.png){kind=icon}
返回
Keypoint Heatmap Guided Self-Supervised Monocular Visual Odometry
.png){kind=icon}
PRE
AI
DOI：10.1007/s10846-022-01685-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual odometry is an important part of visual simultaneous localization and mapping (SLAM) system. In recent years, with the development of deep learning technique, the combination of visual odometry with deep learning has attracted more and more researchers' attentions. Existing deep learning-based monocular visual odometry methods include a large number of calculations of redundant pixels, and they only consider the pose transformation between two adjacent frames, resulting in error accumulations. To solve the above problems, an end-to-end self-supervised monocular visual odometry method based on keypoint heatmap guidance is proposed in this paper. In the process of network training, the keypoint heatmap is used to guide network learning to reduce the influence of redundant pixels. The photometric error based on the pose consistency constraint of image sequence is calculated to reduce the accumulated error in the pose estimation of video sequence. Extensive experimental results on the KITTI visual odometry dataset have fully validated the effectiveness of the proposed method.
Keyword:
Visual SLAM
Visual Odometry
Keypoint heatmap
Pose consistency constraint
期刊
J
IF:
2.8
论文数:
3.8K
被引数:
6.9K
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏AutoMorph: Automated Retinal Vascular Morphology Quantification Via a Deep Learning PipelineAutoMorph: 通过深度学习管道自动量化视网膜血管形态
OAAI
OAAI分享收藏Supramolecular Approaches for Taming the Chemo- and Regiochemistry of C60 Addition Reactions驯服C60加成反应的化学和区域化学的超分子方法
OAAI
OAAI分享收藏
查看更多内容