StereoScan: Dense 3d reconstruction in real-time
Top Cited Papers
- 1 June 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 963-968
- https://doi.org/10.1109/ivs.2011.5940405
Abstract
Accurate 3d perception from video sequences is a core subject in computer vision and robotics, since it forms the basis of subsequent scene analysis. In practice however, online requirements often severely limit the utilizable camera resolution and hence also reconstruction accuracy. Furthermore, real-time systems often rely on heavy parallelism which can prevent applications in mobile devices or driver assistance systems, especially in cases where FPGAs cannot be employed. This paper proposes a novel approach to build 3d maps from high-resolution stereo sequences in real-time. Inspired by recent progress in stereo matching, we propose a sparse feature matcher in conjunction with an efficient and robust visual odometry algorithm. Our reconstruction pipeline combines both techniques with efficient stereo matching and a multi-view linking scheme for generating consistent 3d point clouds. In our experiments we show that the proposed odometry method achieves state-of-the-art accuracy. Including feature matching, the visual odometry part of our algorithm runs at 25 frames per second, while - at the same time - we obtain new depth maps at 3-4 fps, sufficient for online 3d reconstructions.Keywords
This publication has 16 references indexed in Scilit:
- A generative model for 3D urban scene understanding from movable platformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Fast robust large-scale mapping from video and internet photo collectionsISPRS Journal of Photogrammetry and Remote Sensing, 2010
- Visual odometry based on stereo image sequences with RANSAC-based outlier rejection schemePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Piecewise planar and non-planar stereo for urban scene reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Building Rome in a dayPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- MonoSLAM: Real-Time Single Camera SLAMIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Towards Urban 3D Reconstruction from VideoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Efficient Non-Maximum SuppressionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Geometric context from a single imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A solution to the simultaneous localization and map building (SLAM) problemIEEE Transactions on Robotics and Automation, 2001