{"id":16541130,"url":"https://github.com/anibali/aspset-510","last_synced_at":"2025-07-28T19:37:42.437Z","repository":{"id":137205107,"uuid":"263211880","full_name":"anibali/aspset-510","owner":"anibali","description":"A large-scale video dataset for the training and evaluation of 3D human pose estimation models","archived":false,"fork":false,"pushed_at":"2024-02-04T00:10:56.000Z","size":220,"stargazers_count":44,"open_issues_count":0,"forks_count":0,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-18T00:01:47.096Z","etag":null,"topics":["dataset","human-pose-estimation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anibali.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2020-05-12T02:29:16.000Z","updated_at":"2025-01-17T05:50:53.000Z","dependencies_parsed_at":"2024-02-04T01:24:11.893Z","dependency_job_id":"6fc8a588-61ed-453e-8e22-e08030867c1a","html_url":"https://github.com/anibali/aspset-510","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Faspset-510","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Faspset-510/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Faspset-510/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Faspset-510/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anibali","download_url":"https://codeload.github.com/anibali/aspset-510/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244772673,"owners_count":20508037,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dataset","human-pose-estimation"],"created_at":"2024-10-11T18:54:09.739Z","updated_at":"2025-03-21T09:32:22.812Z","avatar_url":"https://github.com/anibali.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"**UPDATE 2024-02-04: Test set annotations have now been released. [Click to download](https://archive.org/download/aspset510/aspset510_v1_test-joints_3d.tar.gz).**\n\n# ASPset-510\n\n![ASPset logo](docs/images/aspset_logo.svg)\n\nASPset-510 (**A**ustralian **S**ports **P**ose Data**set**) is a large-scale video dataset for\nthe training and evaluation of 3D human pose estimation models. It contains 17 different amateur\nsubjects performing 30 sports-related actions each, for a total of 510 action clips.\n\nThis repository contains Python code for working with ASPset-510.\n\nIf you don't want to use these scripts and would prefer to directly download the data yourself,\nASPset-510 is available on the Internet Archive at\n[https://archive.org/details/aspset510](https://archive.org/details/aspset510).\n\n\n## Requirements\n\n### Core\n\n```bash\n$ conda env create -f environment.yml\n```\n\n* python \u003e= 3.6\n* numpy\n* [ezc3d](https://github.com/pyomeca/ezc3d)\n* [posekit](https://github.com/anibali/posekit)\n\n### GUI (Optional)\n\n```bash\n$ conda env update -f environment-gui.yml\n```\n\n* [PyOpenGL](http://pyopengl.sourceforge.net/)\n* [glfw](https://github.com/FlorianRhiem/pyGLFW)\n* matplotlib\n\n### PyTorch (Optional)\n\n```bash\n$ conda env update -f environment-torch.yml\n```\n\n\n## Scripts\n\n### Downloading the dataset\n\n`download_data.py` downloads and extracts ASPset-510 data.\n\nExample usage:\n\n```bash\n$ python src/aspset510/bin/download_data.py --data-dir=./data\n```\n\nNote that by default the original archive files will be downloaded and kept in the `archives`\nsubdirectory of whichever path you set using `--data-dir`. To set a different path for the\narchives, use the `--archive-dir` option. To download the archives without extracting them,\nuse the `--skip-extraction` option.\n\n### Browsing clips from the dataset\n\n`browse_clips.py` provides a graphical user interface for browsing clips from ASPset-510.\n\nExample usage:\n\n```bash\n$ python src/aspset510/bin/browse_clips.py --data-dir=./data\n```\n\n![Screenshot of the clip browser GUI](docs/images/browse_clips_gui.jpg)\n\n\n## Acknowledgments and license\n\nASPset-510 is brought to you by [La Trobe University](https://www.latrobe.edu.au/) and the\n[Australian Institute of Sport](https://www.ais.gov.au/). It is dedicated to the public\ndomain under the [CC0 1.0 license](https://creativecommons.org/publicdomain/zero/1.0/).\n\nIf you find this dataset useful for your own work, please cite the following paper:\n\n```\n@article{nibali2021aspset,\n  title={{ASPset}: An Outdoor Sports Pose Video Dataset With {3D} Keypoint Annotations},\n  author={Nibali, Aiden and Millward, Joshua and He, Zhen and Morgan, Stuart},\n  journal={Image and Vision Computing},\n  pages={104196},\n  year={2021},\n  issn={0262-8856},\n  doi={https://doi.org/10.1016/j.imavis.2021.104196},\n  url={https://www.sciencedirect.com/science/article/pii/S0262885621001013},\n  publisher={Elsevier}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanibali%2Faspset-510","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanibali%2Faspset-510","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanibali%2Faspset-510/lists"}