Knowledge management system National Space Science Center,CAS
| 小行星场景下基于循环卷积网络的位姿估计方法 | |
| Alternative Title | Pose estimation method based on RNN-CNN for asteroid scene |
| 李媛; 彭晓东; 周武根; 李运; 谢文明 | |
| Source Publication | 传感器与微系统
 |
| 2020 | |
| Volume | 39Issue:8Pages:55; AR:2096-2436(2020)39:8<55:XXXCJX>2.0.TX;2-6 |
| ISSN | 2096-2436 |
| Language | 中文 |
| Keyword | 小行星 循环神经网络卷积神经网络(RNN-CNN) 单应性矩阵 位姿估计 asteroid recurrent neural network-convolutional neural network(RNN-CNN) homography matrix pose estimation |
| Abstract | 针对小行星探测绕飞阶段采用视觉导航,小行星表面光照变化会影响视觉图像特征的稳定性而影响相对位姿估计的问题,提出了一个基于单应性矩阵的位姿估计方法。其采用一个基于循环神经网络卷积神经网络(RNN-CNN)的深度学习框架估计单应性矩阵。实验结果表明:该网络提高了光照变化下单应性矩阵估计的精度。通过被用于小行星表面图像序列的位姿估计,证明了该方法的有效性及其在精度和效率方面优于传统方法。 |
| Other Abstract | When using visual and other optical means to navigate during the asteroid exploration flight, the aspherical surface illumination changes will affect the stability of the visual image features,so as to affect the estimation of the relative pose. A pose estimation method based on homography matrix is proposed aiming at this problem. The method realizes estimation of the homography matrix with a deep learning framework based on a recurrent convolutional network-convolutional neural network(RNN-CNN). The experimental results show that the network improves the precision of the homography matrix estimation under illumination variation. The method is applied to estimate poses of the asteroid surface images sequence,which proves the effectiveness of the method and its superiority in precision and efficiency over traditional methods. |
| Indexed By | CSCD |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.nssc.ac.cn/handle/122/7448 |
| Collection | 中国科学院国家空间科学中心 |
| Affiliation | 1.李媛, 中国科学院国家空间科学中心 2.中国科学院大学计算机与控制学院, 北京 3.北京 100190 4.100049, 中国. 5.周武根, 中国科学院国家空间科学中心 6.中国科学院大学计算机与控制学院, 北京 7.北京 100190 8.100049, 中国. 9.彭晓东, 中国科学院国家空间科学中心, 北京 100190, 中国. 10.李运, 中国科学院国家空间科学中心, 北京 100190, 中国. 11.谢文明, 中国科学院国家空间科学中心, 北京 100190, 中国. 12.Li Yuan, National Space Science Center,Chinese Academy of Sciences 13.School of Computer and Control Engineering,University of Chinese Academy of Sciences, Beijing 14.Beijing 100190 15.100049. 16.Zhou Wugen, National Space Science Center,Chinese Academy of Sciences 17.School of Computer and Control Engineering,University of Chinese Academy of Sciences, Beijing 18.Beijing 100190 19.100049. 20.Peng Xiaodong, National Space Science Center,Chinese Academy of Sciences, Beijing 100190, China. 21.Li Yun, National Space Science Center,Chinese Academy of Sciences, Beijing 100190, China. 22.Xie Wenming, National Space Science Center,Chinese Academy of Sciences, Beijing 100190, China. 23.liyuan165@mails.ucas.edu.cn 24.pxd@nssc.ac.cn |
| Recommended Citation GB/T 7714 | 李媛,彭晓东,周武根,等. 小行星场景下基于循环卷积网络的位姿估计方法[J]. 传感器与微系统,2020,39(8):55; AR:2096-2436(2020)39:8<55:XXXCJX>2.0.TX;2-6. |
| APA | 李媛,彭晓东,周武根,李运,&谢文明.(2020).小行星场景下基于循环卷积网络的位姿估计方法.传感器与微系统,39(8),55; AR:2096-2436(2020)39:8<55:XXXCJX>2.0.TX;2-6. |
| MLA | 李媛,et al."小行星场景下基于循环卷积网络的位姿估计方法".传感器与微系统 39.8(2020):55; AR:2096-2436(2020)39:8<55:XXXCJX>2.0.TX;2-6. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment