3D追跡arXiv:1806.11534
カメラとLIDARを統合した検出ベース3D追跡のエンドツーエンド学習
End-to-end Learning of Multi-sensor 3D Tracking by Detection
カメラとLIDARの両データを活用し、検出とマッチングをエンドツーエンドで学習する線形計画ベースの3D追跡手法を提案し、KITTIで高精度を達成した。
著者: Davi Frossard, Raquel Urtasun
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
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.
