https://github.com/stephanj/basketballvideoanalysis

https://github.com/stephanj/basketballvideoanalysis

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/stephanj/basketballvideoanalysis
• Owner: stephanj
• License: apache-2.0
• Created: 2019-12-14T12:44:50.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-06-21T23:51:49.000Z (almost 3 years ago)
• Last Synced: 2025-03-31T15:19:58.286Z (about 2 months ago)
• Language: Jupyter Notebook
• Size: 136 MB
• Stars: 306
• Watchers: 37
• Forks: 76
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Sports Video Analysis

See wiki page for [more details](https://github.com/stephanj/basketballVideoAnalysis/wiki).

## Court Detection



See details on court detection [here](https://github.com/stephanj/basketballVideoAnalysis/tree/master/court-detection).

## Mask R-CNN of persons (mask-rcnn)

See details [here](https://github.com/stephanj/basketballVideoAnalysis/tree/master/mask-rcnn) including online tutorial.

[](https://www.youtube.com/watch?v=yEqGTSd5DQU)

Video output example

https://www.youtube.com/watch?v=yEqGTSd5DQU

## Color detection of players (color-detection)

The run script will produce a CSV with the RGB values and percentage of each color.

ToDo:  Classify each color result into two groups, identify hopefully each team by color.

![Colors](https://user-images.githubusercontent.com/179457/71019085-040b8c80-20fa-11ea-8e44-d22759d9352a.jpg)

## Players tracking

See article on [players tracking solutions](https://github.com/stephanj/basketballVideoAnalysis/wiki/Tracking-Players)

See also [YouTube](https://www.youtube.com/watch?v=6b__GMsoW4k) video with different solutions.

## Action Classification

![PoseDetection](https://user-images.githubusercontent.com/179457/71200350-23d8b700-2298-11ea-85eb-37b2c8d07b76.png)

Required so we can classify the game play action of players.

## Homography mapping of court

Maps the 3D court onto a 2D version, required for analysis of movement.

![MiniMap](https://user-images.githubusercontent.com/179457/71530819-2c5e6c80-28ec-11ea-91fe-4dc9d2d19793.jpg)

See also [YouTube video](https://www.youtube.com/watch?v=tpavRDeDlTI)

See details [here](https://github.com/stephanj/basketballVideoAnalysis/tree/master/homography-mapping)

and [article](https://www.linkedin.com/pulse/journey-towards-creating-basketball-mini-map-stephan-janssen/) with [tutorial](https://github.com/stephanj/basketballVideoAnalysis/tree/master/mini-map-tutorial).