arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.03591cs.CV
收藏

视频中人体姿态估计的基于关系的关联关节定位

Relation-Based Associative Joint Location for Human Pose Estimation in Videos

Beijing University of Posts and Telecommunications(北京邮电大学)

Yonghao Dang, Jianqin Yin, Shaojie Zhang

AI总结:

针对视频中人体姿态估计的关节长距离交互建模和遮挡问题,提出轻量级即插即用的关节关系提取器(JRE)显式建模关节关联,并结合姿态语义转移网络(RPSTN)跨帧传递语义特征,有效提升了遮挡场景下的姿态估计性能。

摘要:

基于视频的人体姿态估计(VHPE)是一项重要且具有挑战性的任务。尽管深度学习方法在VHPE方面取得了显著进展,但该任务的大多数方法通过扩大卷积的感受野来隐式建模关节之间的长距离交互。与以往方法不同,我们设计了一个轻量级且即插即用的关节关系提取器(JRE),以显式且自动地建模关节之间的关联关系。JRE将关节的伪热图作为输入,并计算伪热图之间的相似度。通过这种方式,JRE能够灵活地学习任意两个关节之间的关系,使其能够学习人体姿态丰富的空间配置。此外,JRE可以根据关节之间的关系推断不可见关节,这有利于模型定位被遮挡的关节。然后,结合时间语义连续性建模,我们提出了一种用于基于视频的人体姿态估计的基于关系的姿态语义转移网络(RPSTN)。具体而言,为了捕捉姿态的时间动态,通过一个关节关系引导的姿态语义传播器(JRPSP),将当前帧的姿态语义信息转移到下一帧。所提出的模型能够将姿态语义特征从非遮挡帧转移到遮挡帧,使我们的方法对遮挡具有鲁棒性。此外,所提出的JRE模块也适用于基于图像的人体姿态估计。所提出的RPSTN在基于视频的Penn Action数据集、Sub-JHMDB数据集和PoseTrack2018数据集上取得了最先进的结果。此外,所提出的JRE提高了骨干网络在基于图像的COCO2017数据集上的性能。代码可在https://github.com/YHDang/pose-estimation获取。

英文摘要:

Video-based human pose estimation (VHPE) is a vital yet challenging task. While deep learning methods have made significant progress for the VHPE, most approaches to this task implicitly model the long-range interaction between joints by enlarging the receptive field of the convolution. Unlike prior methods, we design a lightweight and plug-and-play joint relation extractor (JRE) to model the associative relationship between joints explicitly and automatically. The JRE takes the pseudo heatmaps of joints as input and calculates the similarity between pseudo heatmaps. In this way, the JRE flexibly learns the relationship between any two joints, allowing it to learn the rich spatial configuration of human poses. Moreover, the JRE can infer invisible joints according to the relationship between joints, which is beneficial for the model to locate occluded joints. Then, combined with temporal semantic continuity modeling, we propose a Relation-based Pose Semantics Transfer Network (RPSTN) for video-based human pose estimation. Specifically, to capture the temporal dynamics of poses, the pose semantic information of the current frame is transferred to the next with a joint relation guided pose semantics propagator (JRPSP). The proposed model can transfer the pose semantic features from the non-occluded frame to the occluded frame, making our method robust to the occlusion. Furthermore, the proposed JRE module is also suitable for image-based human pose estimation. The proposed RPSTN achieves state-of-the-art results on the video-based Penn Action dataset, Sub-JHMDB dataset, and PoseTrack2018 dataset. Moreover, the proposed JRE improves the performance of backbones on the image-based COCO2017 dataset. Code is available at https://github.com/YHDang/pose-estimation.

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。

↑