Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

被引:94
作者
Qin, Zengyi [1 ]
Wang, Jinglu [2 ]
Lu, Yan [2 ]
机构
[1] Tsinghua Univ, Beijing, Peoples R China
[2] Microsoft Res, Beijing, Peoples R China
来源
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年
关键词
D O I
10.1109/CVPR.2019.00780
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 study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing 3D anchors to explicitly construct object-level correspondences between the regions of interest in stereo images, from which the deep neural network learns to detect and triangulate the targeted object in 3D space. We also introduce a cost-efficient channel reweighting strategy that enhances representational features and weakens noisy signals to facilitate the learning process. All of these are flexibly integrated into a solid baseline detector that uses monocular images. We demonstrate that both the monocular baseline and the stereo triangulation learning network outperform the prior state-of-the-arts in 3D object detection and localization on the challenging KITTI dataset.
引用
收藏
页码:7607 / 7615
页数:9
相关论文
共 32 条
[1]  
[Anonymous], 2017, INT C INT ROB SYST
[2]  
[Anonymous], 2018, CVPR, DOI DOI 10.1109/CVPR.2018.00249
[3]  
[Anonymous], 2016, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2016.169
[4]  
Cai H., 2013, P 9 INT C COMPUTER V, P103
[5]  
Chen X., 2017, CVPR, DOI [DOI 10.1109/CVPR.2017.691, 10.1109/CVPR.2017.691]
[6]  
Chen X, 2015, LECT NOTES BUS INF P, V2015, P424
[7]   Monocular 3D Object Detection for Autonomous Driving [J].
Chen, Xiaozhi ;
Kundu, Kaustav ;
Zhang, Ziyu ;
Ma, Huimin ;
Fidler, Sanja ;
Urtasun, Raquel .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2147-2156
[8]   Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network [J].
Cheng, Xinjing ;
Wang, Peng ;
Yang, Ruigang .
COMPUTER VISION - ECCV 2018, PT XVI, 2018, 11220 :108-125
[9]  
Dai W., 2018, ARXIV181103217
[10]  
Engelcke Martin, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA), P1355, DOI 10.1109/ICRA.2017.7989161