A Convolutional Neural Network to detect traffic lights states (red, green and yellow). A personal project in development.
The dataset used to train de Conv Net is distributted by Autti. It contains 15,000 frames of a car driving in Mountain View California and neighboring cities during daylight conditions. It contains over 65,000 labels across all the frames, collected from a Point Grey research cameras running at full resolution of 1920x1200 at 2hz.
- Car
- Truck
- Pedestrian
- Street Lights
- frame
- xmin
- ymin
- xmax
- ymax
- occluded
- label
- attributes (Only appears on traffic lights)
| Size | 3.3 GB |
| Annotator | Autti |