Manufactured Object Sub-Segmentation based on Reflection Motion Estimation

In computer vision, reflection is a long-standing problem, it covers image textures, makes original color difficult to recognize, complicates the understanding of the scene. Most of the time, it is considered as ``noise''. Many methods are proposed in order to reduce or delete the reflection effects in the image, but generally, the performances are not quite satisfactory. While instead of working on ``de-noising'', we propose a method to take advantage of moving reflections that can be used for different computer vision applications. For instance, the segmentation of reflective manufactured objects is presented in this paper. We focus on tracking reflection components and segmenting continuous surfaces of the object by taking motion information into account. In this paper, a comparison with several conventional segmentation methods is proposed to illustrate how our approach significantly improves the segmentation results.