Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images

Authors:
  • YCYigit Baran Can
    Yigit Baran Can
  • ALAlexander Liniger
    Alexander Liniger
  • DPDanda Pani Paudel
    Danda Pani Paudel
  • LGLuc Van Gool
    Luc Van Gool

Abstract
Autonomous navigation requires structured representation of the road network and instance-wise identification of the other traffic agents. Since the traffic scene is defined on the ground plane, this corresponds to scene understanding in the bird's-eye-view (BEV). However, the onboard cameras of autonomous cars are customarily mounted horizontally for a better view of the surrounding, making this task very challenging. In this work, we study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image. Moreover, we show that the method can be extended to detect dynamic objects on the BEV plane. The semantics, locations, and orientations of the detected objects together with the road graph facilitates a comprehensive understanding of the scene. Such understanding becomes fundamental for the downstream tasks, such as path planning and navigation. We validate our approach against powerful baselines and show that our network achieves superior performance. We also demonstrate the effects of various design choices through ablation studies. Code: https://github.com/ybarancan/STSU
All Related Versions