# 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)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://irosyadi.gitbook.io/irosyadi/machine-learning/ml-sport-pose.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.