Motion Segmentation Using Spectral Clustering on Indian Road Scenes

Mahtab Sandhu, Sarthak Upadhyay, Madhava Krishna, Shanti Medasani; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

We propose a novel motion segmentation formulation over spatio-temporal depth images obtained from stereo sequences that segments multiple motion models in the scene in an unsupervised manner . The motion segmentation is obtained at frame rates that compete with the speed of the stereo depth computation. This is possible due to a decoupling framework that first delineates spatial clusters and subsequently assigns motion labels to each of these cluster with analysis of a novel motion graph model. A principled computation of the weights of the motion graph that signifies the relative shear and stretch between possible clusters lends itself to a high fidelity segmentation of the motion models in the scene.