Articulated-Body Tracking Through Anisotropic Edge Detection

Abstract

Abstract. This paper addresses the problem of articulated motion tracking from image sequences. We describe a method that relies on both an explicit parameterization of the extremal contours and on the prediction of the human boundary edges in the image. We combine extremal contour prediction and edge detection in a non linear minimization process. The error function that measures the discrepancy between observed image edges and predicted model contours is minimized using an analytical expression of the Jacobian that maps joint velocities onto extremal contour velocities. In practice, we model people both by their geometry (truncated elliptic cones) and their articulated structure -a kinematic model with 40 rotational degrees of freedom. To overcome the flaws of standard edge detection, we introduce a model-based anisotropic Gaussian filter. The parameters of the anisotropic Gaussian are automatically derived from the kinematic model through the prediction of the extremal contours. The theory is validated by performing full body motion capture from six synchronized video sequences at 30 fps without markers.

A Degenerate Conic-Based Method for a Direct Fitting and 3-D Pose of Cylinders with a Single Perspective View

“…In the man-made mechanical object recognition field, geometrical features like straight lines, circles or cylinders are often encountered and for cylindrical objects, e.g., food cans, missiles, containers, pipes and circular pillars, quadrics of revolution can be thought as important components for object modeling, tracking or grasping. Such visual cue occurs in many areas like assembly, human motion capture [8], mobile robot guidance and in medical image analysis, e.g. for estimating geometrical transformations between fragments of a broken cylindrical structure [17].…”

A New Perceptual Edge Detector in Color Images

“…These derivatives can now be combined in an orientation tensor [9]. From this tensor, an anisotropic gradient and its orientation can be computed respectively with the square root of the largest eigenvalue and its associated eigenvector.…”

“…We have tested our method on color images. The result of the first image is compared with the Gaussian anisotropic edge detector [9], the color Gaussian detector [5], the color Deriche detector [4] and the gPb [1]. The first result (Fig.…”

“…Then to avoid or simplify a difficult geometrical search, many works on perceptual organisation in computer vision have been carried out [8], [12], [11], with the aim of selecting edge points involved in large "perceptual" structures. Independently of these works, new edge detection techniques using anisotropic filtering have been defined [7], [9]. These methods are able to correctly detect large linear structures.…”

“…The method described, involves directional linear filtering by means of recursive filters followed by the computation of an edge operator built with a local directional maximization of the response of the filters. This method is inspired from perceptual organisation works [11], and anisotropic filtering [9]. Paper Organization : In the section 2, we remember first the basics of perceptual organization with saliency networks, and then the basics of anisotropic edge detection with the anisotropic tensor.…”