> For the complete documentation index, see [llms.txt](https://irosyadi.gitbook.io/irosyadi/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://irosyadi.gitbook.io/irosyadi/machine-learning/ml-sport-pose.md).

# Machine Learning for Sport Pose Analysis

## Pose Estimation

* [Pose Estimation in Jetson Device](https://github.com/NVIDIA-AI-IOT/deepstream_pose_estimation) [Blog](https://developer.nvidia.com/blog/creating-a-human-pose-estimation-application-with-deepstream-sdk/)

## Sport Pose Analysis

* [Badminton Pose Analysis](https://github.com/deepaktalwardt/badminton-pose-analysis)
* [Action Dataset (Tennis and Badminton)](https://www.cvssp.org/acasva/Downloads)
* [Ref-1](https://www.researchgate.net/publication/316477606_Computer_vision_for_sports_Current_applications_and_research_topics)
* [Ref-2](https://www.researchgate.net/publication/332378399_Position_Detection_for_Badminton_Tactical_Analysis_based_on_Multi-person_Pose_Estimation)
* [Ref-3](https://ieeexplore.ieee.org/document/8686917)
* [Ref-4](https://www.cs.ccu.edu.tw/~wtchu/papers/2017ICMR-chu.pdf)
* [Ref-5](https://dl.acm.org/doi/pdf/10.1145/3375959.3375981?download=true)
* [Ref-6](https://www.groundai.com/project/followmeup-sports-new-benchmark-for-2d-human-keypoint-recognition/1#bib.bib16)
* [Ref-7](https://deepai.org/publication/coachai-a-project-for-microscopic-badminton-match-data-collection-and-tactical-analysis)
* [Ref-8](https://ieeexplore.ieee.org/document/8686917)

## Pose Estimation

### Methods

* HRNet
* OpenPose
* HigherHRNet
* Smiple Baselines
* Alphapose
* Densepose
* Personlab

### Datasets

* [COCO](https://cocodataset.org/#home) (Common Objects in Context)
  * Benchmark; Images from Flickr
* [MPII Human Pose](https://human-pose.mpi-inf.mpg.de/) (body\_25)
  * 25k images, 40k people, 401 human activities, extracted from YouTube videos
* [Leeds Sports Pose](https://sam.johnson.io/research/lsp.html)
  * 2k images of mostly Sports from Flickr
* [Frames Labeled in Cinema](https://human-pose.mpi-inf.mpg.de/) (FLIC)
  * 5003 Images from movies labeled by Amazon Mechanical Turk
* [FLIC Plus](https://jonathantompson.github.io/flic_plus.htm) by [Jon Tompson](https://jonathantompson.github.io/)
* [Human3.6M](https://vision.imar.ro/human3.6m/description.php)
  * 3D Single Person
* [HumanEva](https://humaneva.is.tue.mpg.de/)
  * 7 videos with 3D body poses, 4 subjects, 6 common actions
* [SURREAL](https://www.di.ens.fr/willow/research/surreal/data/)
  * 6m frames of Synthetic Humans
* [Panoptic](https://domedb.perception.cs.cmu.edu/)
* [Basketball Pose Analysis](https://github.com/chonyy/AI-basketball-analysis)