基于OPEC-Net框架的人群框架姿态估计

Crowd Pose Estimation Based on OPEC-Net Framework

人体姿态估计是计算机视觉领域的一个热门研究方向,而遮挡是人体姿态估计的一个基本的挑战,但现有的基于热图的方法遭受了遮挡的严重退化。大部分技术存在一定的内在问题,直接根据视觉信息定位关节,但是看不见的关节将会导致这些相关信息缺乏。针对该技术的局限性,我们提出一个图像引导的渐进式GCN模块,从推理的角度来估计不可见的关节,该模块提供下文和姿态结构的全面理解。此外,现有的基准包含有限的闭塞,以进行评估。本文提出了一个新的OPEC-Net框架和一个新的具有9k个注释图像的遮挡(OCPose)数据集。对基准进行的广泛的定量和定性评估表明,该工作取得了显著的改进。

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation,existing heatmap-based approaches suffffer serious degradation on occlusions.Their intrinsic problem is that they directly localize the joints based on visual information.However,the invisible joints are lack of that.In contrast to localization,our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a com⁃prehensive understanding of both image context and pose structure.Moreover,existing benchmarks contain limited occlusions for evaluation.Therefore,we thoroughly pursue this problem and propose a novel OPEC-Net framework together with a new Occluded Pose(OCPose)dataset with 9k annotated images.Extensive quantitative and qualitative evaluations on benchmarks demonstrate that OPEC-Net achieves significant improvements over recent leading works.Notably,our OCPose is the most complex occlusion dataset with respect to average IoU between adjacent instances.Source code and OCPose will be publicly available.