Slice representation of range data for head pose estimation

CASIA OpenIR > 模式识别实验室

	Slice representation of range data for head pose estimation
	Tang, Yunqi 1,2; Sun, Zhenan1 ; Tan, Tieniu1
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
	2014-11-01
卷号	128 页码:18-35
文章类型	Article
摘要	Visual estimation of head pose is desirable for computer vision applications such as face recognition, human computer interaction, and affective computing. However, accurate estimation of head pose in uncontrolled environment is still a grand challenge. This paper proposes a novel feature representation model for accurate pose estimation. In this model, a range image is divided into a set of simple slices that contain abundant geometric cues can be used to accurately describe the poses of a subject. This model provides a general framework for designing new features for head pose estimation. According to this model, design of a new feature model for describing a slice, then a new set of features is generated by combining all slices for describing range images. Due to the huge number of slices that can be generated from single range image, even a simple description model of slice can achieve robust performance. With the guide of this model, two novel range image representation models, which are Local Slice Depth (LSD) and Local Slice Orientation (LSO), are designed. LSD can be used for coarse estimation of head poses, while LSO can achieve accurate results. Moreover, in order to evaluate the performance of proposed representation model, an automatic head pose estimation method is implemented using a Kinect sensor. Firstly both color and range images captured by a Kinect sensor are used to localize and segment the facial region from background. Secondly, two novel integral images, namely slice depth integral image and slice coordinates integral image, are proposed to achieve real-time feature extraction. Finally, random forests are used to learn a stable relationship between slice feature descriptors and head pose parameters. Experiments on both low-quality depth data set Biwi and high-quality depth data set ETH demonstrate state-of-the-art performance of our method. (C) 2014 Elsevier Inc. All rights reserved.
关键词	Head Pose Estimation Slice Representation Random Forests Range Data Kinect
WOS标题词	Science & Technology ; Technology
关键词[WOS]	RECOGNITION
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000341482400002
引用统计	被引频次：4[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/173211/3780
专题	模式识别实验室
作者单位	1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Peoples Publ Secur Univ China, Sch Criminal Sci & Technol, Beijing 100038, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Tang, Yunqi,Sun, Zhenan,Tan, Tieniu. Slice representation of range data for head pose estimation[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2014,128:18-35.
APA	Tang, Yunqi,Sun, Zhenan,&Tan, Tieniu.(2014).Slice representation of range data for head pose estimation.COMPUTER VISION AND IMAGE UNDERSTANDING,128,18-35.
MLA	Tang, Yunqi,et al."Slice representation of range data for head pose estimation".COMPUTER VISION AND IMAGE UNDERSTANDING 128(2014):18-35.