Road Scene Layout Reconstruction Based on CNN and Its Application in Traffic Simulation

Chao Zhu1, Yaochen Li2, Yuehu Liu3, Zhiqiang Tian4, Zhichao Cui2, Chi Zhang5, Xinyu Zhu2

  • 1School of Software Engineering, Xi'an Jiaotong University
  • 2Xi'an Jiaotong University
  • 3Institute Of Artificial Intelligence And Robotics, Xi'An Jiaoton
  • 4School Of Software Engineering, Xi'An Jiaotong University
  • 5Institute of Artificial Intelligence and Robotics, Xi'an Jiaoton

Details

11:00 - 12:30 | Mon 10 Jun | Room 5 | MoAM_P1.12

Session: Poster 1: AV + Vision

Full Text

Digital Library Website

Abstract

In this paper, we propose a road scene prediction framework based on the control points of road boundaries using CNN. Firstly, the image features are extracted and the heatmaps are generated by CNN to locate the control points of road boundaries. The input images are then segmented to specify the scene layout based on the control points. Furthermore, the 3D traffic scene models are constructed. The applications for traffic simulation are then developed. The evaluations and comparisons based on TSD-max dataset and KITT dataset prove the effectiveness of the proposed method.