Hierarchical Recurrent Attention Networks for Structured Online Maps

Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 3417-3426

Abstract


In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on vertices, as there exists many ways to draw equivalent polylines. We demonstrate the effectiveness of our method on a 90 km stretch of highway, and show that we can recover the right topology 92% of the time.

Related Material


[pdf]
[bibtex]
@InProceedings{Homayounfar_2018_CVPR,
author = {Homayounfar, Namdar and Ma, Wei-Chiu and Lakshmikanth, Shrinidhi Kowshika and Urtasun, Raquel},
title = {Hierarchical Recurrent Attention Networks for Structured Online Maps},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}