A practical framework of multi-person 3D human pose estimation with a single RGB camera

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	A practical framework of multi-person 3D human pose estimation with a single RGB camera
	Le Ma 2,4; Sen Lian 2,4; Shandong Wang 1; Weiliang Meng 2,3,4,5; Jun Xiao 2; Xiaopeng Zhang 2,3,4
	2021-03
会议日期	March 27-April 2, 2021
会议地点	Virtual
英文摘要	We propose a practical framework named ’DN-2DPN-3DPN’ for multi-person 3D pose estimation with a single RGB camera. Our framework performs three-stages tasks on the input video: our DetectNet(DN) firstly detects the people’s bounding box individually for each frame of the video, while our 2DPoseNet(2DPN) estimates the 2D poses for each person in the second stage, and our 3DPoseNet(3DPN) is finally applied to obtain the 3D poses of the people. Experiments validate that our method can achieve state-ofthe-art performance for multi-person 3D human pose estimation on the Human3.6M dataset.
源文献作者	IEEE
会议录	IEEE VR
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/47429]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Weiliang Meng; Jun Xiao; Xiaopeng Zhang
作者单位	1.Intel Labs China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Zhejiang Lab 4.NLPR, Institute of Automation, Chinese Academy of Sciences 5.The State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Le Ma,Sen Lian,Shandong Wang,et al. A practical framework of multi-person 3D human pose estimation with a single RGB camera[C]. 见:. Virtual. March 27-April 2, 2021.