BriefGPT.xyz
Aug, 2016
基于局部关节到人员关联的多人姿态估计
Multi-Person Pose Estimation with Local Joint-to-Person Associations
HTML
PDF
Umar Iqbal, Juergen Gall
TL;DR
本文提出了一种基于整数线性规划的方法来解决多人姿态估计的问题，并且在 MPII 人体多人姿态数据集上实现了与最先进方法相当的精度，但速度快了 6,000 到 19,000 倍。
Abstract
Despite of the recent success of
neural networks
for
human pose estimation
, current approaches are limited to pose estimation of a single person and cannot handle humans in groups or crowds. In this work, we prop
→