Rigid scene flow for 3D LiDAR scans
Authors:
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1765-1770
Abstract
The perception of the dynamic aspects of the environment is a highly relevant precondition for the realization of autonomous robot system acting in the real world. In this paper, we propose a novel method for estimating dense rigid scene flow in 3D LiDAR scans. We formulate the problem as an energy minimization problem, where we assume local geometric constancy and incorporate regularization for smooth motion fields. Analyzing the dynamics at point level helps in inferring the fine-grained details of motion. We show results on multiple sequences of the KITTI odometry dataset, where we seamlessly estimate multiple motions pertaining to different dynamic objects. Furthermore, we test our approach on a dataset with pedestrians to show how our method adapts to a case with non-rigid motion. For comparison we use the ground truth from KITTI and show how our method outperforms different ICP-based methods.Keywords
This publication has 15 references indexed in Scilit:
- DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time2015
- Object scene flow for autonomous vehicles2015
- A primal-dual framework for real-time dense RGB-D scene flow2015
- Optical flow modeling and computation: A surveyComputer Vision and Image Understanding, 2015
- Combining 3D Shape, Color, and Motion for Robust Anytime Tracking2014
- Joint self-localization and tracking of generic objects in 3D range data2013
- RGB-D flow: Dense 3-D motion estimation using color and depth2013
- Generative object detection and tracking in 3D range data2012
- 3D scene flow estimation with a rigid motion prior2011
- G2o: A general framework for graph optimization2011