Real time 3D face and facial feature tracking

Detecting and tracking human faces in video sequences is useful in a number of applications such as gesture recognition and human-machine interaction. In this paper, we show that online appearance models (holistic approaches) can be used for simultaneously tracking the head, the lips, the eyebrows, and the eyelids in monocular video sequences. Unlike previous approaches to eyelid tracking, we show that the online appearance models can be used for this purpose. Neither color information nor intensity edges are used by our proposed approach. More precisely, we show how the classical appearance-based trackers can be upgraded in order to deal with fast eyelid movements. The proposed eyelid tracking is made robust by avoiding eye feature extraction. Experiments on real videos show the usefulness of the proposed tracking schemes as well as their enhancement to our previous approach.

Stereo geometry from 3D ego-motion streams

This paper addresses the problem of geometry determination of a stereo rig that undergoes general rigid motions. Neither known reference objects nor stereo correspondence are required. With almost no exception, all existing online solutions attempt to recover stereo geometry by first establishing stereo correspondences. We first describe a mathematical framework that allows us to solve for stereo geometry, i.e., the rotation and translation between the two cameras, using only motion correspondence that is far easier to acquire than stereo correspondence. Second, we show how to recover the rotation and present two linear methods, as well as a nonlinear one to solve for the translation. Third, we perform a stability study for the developed methods in the presence of image noise, camera parameter noise, and ego-motion noise. We also address accuracy issues. Experiments with real image data are presented. The work allows the concept of online calibration to be broadened, as it is no longer true that only single cameras can exploit structure-from-motion strategies; even the extrinsic parameters of a stereo rig of cameras can do so without solving stereo correspondence. The developed framework is applicable for estimating the relative three-dimensional (3D) geometry associated with a wide variety of mounted devices used in vision and robotics, by exploiting their scaled ego-motion streams.     

Texture-independent recognition of facial expressions in image snapshots and videos

This paper addresses the static and dynamic recognition of basic facial expressions. It has two main contributions. First, we introduce a view- and texture-independent scheme that exploits facial action parameters estimated by an appearance-based 3D face tracker. We represent the learned facial actions associated with different facial expressions by time series. Second, we compare this dynamic scheme with a static one based on analyzing individual snapshots and show that the former performs better than the latter. We provide evaluations of performance using three subspace learning techniques: linear discriminant analysis, non-parametric discriminant analysis and support vector machines.     

Embedding new observations via sparse-coding for non-linear manifold learning

Non-linear dimensionality reduction techniques are affected by two critical aspects: (i) the design of the adjacency graphs, and (ii) the embedding of new test data—the out-of-sample problem. For the first aspect, the proposed solutions, in general, were heuristically driven. For the second aspect, the difficulty resides in finding an accurate mapping that transfers unseen data samples into an existing manifold. Past works addressing these two aspects were heavily parametric in the sense that the optimal performance is only achieved for a suitable parameter choice that should be known in advance.     

Binocular matching constraints from motion

Structure from motion and structure from stereo are two vision cues for achieving 3D reconstruction. The two cues have complementary strengths; while 3D reconstruction is accurate but correspondence establishment is difficult in the stereo cue, the reverse is true in the motion cue. This paper addresses how to combine the two cues when a stereo pair of cameras are available to capture image data for 3D reconstruction. The work is distinct in that, in contrast with the previous ones, it is not to exploit the redundancy in the image data for boosting the reconstruction accuracy, but to make the two vision cues complementary, preserving their strengths and avoiding their weaknesses. A mechanism is introduced that allows dense motion correspondences in the two separate image streams be transferred to dense binocular correspondences across the image streams, so that 3D can be reconstructed from the latter and accurate reconstruction is possible even with short motions of the stereo rig. Both the stereo correspondences and the motion of the stereo rig are assumed to be unknown in this work. Experiments involving real image data are presented to indicate the feasibility and robustness of the approach.     

Efficient object detection and tracking in video sequences

One of the most important problems in computer vision is the computation of the two-dimensional projective transformation (homography) that maps features of planar objects in different images and videos. This computation is required by many applications such as image mosaicking, image registration, and augmented reality. The real-time performance imposes constraints on the methods used. In this paper, we address the real-time detection and tracking of planar objects in a video sequence where the object of interest is given by a reference image template. Most existing approaches for homography estimation are based on two steps: feature extraction (first step) followed by a combinatorial optimization method (second step) to match features between the reference template and the scene frame. This paper has two main contributions. First, we detect both planar and nonplanar objects via efficient object feature classification in the input images, which is applied prior to performing the matching step. Second, for the tracking part (planar objects), we propose a fast method for the computation of the homography that is based on the transferred object features and their associated local raw brightness. The advantage of the proposed schemes is a fast matching as well as fast and robust object registration that is given by either a homography or three-dimensional pose.     

Facial expression recognition using tracked facial actions: Classifier performance analysis

In this paper, we address the analysis and recognition of facial expressions in continuous videos. More precisely, we study classifiers performance that exploit head pose independent temporal facial action parameters. These are provided by an appearance-based 3D face tracker that simultaneously provides the 3D head pose and facial actions. The use of such tracker makes the recognition pose- and texture-independent. Two different schemes are studied. The first scheme adopts a dynamic time warping technique for recognizing expressions where training data are given by temporal signatures associated with different universal facial expressions. The second scheme models temporal signatures associated with facial actions with fixed length feature vectors (observations), and uses some machine learning algorithms in order to recognize the displayed expression. Experiments quantified the performance of different schemes. These were carried out on CMU video sequences and home-made video sequences. The results show that the use of dimension reduction techniques on the extracted time series can improve the classification performance. Moreover, these experiments show that the best recognition rate can be above 90%.     

A supervised discriminant data representation: application to pattern classification

Neural Computing and Applications - The performance of machine learning and pattern recognition algorithms generally depends on data representation. That is why, much of the current effort in...     

Cooperative Stereo–Motion: Matching and Reconstruction

One of the most interesting goals of computer vision is the 3D structure recovery of scenes. Traditionally, two cues are used: structure from motion and structure from stereo, two subfields with complementary sets of assumptions and techniques. This paper introduces a new general framework of cooperation between stereo and motion. This framework combines the advantages of both cues: (i) easy correspondence from motion and (ii) accurate 3D reconstruction from stereo. First, we show how the stereo matching can be recovered from motion correspondences using only geometric constraints. Second, we propose a method of 3D reconstruction of both binocular and monocular features using all stereo pairs in the case of a calibrated stereo rig. Third, we perform an analysis of the performance of the proposed framework as well as a comparison with an affine method. Experiments involving real and synthetic stereo pairs indicate that rich and reliable information can be derived from the proposed framework. They also indicate that robust 3D reconstruction can be obtained even with short image sequences.     

Object Pose: The Link between Weak Perspective,Paraperspective, and Full Perspective

Recently, DeMenthon and Davis (1992, 1995) proposed a method for determining the pose of a 3-D object with respect to a camera from 3-D to 2-D point correspondences. The method consists of iteratively improving the pose computed with a weak perspective camera model to converge, at the limit, to a pose estimation computed with a perspective camera model. In this paper we give an algebraic derivation of DeMenthon and Davis' method and we show that it belongs to a larger class of methods where the perspective camera model is approximated either at zero order (weak perspective) or first order (paraperspective). We describe in detail an iterative paraperspective pose computation method for both non coplanar and coplanar object points. We analyse the convergence of these methods and we conclude that the iterative paraperspective method (proposed in this paper) has better convergence properties than the iterative weak perspective method. We introduce a simple way of taking into account the orthogonality constraint associated with the rotation matrix. We analyse the sensitivity to camera calibration errors and we define the optimal experimental setup with respect to imprecise camera calibration. We compare the results obtained with this method and with a non-linear optimization method.