RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement
Preprint
Abstract
The road network graph is a critical component for downstream tasks in autonomous driving, such as global route planning and navigation. In the past years, road network graphs are usually annotated by human experts manually, which is time-consuming and labor-intensive. To annotate road network graphs effectively and efficiently, automatic algorithms for road network graph detection are demanded. Most existing methods either adopt a post-processing step on semantic segmentation maps to produce road network graphs, or propose graph-based algorithms to directly predict the graphs. However, these works suffer from hard-coded algorithms and inferior performance. To enhance the previous state-of-the-art (SOTA) method RNGDet, we add an instance segmentation head to better supervise the training, and enable the network to leverage multi-scale features of the backbone. Since the new proposed approach is improved from RNGDet, we name it RNGDet++. Experimental results show that our RNGDet++ outperforms baseline methods in terms of almost all evaluation metrics on two large-scale public datasets. Our code and supplementary materials are available at \url{https://tonyxuqaq.github.io/projects/RNGDetPlusPlus/}.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- csBoundary: City-Scale Road-Boundary Detection in Aerial Images for High-Definition MapsIEEE Robotics and Automation Letters, 2022
- Split Depth-Wise Separable Graph-Convolution Network for Road Extraction in Complex Environments From High-Resolution Remote-Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2021
- Topo-Boundary: A Benchmark Dataset on Topological Road-Boundary Detection Using Aerial Images for Autonomous DrivingIEEE Robotics and Automation Letters, 2021
- iCurb: Imitation Learning-Based Detection of Road Curbs Using Aerial Images for Autonomous DrivingIEEE Robotics and Automation Letters, 2021
- The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods TransportationIEEE Robotics & Automation Magazine, 2021
- Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural NetworkIEEE Transactions on Geoscience and Remote Sensing, 2017
- Road Centerline Extraction via Semisupervised Segmentation and Multidirection Nonmaximum SuppressionIEEE Geoscience and Remote Sensing Letters, 2016
- Road Centerline Extraction in Complex Urban Scenes From LiDAR Data Based on Multiple FeaturesIEEE Transactions on Geoscience and Remote Sensing, 2014
- Spectral–Spatial Classification and Shape Features for Urban Road Centerline ExtractionIEEE Geoscience and Remote Sensing Letters, 2013
- Road Network Detection Using Probabilistic and Graph Theoretical MethodsIEEE Transactions on Geoscience and Remote Sensing, 2012