High Frame Rate Egomotion Estimation

In this paper, we present an algorithm for doing high frame rate egomotion estimation. We achieve this by using a basis flow model, along with a novel inference algorithm, that uses spatio-temporal gradients, foregoing the computation of the slow and noisy optical flow. The inherent linearity in our model allows us to achieve fine grained parallelism. We demonstrate this by running our algorithm on GPUs to achieve egomotion estimation at 120Hz. Image motion is tightly coupled with the camera egomotion and depth of the scene. Hence, we validate our approach by using the egomotion estimate to compute the depth of a static scene. Our applications are aimed towards autonomous navigation scenarios where, it is required to have a quick estimate of the state of the vehicle, while freeing up computation time for higher level vision tasks. Fig. 1. (a) Input Stream from a high frame rate camera (b) Spatio-temporal gradients as an RGB image, rDx, g-Dy , b-Dt. (c) Learned Dense basis flows corresponding to pitch, yaw and forward motion (e) Platform showing typical motion during autonomous navigation (f) Estimated translational and rotational velocity (g) Recovered translational flow (h) Depth map of the scene. M. Chen, B. Leibe, and B. Neumann (Eds.): ICVS 2013, LNCS 7963, pp. 183–192, 2013. c © Springer-Verlag Berlin Heidelberg 2013 184 N. Srinivasan, R. Roberts, and F. Dellaert