2015 · 34 citations · 23 references
ComputingComputer Science3D ModelingComputer VisionMachine VisionImage RegistrationImage SegmentationMotion AnalysisMotion EstimationOptical FlowScene UnderstandingMotion RegistrationMotion SegmentationNon-rigid Motion EstimationNon-rigid RegistrationOptical Flow EstimationRigid MotionsScene Flow
We propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid deformations at transitions between the rigid parts of the scene. Thus, the velocity of any point can be computed as a linear combination (interpolation) of the estimated rigid motions, which provides better results than traditional sharp piecewise segmentations. Within a variational framework, the smooth segments of the scene and their corresponding rigid velocities are alternately refined until convergence. A K-means-based segmentation is employed as an initialization, and the number of regions is subsequently adapted during the optimization process to capture any arbitrary number of independently moving objects. We evaluate our approach with both synthetic and real RGB-D images that contain varied and large motions. The experiments show that our method estimates the scene flow more accurately than the most recent works in the field, and at the same time provides a meaningful segmentation of the scene based on 3D motion.
23
A Database and Evaluation Methodology for Optical Flow
Simon Baker, Daniel Scharstein, John Lewis et al. · International Journal of Computer Vision · 2010 · 2.2K citations · Full text
Robust odometry estimation for RGB-D cameras
Christian Kerl, Jürgen Sturm, Daniel Cremers · 2013 · 553 citations
S. Vedula, Simon Baker, Peter Rander et al. · 1999 · 433 citations