Knowledge Commons of Institute of Automation,CAS
Optical Flow Assisted Monocular Visual Odometry | |
Wan, Yiming1,2![]() ![]() ![]() | |
2020-02 | |
会议名称 | Asian Conference on Pattern Recognition |
会议日期 | 2019.11.26-2019.11.29 |
会议地点 | Auckland, New Zealand |
摘要 | This paper proposes a novel deep learning based approach for monocular visual odometry (VO) called FlowVO-Net. Our approach utilizes CNN to extract motion information between two consecutive frames and employs Bi-directional convolution LSTM (Bi-ConvLSTM) for temporal modelling. ConvLSTM can encode not only temporal information but also spatial correlation, and the bidirectional architecture enables it to learn the geometric relationship from image sequences pre and post. Besides, our approach jointly predicts optical flow as an auxiliary task in a self-supervised way by measuring photometric consistency. Experiment results indicate competitive performance of the proposed FlowVO-Net to the state-of-art methods. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 三维视觉 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39135 |
专题 | 多模态人工智能系统全国重点实验室_机器人视觉 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wan, Yiming,Gao, Wei,Wu, Yihong. Optical Flow Assisted Monocular Visual Odometry[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Optical Flow Assiste(2741KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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