BriefGPT.xyz
Sep, 2016
Lie-X: 基于深度图像的关节物体姿态估计、跟踪和动作识别
Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups
HTML
PDF
Chi Xu, Lakshmi Narasimhan Govindarajan, Yu Zhang, Li Cheng
TL;DR
本文提出了一种基于李群理论的统一框架，用于解决深度图像中复杂目标的姿态估计、跟踪和动作识别问题，并在多种实验中验证其优于卷积神经网络和回归森林等方法的竞争力。
Abstract
pose estimation
,
tracking
, and
action recognition
of
articulated object
→