Semantic Monocular SLAM for Highly Dynamic Environments
Authors:
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 393-400
Abstract
Recent advances in monocular SLAM have enabled real-time capable systems which run robustly under the assumption of a static environment, but fail in presence of dynamic scene changes and motion, since they lack an explicit dynamic outlier handling. We propose a semantic monocular SLAM framework designed to deal with highly dynamic environments, combining feature-based and direct approaches to achieve robustness under challenging conditions. The proposed approach exploits semantic information extracted from the scene within an explicit probabilistic model, which maximizes the probability for both tracking and mapping to rely on those scene parts that do not present a relative motion with respect to the camera. We show more stable pose estimation in dynamic environments and comparable performance to the state of the art on static sequences on the Virtual KITTI and Synthia datasets.Keywords
This publication has 16 references indexed in Scilit:
- The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes2016
- Comparative design space exploration of dense and semi-dense SLAM2016
- Dynamic body VSLAM with semantic constraints2015
- Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction2015
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Mesh Based Semantic Modelling for Indoor and Outdoor Scenes2013
- A benchmark for the evaluation of RGB-D SLAM systems2012
- DTAM: Dense tracking and mapping in real-time2011
- Video-based, real-time multi-view stereoImage and Vision Computing, 2011
- Parallel Tracking and Mapping for Small AR Workspaces2007