Object scene flow for autonomous vehicles
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3061-3070
- https://doi.org/10.1109/cvpr.2015.7298925
Abstract
This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor scenes often decompose into a small number of independently moving objects, we represent each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. This minimal representation increases robustness and leads to a discrete-continuous CRF where the data term decomposes into pairwise potentials between superpixels and objects. Moreover, our model intrinsically segments the scene into its constituting dynamic components. We demonstrate the performance of our model on existing benchmarks as well as a novel realistic dataset with scene flow ground truth. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. Our experiments also reveal novel challenges which cannot be handled by existing methods.Keywords
This publication has 31 references indexed in Scilit:
- Piecewise Rigid Scene FlowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- 3D Traffic Scene Understanding From Movable PlatformsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- A Fully-Connected Layered Model of Foreground and Background FlowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Are we ready for autonomous driving? The KITTI vision benchmark suitePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- 3D scene flow estimation with a rigid motion priorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Stereoscopic Scene Flow Computation for 3D Motion UnderstandingInternational Journal of Computer Vision, 2010
- Unsupervised Learning of Stereo Vision with Monocular CuesPublished by British Machine Vision Association and Society for Pattern Recognition ,2009
- Three-dimensional scene flowIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Three-dimensional scene flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999