, Bus) from a video footage of a traffic intersection in Ingolstadt. This project is a part of SaveNoW, where all these data are used to create a digital twin of Ingolstadt for simulation purposes. <img src="https://raw.githubusercontent.com/savenow/Traffic_Camera_Tracking/main/readme_photos/Overview.png" alt="B3" width="800px"> <img src="hhttps://github.com/savenow/Traffic_Camera_Tracking/blob/main/readme_photos/sample_inference.gif?raw=true" alt="B3" width="800px"> This algorithm has been specially trained to distinguish between cyclists, e-scooter riders and pedestrians. This data is important to better study the traffic density and the behavior of e-scooters. The weights of the Network are currently not part of the Github repo. If you are interessted in the weights, please contact Pascal Brunner.