The pose of a calibrated camera can be estimated from known correspondences with known scene structure. There is a number of pose estimation algorithms which solve this problem, however, all of these algorithms suffer from pose ambiguity. This paper analyses the reason of pose ambiguity from the aspect of the distribution of object points. Then, we develop a novel robust method to solve pose am...

We present an original method for tracking in an image sequence complex objects which can be modeled approximately by a polyhedral shape. The approach relies on the estimation of the object image motion as well as the computation of the object pose. The proposed method fulllls real-time constraints along with reliability and robustness requirements.

In this paper,wepropose a supervised SmoothMulti-Manifold Embedding (SMME) method for robust identity-independent head pose estimation. In order to handle the appearance variations caused by identity, we consider the pose data space as multiple manifolds in which each manifold characterizes the underlying subspace of subjects with similar appearance. We then propose a novel embedding criterion ...

This work proposes a methodology for the analysis of the uncertainty in the localization of objects when considering uncertain image data, camera and object geometry parameters. The uncertainty is propagated through an extended static Kalman filter initialized with the parameters used for the localization and updated with new matched features obtained by back-projecting onto the image. At the e...

This paper proposes a real-time head pose estimation system usinga new image matchingtechnique. The system consists ofa trainingstage,in which subspace dictionaries for classifyinghead poses are computed using template matchingand the factorization method, and a recognition stage,in which head poses are estimated usingthe subspace method. The system uses the method ofadaptivelyscaled template m...

Sensor-line cameras have been designed for space missions in the 1980s, and are used for various tasks, including panoramic imaging. Laser range-finders are able to generate dense depth maps (of isolated surface points). Panoramic sensor-line cameras and laser range-finders may both be implemented as rotating sensors, and we used them together this way to reconstruct accurately 3D environments ...

In this paper, we present our system used and evaluated on the CLEAR’07 benchmarks, both on singleand multi-view head pose estimation. The benchmarks show a high contrast in the application domain: whereas the single-view task provides meeting recordings involving high-quality captures of the participants, the multi-view benchmark targets at low-quality, unobtrusive observations of people by me...

We develop a new formulation for including invariance in a general form of the Hough transform. We first develop a formal definition of the Hough transform mapping for arbitrary shapes and general transformations. We then include an invariant characterization of shapes and we develop and apply our technique to extract shapes under similarity and affine transformations. Our characterization does...

We propose a method for the extraction of complete and rich symbolic line segments in 3D based on RGB-D data. Edges are detected by combining cues from the RGB image and the aligned depth map. 3D line segments are then reconstructed by back-projecting 2D line segments and intersecting this with local surface patches computed from the 3D point cloud. Different edge types are classified using the...

We present a method for estimating pose information from a single depth image given an arbitrary kinematic structure without prior training. For an arbitrary skeleton and depth image, an evolutionary algorithm is used to find the optimal kinematic configuration to explain the observed image. Results show that our approach can correctly estimate poses of 39 and 78 degree-of-freedom models from a...