https://github.com/codeformuenster/traffic-cam
https://github.com/codeformuenster/traffic-cam
mshack20 mshack2020 mszaehlt
Last synced: 29 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/codeformuenster/traffic-cam
- Owner: codeformuenster
- License: mit
- Created: 2020-09-25T10:35:04.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2025-01-07T16:52:04.000Z (about 1 year ago)
- Last Synced: 2025-01-07T18:00:30.411Z (about 1 year ago)
- Topics: mshack20, mshack2020, mszaehlt
- Language: Jupyter Notebook
- Homepage:
- Size: 2.7 MB
- Stars: 5
- Watchers: 8
- Forks: 2
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Observing traffic in the City of Muenster
Image classification and object detection, applied to a public webcam in the city of Münster.
See webcam data source [here](https://www.blick.ms/webcam-auf-dem-prinzipalmarkt-muenster.php).
## Dependencies
* Tested on `Ubuntu 20.04`
* `ffmpeg`, e.g. on Ubuntu install with:
```bash
sudo apt install ffmpeg
```
## Getting started
1. Create and activate virtual environment. For example with `conda`:
```bash
conda env create -n cam python=3.7
conda activate cam
```
2. Install Python dependencies and `traffic-cam` package (with virtual environment activated):
```bash
pip install -r requirements.txt
pip install -e .
```
3. Run scripts in `bin/` in their numerical order.
This includes downloading images, training a classifier, and counting persons.