We present a generic and robust method for model-based global 3D head pose estimation in monocular and non-calibrated video sequences. The proposed method relies on a 3D/2D matching between 2D image features estimated throughout the sequence and 3D object features of a generic head model. Specifically, it combines motion and texture features in an iterative optimization procedure based on the downhill simplex algorithm. A proper initialization of the pose parameters, based on a block matching procedure, is performed at each frame in order to take into account large amplitude motions. For the same reason, we have developed a non-linear optical flow-based interpolation algorithm for increasing the frame rate. Experiments demonstrate that this method is stable over extended sequences including large head motions, occlusions, various head postures and lighting variations. The estimation accuracy is related to the head model, as established by using an ellipsoidal model and an ad hoc synthe...

This paper presents an original algorithm for the computation of optical ow called Orthogonal Dynamic Programming (ODP) as well as several enhancements to it. The principle is to minimize a sum of square di erences (SSD) between a pair of images. The originality of the approach is that an optimal matching is searched for entire image strips rather than for pixel neighborhoods. Dynamic programming is used to provide very robust strip alignmentsandamultiresolution iterative process is used to compute the velocity eld. Extensions to the computation of the velocity eldfornoninteger image indexes, to the use of more than two images, and to the search for subpixel velocities, are presented. Results obtained for the Barron, Fleet and Beauchemin performance tests appear to be at least as good as or better than those obtained using classical optical ow detection methods. 1

This paper presents an original algorithm called the \Orthogonal Algorithm " for image matching using dynamic programming and experimental results from its application to stereovision and image interpolation. The algorithm provides a dense, continuous and di erentiable eld of bidimensional displacements like classical optical ow detection algorithms. It is based on an iterative search for a displacement eld that minimizes the L1 or L2 distance between two images. Both images are sliced into parallel and overlapping strips. Corresponding strips are aligned using dynamic programming exactly as 2D representations of speech signal are with the DTW algorithm. Two passes are performed using orthogonal slicing directions. This process is iterated in a pyramidal fashion while reducing the spacing and width of the strips. Very good results have been obtained for stereovision and image interpolation. 1.

Optical flow or image motion estimation is important in the area of computer vision. This paper presents a fast and reliable optical flow algorithm which produces a dense optical flow map by using fast cross-correlation and shortest-path techniques. Fast correlation is achieved by using the box filtering technique which is invariant to the size of the correlation window. The motion for each scan line of the input image is obtained from the correlation volume by finding the best 3D path using dynamic programming rather than simply choosing the position that gives the maximum cross correlation coefficient. Sub-pixel accuracy is achieved by fitting the local correlation coefficients to a quadratic surface. Typical running time for a 256\Theta256 image is in the order of a few seconds rather than minutes. A variety of synthetic and real images have been tested, and good results have been obtained. 1. Introduction Optical flow or image motion is the displacement of each image pixels in an...

This paper presents the use of a new 2D dynamic programming approach for handwritten character recognition. The theoretical natural extension of the well-known 1D dynamic programming algorithm has been presented recently within an hidden Markov random field modeling framework. This principle has been adapted to a handwritten character recognition task and the performances are analyzed on the MNIST database for which spectral local features are extracted. Preliminary results exhibit an error rate similar to the ones reported in the literature. 1.