☆ This paper has been recommended for acceptance ☆☆ This work was supported by the EU project TOMSY Swedish Foundation for Strategic Research. An early ver in [1]. ⁎ Corresponding author. Tel.: +49 1774659896. E-mail addresses: [email protected] (H. Kjellström), [email protected] (C.H. Ek), [email protected] URLs: http://ps.is.tuebingen.mpg.de/person/romero http://www.csc.kth.se/~hedvig (H...

Augmented reality requires accurate position and orientation estimates of a camera. In our approach inertial and visual data are fused using the conditional probability framework to estimate camera pose. We propose a measurement equation for 2D-3D model correspondence, i.e., detecting known 3D features of the scene in a camera image. The probability density of this measurement equation is inves...

In this paper, a novel activity recognition method based on signal-oriented and model-based features is presented. The model-based features are calculated from shoulder and elbow joint angles and torso orientation, provided by upper-body pose estimation based on a biomechanical body model. The recognition performance of signal-oriented and model-based features is compared within this paper, and...

xvi Chapter

Automatic recovery of 3d pose of multiple interacting subjects from unconstrained monocular image sequence is a challenging and largely unaddressed problem. We observe, however, that by tacking the interactions explicitly into account, treating individual subjects as mutual “context” for one another, performance on this challenging problem can be improved. Building on this observation, in this ...

Face orientation can be used to derive vigilance cues about the vehicle driver. In this paper, a face pose estimation model based on visual features is presented. The face orientation is estimated through SVM with features detection such as eyes, mouth, facial outlines and so on. Innovative point of this research is the utilization of the features triangle, which composed with eyes and mouth lo...

We present a system for estimating location and orientation of a person’s head, from depth data acquired by a low quality device. Our approach is based on discriminative random regression forests: ensembles of random trees trained by splitting each node so as to simultaneously reduce the entropy of the class labels distribution and the variance of the head position and orientation. We evaluate ...

In this paper we propose a method for evaluating the dynamic blind spot of an operator of a construction vehicle by integrating static blind spot map of a construction vehicle with the head orientation of the operator. By computing the position and orientation of the equipment operator’s head, the field-of-view (FOV) of the operator is known which is projected on the blind spot map of the vehic...

Camera pose estimation is the problem of determining the position and orientation of an internally calibrated camera from known 3D reference points and their images. We briefly survey several existing methods for pose estimation, then introduce our new improved linear algorithm. The advantage of the algorithm is that it is easy to implement and stable. We give the experimental results.