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 2103.15534cs.CV
收藏

一种引入图结构的对抗性人体姿态估计网络

An Adversarial Human Pose Estimation Network Injected with Graph Structure

Northwestern Polytechnical University(西北工业大学);National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology(空天地海一体化大数据应用技术国家工程实验室);The University of Adelaide(阿德莱德大学)

Lei Tian, Guoqiang Liang, Peng Wang, Chunhua Shen

摘要:

由于光照、遮挡和重叠等因素导致图像中的人体关键点不可见,现有的大多数人体姿态估计方法都可能产生不合理的人体姿态预测。在本文中,我们设计了一种新的生成对抗网络(GAN),以提高可见关节的定位精度时,一些关节是不可见的。该网络由两个简单而有效的模块,级联特征网络(CFN)和图结构网络(GSN)。首先,CFN利用来自前一阶段的预测图来指导下一阶段中的预测图以产生准确的人体姿势。其次,GSN的目的是通过在不同的关节之间传递消息,以有助于不可见关节的定位。根据GAN,如果由生成器G产生的预测姿态不能被CNOID区分,则生成器网络G已经成功地获得了人体关节的潜在依赖性。在LSP、MPII和COCO三种常用的人体姿态估计基准数据集上进行了实验,实验结果表明了该框架的有效性。

英文摘要:

Because of the invisible human keypoints in images caused by illumination, occlusion and overlap, it is likely to produce unreasonable human pose prediction for most of the current human pose estimation methods. In this paper, we design a novel generative adversarial network (GAN) to improve the localization accuracy of visible joints when some joints are invisible. The network consists of two simple but efficient modules, Cascade Feature Network (CFN) and Graph Structure Network (GSN). First, the CFN utilizes the prediction maps from the previous stages to guide the prediction maps in the next stage to produce accurate human pose. Second, the GSN is designed to contribute to the localization of invisible joints by passing message among different joints. According to GAN, if the prediction pose produced by the generator G cannot be distinguished by the discriminator D, the generator network G has successfully obtained the underlying dependence of human joints. We conduct experiments on three widely used human pose estimation benchmark datasets, LSP, MPII and COCO, whose results show the effectiveness of our proposed framework.

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。

↑