3-D Head Tracking via Invariant Keypoint Learning

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	3-D Head Tracking via Invariant Keypoint Learning
	Wang, Haibo 1; Davoine, Franck 2; Lepetit, Vincent 3; Chaillou, Christophe 4; Pan, Chunhong5
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2012-08-01
卷号	22 期号:8 页码:1113-1126
文章类型	Article
摘要	Keypoint matching is a standard tool to solve the correspondence problem in vision applications. However, in 3-D face tracking, this approach is often deficient because the human face complexities, together with its rich viewpoint, nonrigid expression, and lighting variations in typical applications, can cause many variations impossible to handle by existing keypoint detectors and descriptors. In this paper, we propose a new approach to tailor keypoint matching to track the 3-D pose of the user head in a video stream. The core idea is to learn keypoints that are explicitly invariant to these challenging transformations. First, we select keypoints that are stable under randomly drawn small viewpoints, nonrigid deformations, and illumination changes. Then, we treat keypoint descriptor learning at different large angles as an incremental scheme to learn discriminative descriptors. At matching time, to reduce the ratio of outlier correspondences, we use second-order color information to prune keypoints unlikely to lie on the face. Moreover, we integrate optical flow correspondences in an adaptive way to remove motion jitter efficiently. Extensive experiments show that the proposed approach can lead to fast, robust, and accurate 3-D head tracking results even under very challenging scenarios.
关键词	3-d Head Tracking Keypoint-based Tracking Pose Estimation
WOS标题词	Science & Technology ; Technology
关键词[WOS]	ACTIVE APPEARANCE MODELS ; POSE ESTIMATION ; FACE TRACKING ; RECOGNITION ; DESCRIPTOR ; RECOVERY ; FEATURES ; MOTION ; SCALE ; FLOW
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000308437500001
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/3707
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
作者单位	1.Shandong Univ, Jinan 250061, Peoples R China 2.Peking Univ, LIAMA MPR Project Team, Ctr Natl Rech Sci, Beijing 100190, Peoples R China 3.Ecole Polytech Fed Lausanne, CH-1015 Lausanne, Switzerland 4.Lille Univ Sci & Technol, LIFL Lab, F-59655 Lille, France 5.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Haibo,Davoine, Franck,Lepetit, Vincent,et al. 3-D Head Tracking via Invariant Keypoint Learning[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2012,22(8):1113-1126.
APA	Wang, Haibo,Davoine, Franck,Lepetit, Vincent,Chaillou, Christophe,&Pan, Chunhong.(2012).3-D Head Tracking via Invariant Keypoint Learning.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,22(8),1113-1126.
MLA	Wang, Haibo,et al."3-D Head Tracking via Invariant Keypoint Learning".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 22.8(2012):1113-1126.