OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
arXiv:1903.07918 · doi:10.1109/IROS40897.2019.8968094
Abstract
We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. We employ a triplet loss function for training and use a hard-negative mining strategy to further increase the performance of our descriptor extractor. In an evaluation on the NCLT and KITTI datasets, we demonstrate that our method outperforms related state-of-the-art approaches based on both data-driven and handcrafted data representation in challenging long-term outdoor conditions.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- SegMatch: Segment based loop-closure for 3D point clouds
- Vehicle Detection from 3D Lidar Using Fully Convolutional Network
- SegMap: 3D Segment Mapping using Data-Driven Descriptors
- LocNet: Global localization in 3D point clouds for mobile vehicles
- Image similarity using Deep CNN and Curriculum Learning
Cited by in corpus (13)
- OverlapNet: Loop Closing for LiDAR-based SLAM
- Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems
- AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition
- Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments
- FRAME: Fast and Robust Autonomous 3D point cloud Map-merging for Egocentric multi-robot exploration
- FRAME: A Modular Framework for Autonomous Map Merging: Advancements in the Field
- RecNet: An Invertible Point Cloud Encoding through Range Image Embeddings for Multi-Robot Map Sharing and Reconstruction
- An Addendum to NeBula: Towards Extending TEAM CoSTAR's Solution to Larger Scale Environments
- An experimental evaluation of Siamese Neural Networks for robot localization using omnidirectional imaging in indoor environments
- Redundant and Loosely Coupled LiDAR-Wi-Fi Integration for Robust Global Localization in Autonomous Mobile Robotics
- Infrastructure Node-based Vehicle Localization for Autonomous Driving
- DiSCO: Differentiable Scan Context with Orientation
- Place recognition survey: An update on deep learning approaches