arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10060cs.CV
收藏

多人全身姿态估计

Multi-Person Full Body Pose Estimation

Shanghai Jiao Tong University(上海交通大学)

Haoyi Zhu, Cheng Jie, Shaofei Jiang

摘要:

多人姿态估计在许多领域都有着重要的应用。虽然前人对人体姿态估计的各个部分进行了大量的研究,但对于多人的全身姿态估计还需要进一步的研究。我们的工作是通过知识蒸馏开发一个完整的模型,可以估计全身姿态。基于AlphaPose系统和MSCOCO2017数据集进行训练,我们的模型在我们手动注释的验证数据集上实现了51.5 mAP。相关资源可在https://esflfei.github.io/esflfei.gethub.io/website.html获得。

英文摘要:

Multi-person pose estimation plays an important role in many fields. Although previous works have researched a lot on different parts of human pose estimation, full body pose estimation for multi-person still needs further research. Our work has developed an integrated model through knowledge distillation which can estimate full body poses. Trained based on the AlphaPose system and MSCOCO2017 dataset, our model achieves 51.5 mAP on the validation dataset annotated manually by ourselves. Related resources are available at https://esflfei.github.io/esflfei.gethub.io/website.html.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑