{"id":13441161,"url":"https://github.com/AIR-THU/DAIR-RCooper","last_synced_at":"2025-03-20T11:35:40.914Z","repository":{"id":228280246,"uuid":"764967045","full_name":"AIR-THU/DAIR-RCooper","owner":"AIR-THU","description":"[CVPR2024] Official implementation of \"RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception\"","archived":false,"fork":false,"pushed_at":"2024-06-18T02:32:14.000Z","size":61734,"stargazers_count":54,"open_issues_count":4,"forks_count":5,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-07-02T18:04:32.140Z","etag":null,"topics":["autonoumous-driving","cooperative-perception","dataset-and-benchmark","multi-view","roadside-perception"],"latest_commit_sha":null,"homepage":"https://openaccess.thecvf.com/content/CVPR2024/html/Hao_RCooper_A_Real-world_Large-scale_Dataset_for_Roadside_Cooperative_Perception_CVPR_2024_paper.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AIR-THU.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"publiccode":null,"codemeta":null}},"created_at":"2024-02-29T03:06:47.000Z","updated_at":"2024-06-25T16:32:36.000Z","dependencies_parsed_at":"2024-04-25T14:59:10.497Z","dependency_job_id":"5f24a623-fd51-42e2-a2a9-a8f10f41212f","html_url":"https://github.com/AIR-THU/DAIR-RCooper","commit_stats":null,"previous_names":["air-thu/dair-rcooper"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIR-THU%2FDAIR-RCooper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIR-THU%2FDAIR-RCooper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIR-THU%2FDAIR-RCooper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIR-THU%2FDAIR-RCooper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AIR-THU","download_url":"https://codeload.github.com/AIR-THU/DAIR-RCooper/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":213299606,"owners_count":15566650,"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":["autonoumous-driving","cooperative-perception","dataset-and-benchmark","multi-view","roadside-perception"],"created_at":"2024-07-31T03:01:30.609Z","updated_at":"2024-10-28T00:32:09.817Z","avatar_url":"https://github.com/AIR-THU.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception\n\n[![paper](https://img.shields.io/badge/CVPR-Paper-green)](https://openaccess.thecvf.com/content/CVPR2024/papers/Hao_RCooper_A_Real-world_Large-scale_Dataset_for_Roadside_Cooperative_Perception_CVPR_2024_paper.pdf)\n[![supp](https://img.shields.io/badge/Supp-Material-red)](https://openaccess.thecvf.com/content/CVPR2024/supplemental/Hao_RCooper_A_Real-world_CVPR_2024_supplemental.pdf)\n[![arXiv](https://img.shields.io/badge/arXiv-Paper-purple)](http://arxiv.org/abs/2403.10145)\n[![ckpts](https://img.shields.io/badge/ckpts-DOWNLOAD-blue)](https://drive.google.com/drive/folders/1J2nhh41UYp5jugdMT7zpxKr0CRoqpRUJ?usp=drive_link)\n[![video](https://img.shields.io/badge/Youtube-Video-yellow)](https://www.youtube.com/watch?v=6CFi9Bz4wg4)\n[![poster](https://img.shields.io/badge/Poster-Presentation-cyan)](assets/RCooper.jpg)\n\nThis is the official implementation of CVPR2024 paper. \"RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception\".\n[Ruiyang Hao\u003csup\u003e*\u003c/sup\u003e](https://ry-hao.top/),  [Siqi Fan\u003csup\u003e*\u003c/sup\u003e](https://leofansq.github.io/), [Yingru Dai](https://dblp.org/pid/350/9258.html), [Zhenlin Zhang](https://www.linkedin.com/in/zhenlinzhangtim/), [Chenxi Li](),  [Yuntian Wang](), [Haibao Yu](https://scholar.google.com/citations?user=JW4F5HoAAAAJ), [Wenxian Yang](https://scholar.google.com/citations?user=Kiz73xwAAAAJ), [Jirui Yuan](https://air.tsinghua.edu.cn/en/info/1012/1219.htm), [Zaiqing Nie\u003csup\u003e†\u003c/sup\u003e](https://scholar.google.com/citations?user=Qg7T6vUAAAAJ)\n\n\u003cdiv style=\"text-align:center\"\u003e\n\u003cimg src=\"assets/RCooper.jpg\" width=\"800\" alt=\"\" class=\"img-responsive\"\u003e\n\u003c/div\u003e\n\n## Overview\n- [Data Download](#data-download)\n- [Data Conversion](#data-conversion)\n- [Quick Start](#quick-start)\n- [Benchmark](#benchmark)\n- [Citation](#citation)\n- [Acknowledgment](#acknowledgment)\n\n## Data Download\nPlease check the bottom of this page [website](https://www.t3caic.com/qingzhen/) to download the data. As shown in the figure bellow.\n\n\u003cdiv style=\"text-align:center\"\u003e\n\u003cimg src=\"assets/dataset_page_instruction.jpg\" width=\"700\" alt=\"\" class=\"img-responsive\"\u003e\n\u003c/div\u003e\n\nAfter downloading the data, please put the data in the following structure:\n```shell\n├── RCooper\n│   ├── calib\n|      |── lidar2cam\n|      |── lidar2world\n│   ├── data\n|      |── folders named specific scene index\n│   ├── labels\n|      |── folders named specific scene index\n│   ├── original_label\n|      |── folders named specific scene index\n```\n\n## Data Conversion\n\nTo facilitate the research of cooperative perception methods on RCooper. We provide the format converter from RCooper to other popular public cooperative perception datasets. After the conversion, researchers can directly employ the methods using several opensourced frameworks.\n\nWe now support the following conversions:\n* [DAIR-V2X](https://github.com/AIR-THU/DAIR-V2X)\n* [V2V4Real](https://github.com/ucla-mobility/V2V4Real)\n* [OPV2V](https://github.com/ucla-mobility/OpenCOOD)\n\n### RCooper to V2V4Real\nSetup the dataset path in codes/dataset_convertor/converter_config.py, and complete the conversion.\n```bash\ncd codes/dataset_converter\npython rcooper2vvreal.py\n```\n\n### RCooper to OPV2V\nSetup the dataset path in codes/dataset_convertor/converter_config.py, and complete the conversion.\n```bash\ncd codes/dataset_converter\npython rcooper2opv2v.py\n```\n\n### RCooper to DAIR-V2X\nSetup the dataset path in codes/dataset_convertor/converter_config.py, and complete the conversion.\n```bash\ncd codes/dataset_converter\npython rcooper2dair.py\n```\n\n## Quick Start\n\nFor detection training \u0026 inference, you can find instructions in [docs/corridor_scene](docs/corridor_scene) or [docs/intersection_scene](docs/intersection_scene) in detail. (\u003cb\u003eNotes\u003c/b\u003e: you may need to set PYTHONPATH to call modified codes other than the pip-installed ones.)\n\nFor Tracking, you can find instructions in [docs/tracking.md](docs/tracking.md) in detail.\n\nAll the checkpoints are released in link in the tabels below, you can save them in [codes/ckpts/](codes/ckpts/).\n\n## Benchmark\n### Results of Cooperative 3D object detection for corridor scenes\n| Method                                         | AP@0.3   | AP@0.5   | AP@0.7   | Download Link                                                                                  |\n| ---------------------------------------------- | -------- | -------- | -------- | ---------------------------------------------------------------------------------------------- |\n| No Fusion                                      | 40.0     | 29.2     | 11.1     | [url](https://drive.google.com/drive/folders/1mmnIf0HDjS_vL1abptXM91pJHE3BLdqT?usp=drive_link) |\n| Late Fusion                                    | 44.5     | 29.9     | 10.8     | [url](https://drive.google.com/drive/folders/1mKt7zKoS6KKzEqKWilHuQtpb36PSztxP?usp=drive_link) |\n| Early Fusion                                   | **69.8** | 54.7     | 30.3     | [url](https://drive.google.com/drive/folders/1Ox0Vdh_LPShyK5uGX9s1FHI8USpITy_l?usp=drive_link) |\n| [AttFuse](https://arxiv.org/abs/2109.07644)    | 62.7     | 51.6     | 32.1     | [url](https://drive.google.com/drive/folders/1uBTfVMWhbslPzF4f44q36pDHTwEPhoV_?usp=drive_link) |\n| [F-Cooper](https://arxiv.org/abs/1909.06459)   | 65.9     | 55.8     | 36.1     | [url](https://drive.google.com/drive/folders/1k677v_DTHXf5lMC9DMBeOLHWdEtd3H-e?usp=drive_link) |\n| [Where2Comm](https://arxiv.org/abs/2209.12836) | 67.1     | 55.6     | 34.3     | [url](https://drive.google.com/drive/folders/1aKj5A5wTuy2xJQSiErr0qJ6UWOKxJQFX?usp=drive_link) |\n| [CoBEVT](https://arxiv.org/abs/2207.02202)     | 67.6     | **57.2** | **36.2** | [url](https://drive.google.com/drive/folders/1E8CBXLQmBVnShF2TeyTCkPJN_HBGSyzk?usp=drive_link) |\n\n### Results of Cooperative 3D object detection for intersection scenes\n| Method                                         | AP@0.3   | AP@0.5   | AP@0.7   | Download Link                                                                                  |\n| ---------------------------------------------- | -------- | -------- | -------- | ---------------------------------------------------------------------------------------------- |\n| No Fusion                                      | 58.1     | 44.1     | 23.8     | [url](https://drive.google.com/drive/folders/1MMYB9nSBcEprTOIyB3WkJ4nlnUpyEb05?usp=drive_link) |\n| Late Fusion                                    | **65.1** | **47.6** | 24.4     | [url](https://drive.google.com/drive/folders/1MMYB9nSBcEprTOIyB3WkJ4nlnUpyEb05?usp=drive_link) |\n| Early Fusion                                   | 50.0     | 33.9     | 18.3     | [url](https://drive.google.com/drive/folders/1u8g_f3vzqWqn_D4Sx_UdwX98Jm1wCul_?usp=drive_link) |\n| [AttFuse](https://arxiv.org/abs/2109.07644)    | 45.5     | 40.9     | 27.9     | [url](https://drive.google.com/drive/folders/1W6PeNCnsnUMih1qZP3ONMtwcgDiXzciO?usp=drive_link) |\n| [F-Cooper](https://arxiv.org/abs/1909.06459)   | 49.5     | 32.0     | 12.9     | [url](https://drive.google.com/drive/folders/1uO7MIHwjXA33CBv861l35IgAL_iMjAon?usp=drive_link) |\n| [Where2Comm](https://arxiv.org/abs/2209.12836) | 50.5     | 42.2     | 29.9     | [url](https://drive.google.com/drive/folders/18kcO-G5JHLSj_pd6Gyj5zBYIUK4_fG8k?usp=drive_link) |\n| [CoBEVT](https://arxiv.org/abs/2207.02202)     | 53.5     | 45.6     | **32.6** | [url](https://drive.google.com/drive/folders/1jA6Y0cqw4G-CNDCIUkl5QhNSt4axmVmC?usp=drive_link) |\n\n### Results of Cooperative tracking for corridor scenes\n| Method       | AMOTA(↑)  | AMOTP(↑)  | sAMOTA(↑) | MOTA(↑)   | MT(↑)     | ML(↓)     |\n| ------------ | --------- | --------- | --------- | --------- | --------- | --------- |\n| No Fusion    | 8.28      | 22.74     | 34.05     | 23.89     | 17.34     | 42.71     |\n| Late Fusion  | 9.60      | 25.77     | 35.64     | 24.75     | 24.37     | 42.96     |\n| Early Fusion | **23.78** | **38.18** | 59.16     | 44.30     | **53.02** | **12.81** |\n| AttFuse      | 21.75     | 35.31     | 57.43     | 44.50     | 45.73     | 22.86     |\n| F-Cooper     | 22.47     | 35.54     | 58.49     | 45.94     | 47.74     | 22.11     |\n| Where2Comm   | 22.55     | 36.21     | **59.60** | 46.11     | 50.00     | 19.60     |\n| CoBEVT       | 21.54     | 35.69     | 53.85     | **47.32** | 47.24     | 18.09     |\n\n### Results of Cooperative tracking for corridor scenes\n| Method       | AMOTA(↑)  | AMOTP(↑)  | sAMOTA(↑) | MOTA(↑)   | MT(↑)     | ML(↓)     |\n| ------------ | --------- | --------- | --------- | --------- | --------- | --------- |\n| No Fusion    | 18.11     | 39.71     | 58.29     | 49.16     | 35.32     | 41.64     |\n| Late Fusion  | **21.57** | 43.40     | **63.02** | **50.58** | **42.75** | **34.20** |\n| Early Fusion | 21.38     | **47.71** | 62.93     | 50.15     | 36.80     | 42.75     |\n| AttFuse      | 11.84     | 36.63     | 46.92     | 39.32     | 29.00     | 53.90     |\n| F-Cooper     | -4.86     | 14.71     | 0.00      | -45.66    | 11.52     | 50.56     |\n| Where2Comm   | 14.21     | 38.48     | 50.97     | 42.27     | 29.00     | 45.72     |\n| CoBEVT       | 14.82     | 38.71     | 49.04     | 44.67     | 33.83     | 35.69     |\n\n## Citation\nIf you find RCooper useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.\n```shell\n@inproceedings{hao2024rcooper,\n  title={RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception},\n  author={Hao, Ruiyang and Fan, Siqi and Dai, Yingru and Zhang, Zhenlin and Li, Chenxi and Wang, Yuntian and Yu, Haibao and Yang, Wenxian and Jirui, Yuan and Nie, Zaiqing},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2024},\n  pages={22347-22357}\n}\n```\n\n## Acknowledgment\n- [V2V4Real](https://github.com/ucla-mobility/V2V4Real)\n- [OpenCOOD](https://github.com/DerrickXuNu/OpenCOOD)\n- [AB3DMOT](https://github.com/xinshuoweng/AB3DMOT)\n- [DAIR-V2X](https://github.com/AIR-THU/DAIR-V2X)\n\nSincere appreciation for their great contributions.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAIR-THU%2FDAIR-RCooper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAIR-THU%2FDAIR-RCooper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAIR-THU%2FDAIR-RCooper/lists"}