An Altered Image Alignment Technique for 3D Motion Estimation of a Reflective Sphere

Abstract

Recovering 3D motion of reflective objects in image sequences is still a cumbersome problem for computer vision. One common approach is to track geometric features of the object such as contours and edges since they are rather insensitive to light reflections. However, such basic features fail to recover the actual 3D motion in some cases. For example, the external contour of a sphere rotating about one of its axes remains static in the image. In this paper, we propose a new approach to 3D motion recovery of a reflective sphere visible in an image sequence. Instead of tracking only geometric features, our technique makes use of texture information in a slightly modified image alignment method. Unlike in classical image alignment methods, texture information is processed differently whether it comes from a diffuse or a specular light component. Using this technique, we show that motion estimation is not only possible when dealing with reflective objects, but also that specular components can offer information about the 3D motion. Finally, we present some results obtained from the analysis of image sequences.