https://github.com/retkowsky/computer_vision_train_station
Train Station Computer Vision demo
https://github.com/retkowsky/computer_vision_train_station
azure computer-vision
Last synced: 4 months ago
JSON representation
Train Station Computer Vision demo
- Host: GitHub
- URL: https://github.com/retkowsky/computer_vision_train_station
- Owner: retkowsky
- Created: 2022-04-19T08:14:14.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2022-04-20T13:42:53.000Z (about 4 years ago)
- Last Synced: 2025-06-11T14:59:51.778Z (about 1 year ago)
- Topics: azure, computer-vision
- Language: Jupyter Notebook
- Homepage:
- Size: 42.6 MB
- Stars: 14
- Watchers: 3
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Computer Vision Train Station demo
This is an example of a computer vision application to **detect the presence of a train on a platform and to count the number of people on the platform**.
This usecase can be useful for public transportation for passengers crowd counting.
We are going to use **YoloV5 to detect persons and train**. Results will be saved into an **Azure ML experiment**. We can use different versions of **YoloV5 with PyTorch.**
**We can blur the frames** from the video for **people privacy concerns**. There are many ways to do it. In this example we will blur all the frames without degrading the quality of the images for the CV model. We can as well decide to blur only the detected faces (and not the full image).
20-April-2022
Serge Retkowsky | serge.retkowsky@microsoft.com | https://www.linkedin.com/in/serger/
Note: All these Python notebooks were made for demo purposes. They were not designed for production usage. This feature is currently in public preview. This preview version is provided without a service-level agreement. Certain features might not be supported or might have constrained capabilities. For more information, see Supplemental Terms of Use for Microsoft Azure Previews. https://azure.microsoft.com/en-us/support/legal/preview-supplemental-terms/