Optical Flow for Rigid Multi-Motion Scenes

Citations Over Time

Abstract

We observe that in many applications, the motion present in a scene is well characterized by a small number of (rigid) motion hypotheses. Based on this observation, we present rigid multi-motion optical flow (RMM). By restricting flow to one of several motion hypotheses, RMM produces more accurate optical flow than arbitrary motion models. We evaluate an algorithm based on RMM on a novel synthetic dataset, consisting of 12 photo-realistically rendered scenes containing rigid vehicular motion and a corresponding, exact, ground truth. On this dataset, we demonstrate a substantial advantage of RMM over general-purpose algorithms: going from 36% outliers with the DiscreteFlow algorithm, to 26% with ours, with a mean error reduction from 8.4px to 6.9px. We also perform qualitative evaluation on real-world imagery from traffic cameras.

Related Papers

• → Recovering Motion Fields: An Evaluation of Eight Optical Flow Algorithms(1998)184 cited
• → <title>General motion estimation and segmentation</title>(1990)11 cited
• → A confidence measure for assessing optical flow accuracy in the absence of ground truth(2011)1 cited
• Unsupervised Generation of Optical Flow Datasets(2018)
• → Improved optical flow motion estimation for digital image stabilization(2015)