Robust real-time 3D head pose estimation from range data

Malassiotis, Sotiris; Strintzis, Michael G.

doi:10.1016/j.patcog.2004.11.020

Cited by 88 publications

(54 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Walder et al [32] used a complex dynamic 3D scanner setup to track the head's pose and non-rigid shape, though the algorithm took over 20 seconds to compute per frame. Malassiotis et al [22] estimated head pose from CLA range data by tracking the nose, but state their technique is highly dependent on the person's face shape and does not perform well for large rotations. Meers et al [23] used a similar technique on TOF data.…”

Section: D Methodsmentioning

confidence: 99%

Robust head pose estimation by fusing time-of-flight depth and color

Bleiweiss

Werman

2010

2010 IEEE International Workshop on Multimedia Signal Processing

View full text Add to dashboard Cite

Abstract-We present a new solution for real-time head pose estimation. The key to our method is a model-based approach based on the fusion of color and time-of-flight depth data. Our method has several advantages over existing head-pose estimation solutions. It requires no initial setup or knowledge of a pre-built model or training data. The use of additional depth data leads to a robust solution, while maintaining real-time performance. The method outperforms the state-of-the art in several experiments using extreme situations such as sudden changes in lighting, large rotations, and fast motion.

show abstract

Section: D Methodsmentioning

confidence: 99%

Robust head pose estimation by fusing time-of-flight depth and color

Bleiweiss

Werman

2010

2010 IEEE International Workshop on Multimedia Signal Processing

View full text Add to dashboard Cite

show abstract

“…For the purposes of reading the data into our software platform in a convenient format, we store the data (either point clouds or meshes) in a standard geometry description format known as VRML format which contains information on the location of the data points in the physical space and the connectivity information defined between these points. It is important to highlight that captured facial data can be of any orientation or pose and determination of the orientation and pose of the face in itself of is problem which deserves research merit [24,25].…”

Section: Pde Methodsmentioning

confidence: 99%

Reconstruction of 3D Human Facial Images Using Partial Differential Equations

Elyan¹,

Ugail²

2007

JCP

View full text Add to dashboard Cite

Abstract-One of the challenging problems in geometric modeling and computer graphics is the construction of realistic human facial geometry.Such geometry are essential for a wide range of applications, such as 3D face recognition, virtual reality applications, facial expression simulation and computer based plastic surgery application. This paper addresses a method for the construction of 3D geometry of human faces based on the use of Elliptic Partial Differential Equations (PDE). Here the geometry corresponding to a human face is treated as a set of surface patches, whereby each surface patch is represented using four boundary curves in the 3-space that formulate the appropriate boundary conditions for the chosen PDE. These boundary curves are extracted automatically using 3D data of human faces obtained using a 3D scanner. The solution of the PDE generates a continuous single surface patch describing the geometry of the original scanned data. In this study, through a number of experimental verifications we have shown the efficiency of the PDE based method for 3D facial surface reconstruction using scan data. In addition to this, we also show that our approach provides an efficient way of facial representation using a small set of parameters that could be utilized for efficient facial data storage and verification purposes.

show abstract

“…The proposed pose estimation framework, makes extensive use of depth data, which provides fast and simple background suppression [6] and a useful prior on object scale. During testing, the usefulness of depth as an additional channel for generating object features is also demonstrated.…”

Section: Framework Overviewmentioning

confidence: 99%

Generalised Pose Estimation Using Depth

Hadfield

Bowden

2012

Trends and Topics in Computer Vision

View full text Add to dashboard Cite

Abstract. Estimating the pose of an object, be it articulated, deformable or rigid, is an important task, with applications ranging from HumanComputer Interaction to environmental understanding. The idea of a general pose estimation framework, capable of being rapidly retrained to suit a variety of tasks, is appealing. In this paper a solution is proposed requiring only a set of labelled training images in order to be applied to many pose estimation tasks. This is achieved by treating pose estimation as a classification problem, with particle filtering used to provide non-discretised estimates. Depth information extracted from a calibrated stereo sequence, is used for background suppression and object scale estimation. The appearance and shape channels are then transformed to Local Binary Pattern histograms, and pose classification is performed via a randomised decision forest. To demonstrate flexibility, the approach is applied to two different situations, articulated hand pose and rigid head orientation, achieving 97% and 84% accurate estimation rates, respectively.

show abstract

Robust real-time 3D head pose estimation from range data

Cited by 88 publications

References 20 publications

Robust head pose estimation by fusing time-of-flight depth and color

Robust head pose estimation by fusing time-of-flight depth and color

Reconstruction of 3D Human Facial Images Using Partial Differential Equations

Generalised Pose Estimation Using Depth

Contact Info

Product

Resources

About