Deep Continuous Fusion for Multi-sensor 3D Object Detection

被引：687

作者：

Liang, Ming ^{[1
]}

Yang, Bin ^{[1
,2
]}

Wang, Shenlong ^{[1
,2
]}

Urtasun, Raquel ^{[1
,2
]}

机构：

[1] Uber Adv Technol Grp, Pittsburgh, PA 15201 USA

[2] Univ Toronto, Toronto, ON, Canada

来源：

COMPUTER VISION - ECCV 2018, PT XVI | 2018年 / 11220卷

关键词：

3D object detection; Multi-sensor fusion; Autonomous driving;

D O I：

10.1007/978-3-030-01270-0_39

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDAR feature maps at different levels of resolution. Our proposed continuous fusion layer encode both discrete-state image features as well as continuous geometric information. This enables us to design a novel, reliable and efficient end-to-end learnable 3D object detector based on multiple sensors. Our experimental evaluation on both KITTI as well as a large scale 3D object detection benchmark shows significant improvements over the state of the art.

引用

页码：663 / 678

页数：16