Uber AI, Engineering
End-to-end Learning of Multi-sensor 3D Tracking by Detection
June 1, 2018 / GlobalAbstract
In this paper we propose a novel approach to tracking by detection that can exploit both cameras as well as LIDAR data to produce very accurate 3D trajectories. Towards this goal, we formulate the problem as a linear program that can be solved exactly, and learn convolutional networks for detection as well as matching in an end-to-end manner. We evaluate our model in the challenging KITTI dataset and show very competitive results.
Authors
Davi Frossard, Raquel Urtasun
Conference
ICRA 2018
Full Paper
Uber ATG
Category:
