TSDF-based change detection for consistent long-term dense reconstruction and dynamic object discovery
- 1 May 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5237-5244
Abstract
Robots that are operating for extended periods of time need to be able to deal with changes in their environment and represent them adequately in their maps. In this paper, we present a novel 3D reconstruction algorithm based on an extended Truncated Signed Distance Function (TSDF) that enables to continuously refine the static map while simultaneously obtaining 3D reconstructions of dynamic objects in the scene. This is a challenging problem because map updates happen incrementally and are often incomplete. Previous work typically performs change detection on point clouds, surfels or maps, which are not able to distinguish between unexplored and empty space. In contrast, our TSDF-based representation naturally contains this information and thus allows us to more robustly solve the scene differencing problem. We demonstrate the algorithms performance as part of a system for unsupervised object discovery and class recognition. We evaluated our algorithm on challenging datasets that we recorded over several days with RGB-D enabled tablets. To stimulate further research in this area, all of our datasets are publicly available 3 .Keywords
This publication has 19 references indexed in Scilit:
- Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario2015
- DART: dense articulated real-time tracking with consumer depth camerasAutonomous Robots, 2015
- Chisel: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially Hashed Signed Distance Fields2015
- Floating scale surface reconstructionACM Transactions on Graphics, 2014
- Toward online 3-D object segmentation and mapping2014
- 3D normal distributions transform occupancy maps: An efficient representation for mapping in dynamic environmentsThe International Journal of Robotics Research, 2013
- Toward lifelong object segmentation from change detection in dense RGB-D maps2013
- A survey on Mesh Segmentation TechniquesComputer Graphics Forum, 2008
- Has somethong changed here? Autonomous difference detection for security patrol robots2007
- Dynamic Maps for Long-Term Operation of Mobile Service Robots2005