Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Neural Network Based Roadwork Detection for Autonomous Driving

Sebastian Wullrich, Nicolai Steinke, Daniel Goehring

Abstract

Road construction sites create major challenges for both autonomous vehicles and human drivers due to their highly dynamic and heterogeneous nature. This paper presents a real-time system that detects and localizes roadworks by combining a YOLO neural network with LiDAR data. The system identifies individual roadwork objects while driving, merges them into coherent construction sites and records their outlines in world coordinates. The model training was based on an adapted US dataset and a new dataset collected from test drives with a prototype vehicle in Berlin, Germany. Evaluations on real-world road construction sites showed a localization accuracy below 0.5 m. The system can support traffic authorities with up-to-date roadwork data and could enable autonomous vehicles to navigate construction sites more safely in the future.

Deep Neural Network Based Roadwork Detection for Autonomous Driving

Abstract

Road construction sites create major challenges for both autonomous vehicles and human drivers due to their highly dynamic and heterogeneous nature. This paper presents a real-time system that detects and localizes roadworks by combining a YOLO neural network with LiDAR data. The system identifies individual roadwork objects while driving, merges them into coherent construction sites and records their outlines in world coordinates. The model training was based on an adapted US dataset and a new dataset collected from test drives with a prototype vehicle in Berlin, Germany. Evaluations on real-world road construction sites showed a localization accuracy below 0.5 m. The system can support traffic authorities with up-to-date roadwork data and could enable autonomous vehicles to navigate construction sites more safely in the future.

Paper Structure

This paper contains 21 sections, 2 equations, 10 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Implementation
  4. Datasets
  5. ROADWork Dataset (US)
  6. AutoNOMOS Labs Dataset
  7. YOLO Training Setup and Hyperparameter Settings
  8. Technology Infrastructure
  9. System Implementation
  10. Odometry Processing
  11. LiDAR Processing
  12. Camera Processing
  13. Experiments / Evaluation
  14. YOLO Model
  15. Model Improvement via Background Images
  16. ...and 6 more sections

Figures (10)

  • Figure 1: Roadwork objects indicating road construction sites in Germany rsa_mainpage: (a) Barrier; (b) Traffic cone; (c) Left-facing vertical panel ("pass left"); (d) Right-facing vertical panel ("pass right")
  • Figure 2: Dataflow of the roadwork detection system
  • Figure 3: Differing shapes of final roadwork outputs: (a) Unaltered version recorded during driving; (b) Refined version using only convex hull outer points
  • Figure 4: Average confusion matrices from 6-fold cross-validation of the final YOLO model: (a) A confidence threshold of 0.001; (b) A class-specific threshold of 0.75 for barriers and 0.7 for other classes
  • Figure 5: False positive example detected by the final model
  • ...and 5 more figures