Joint Self-Supervised Monocular Depth Estimation and SLAM | |
Xing, Xiaoxia1,2; Cai, Yinghao2; Lu, Tao2; Yang, yiping2; Wen, dayong2 | |
2022 | |
会议日期 | Aug. 21-25, 2022 |
会议地点 | Montréal Québec, Canada |
英文摘要 | Classical monocular Simultaneous Localization and Mapping (SLAM) and convolutional neural networks (CNNs) based monocular depth estimation represent two different methods towards reconstructing the 3D geometry of the scene. In this paper, we leverage SLAM and depth estimation for their respective advantages to further improve the performance of both tasks. For SLAM, running pseudo RGBD-SLAM with CNN predicted depths improves the accuracy of visual odometry and mapping compared with the monocular SLAM baseline. For depth estimation, we use 3D scene structures from geometric SLAM to refine the pre-trained monocular depth estimation network to update the model which did not reach the optimum due to the photometric inconsistency. Moreover, the proposed method adds an optional Sparse Auxiliary Network into the original depth estimation network, from which the sparse depth features are dynamically combined with RGB features for predicting depth map. Experimental results on KITTI and TUM RGB-D datasets show that our method achieves state-of-the-art performances on both depth predictions and pose estimations. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48802] |
专题 | 综合信息系统研究中心_视知觉融合及其应用 |
通讯作者 | Cai, Yinghao |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing, China 2.Institute of Automation, Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Xing, Xiaoxia,Cai, Yinghao,Lu, Tao,et al. Joint Self-Supervised Monocular Depth Estimation and SLAM[C]. 见:. Montréal Québec, Canada. Aug. 21-25, 2022. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论