Robust Dense Mapping for Large-Scale Dynamic Environments
arXiv:1905.02781 · doi:10.1109/ICRA.2018.8462974
Abstract
We present a stereo-based dense mapping algorithm for large-scale dynamic urban environments. In contrast to other existing methods, we simultaneously reconstruct the static background, the moving objects, and the potentially moving but currently stationary objects separately, which is desirable for high-level mobile robotic tasks such as path planning in crowded environments. We use both instance-aware semantic segmentation and sparse scene flow to classify objects as either background, moving, or potentially moving, thereby ensuring that the system is able to model objects with the potential to transition from static to dynamic, such as parked cars. Given camera poses estimated from visual odometry, both the background and the (potentially) moving objects are reconstructed separately by fusing the depth maps computed from the stereo input. In addition to visual odometry, sparse scene flow is also used to estimate the 3D motions of the detected moving objects, in order to reconstruct them accurately. A map pruning technique is further developed to improve reconstruction accuracy and reduce memory consumption, leading to increased scalability. We evaluate our system thoroughly on the well-known KITTI dataset. Our system is capable of running on a PC at approximately 2.5Hz, with the primary bottleneck being the instance-aware semantic segmentation, which is a limitation we hope to address in future work. The source code is available from the project website (http://andreibarsan.github.io/dynslam).
Presented at IEEE International Conference on Robotics and Automation (ICRA), 2018
References in corpus (3)
Cited by in corpus (23)
- RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation
- CubeSLAM: Monocular 3D Object SLAM
- Track to Reconstruct and Reconstruct to Track
- A Robust Laser-Inertial Odometry and Mapping Method for Large-Scale Highway Environments
- AirDOS: Dynamic SLAM benefits from Articulated Objects
- A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks
- A Unified Framework for Mutual Improvement of SLAM and Semantic Segmentation
- Stereo Camera Visual SLAM with Hierarchical Masking and Motion-state Classification at Outdoor Construction Sites Containing Large Dynamic Objects
- MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM
- RGB-D SLAM in Dynamic Environments Using Point Correlations
- Real-time Scalable Dense Surfel Mapping
- ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
- Removing Dynamic Objects for Static Scene Reconstruction using Light Fields
- Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
- Inferring Distributions Over Depth from a Single Image
- Monocular Outdoor Semantic Mapping with a Multi-task Network
- MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos
- Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
- Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras
- A Light Field Front-end for Robust SLAM in Dynamic Environments
- Convolutional Recurrent Network for Road Boundary Extraction
- Learning to Segment Rigid Motions from Two Frames
- Real-time Identification and Simultaneous Avoidance of Static and Dynamic Obstacles on Point Cloud for UAVs Navigation