Combining Optical Flow and Range Flow to Recover RGBD Sensor Ego-Motion
G.A. Jones · 2013
Abstract—The ego-motion of a moving RGB-Z sensor is computed using combined range flow and optical flow pixel constraints. The emphasis of the work is on computationally cheap yet accurate estimation of inter-frame translation and rotation parameters using a linear small rotation model. To ensure accurate inter-frame motion estimates, an iterative form of the estimator is developed which repeatedly warps the target frame and measures its misalignment with the current frame. Whilst accurate motion estimates are generated from the range flow in well structured scenes, the addition of optical flow enables the system to continue generating reasonable estimates in cases of degenerate scene structure such as when imaging a textured plane. The algorithm is evaluated on the recently published TUB RGB-D Benchmark. Performance is commensurate with alternative methodologies such as SLAM but at a fraction of the computational cost. I.