期刊
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
卷 -, 期 -, 页码 4790-4796出版社
IEEE
DOI: 10.1109/icra.2019.8794415
关键词
-
资金
- National Research Foundation (NRF) Singapore through the Singapore-MIT Alliance for Research and Technology's (FM IRG)
- Singapore MOE Tier 1 grant [R-252-000-637-112]
Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this paper, we propose the 2D3D-MatchNet - an end-to-end deep network architecture to jointly learn the descriptors for 2D and 3D keypoint from image and point cloud, respectively. As a result, we are able to directly match and establish 2D-3D correspondences from the query image and 3D point cloud reference map for visual pose estimation. We create our Oxford 2D-3D Patches dataset from the Oxford Robotcar dataset with the ground truth camera poses and 2D-3D image to point cloud correspondences for training and testing the deep network. Experimental results verify the feasibility of our approach.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据