一种嫦娥三号高程值的估计方法

doi:10.19665/j.issn1001-2400.2019.02.023

摘要/Abstract

摘要：

针对嫦娥三号所拍摄的图像为近月表图像,未搭载激光高度计,无法获得高程值这一问题,提出一种嫦娥三号高程值估计的方法。该算法是在嫦娥二号多传感器数据的基础上,训练出在图像中的特征描述子与高程值之间对应关系的误差反向传播神经网络模型;然后利用嫦娥三号的高精度图像特点,估计出相应的高程值。实验测试结果表明,这种算法可将高程值估计误差降低到3.94%,因此得到的嫦娥三号高程值具有可靠性,可应用于高精度月球重建。

关键词: 嫦娥三号, 高程值估计, 误差反向传播神经网络, 全月重建

Abstract:

According to the image taken by the Chang’e-3 as a near moon image, the elevation value cannot be obtained without a laser altimeter, and a method to estimate the elevation value of the Chang’e-3 is proposed. The method is based on the “Chang’e-2” multi-sensor data and trains the BP neural network model of the corresponding relationship between the feature descriptors and the elevation values in the image. Then, the corresponding elevation values are estimated using the features of the high precision image of the Chang’e-3. Exxperimental results show that the proposed method can reduce the elevation value estimation error to 3.94%. Therefore, the elevation value of the “Chang’e-3” is reliable and can be applied to high-precision moon reconstruction.

Key words: Chang’e-3, elevation value estimation, back propagation(BP) neural network, moon reconstruction

中图分类号:

TP39

周哲哲,赵萌,石凡,陈胜勇,栾昊. 一种嫦娥三号高程值的估计方法[J]. 西安电子科技大学学报, 2019, 46(2): 139-144.

ZHOU Zhezhe,ZHAO Meng,SHI Fan,CHEN Shengyong,LUAN Hao. Method for estimation of the elevation value of the Chang’e-3[J]. Journal of Xidian University, 2019, 46(2): 139-144.

图/表 6

图1

图2

表1

图3

图4

表2

参考文献 15

[1]	李春来, 刘建军, 任鑫 , 等. 基于嫦娥二号立体影像的全月高精度地形重建[J]. 武汉大学学报(信息科学版), 2018,43(4):485-495. doi: 10.13203/j.whugis20170400
	LI Chunlai, LIU Jianjun, REN Xin , et al. Lunar Global High-precision Terrain Reconstruction Based on Chang’e-2 Stereo Images[J]. Geomatics and Information Science of Wuhan University, 2018,43(4):485-495. doi: 10.13203/j.whugis20170400
[2]	LIU R . The Performance of the Chang’e 3 Lunar Satellite[J]. Aerospace China, 2014,15(1):4-7.
[3]	曹建峰, 张宇, 胡松杰 , 等. 嫦娥三号着陆器精确定位与精度分析[J]. 武汉大学学报(信息科学版), 2016,41(2):274-278. doi: 10.13203/j.whugis20140123
	CAO Jianfeng, ZHANG Yu, HU Songjie , et al. An Analysis of Precise Positionging and Accuracy of the CE-3 Lunarlander Soft Landing[J]. Geomatics and Information Science of Wuhan University, 2016,41(2):274-278. doi: 10.13203/j.whugis20140123
[4]	SILBURT A, ALI-DIB M, ZHU C C , et al. Lunar Crater Identification via Deep Learning[J/OL]. [2018-06-20]. https://arxiv.org/pdf/1803.02192.pdf.
[5]	BARKER M K, MAZARICO E, NEUMANN G A , et al. A New Lunar Digital Elevation Model from the Lunar Orbiter Laser Altimeter and SELENE Terrain Camera[J]. Icarus, 2016,273:346-355. doi: 10.1016/j.icarus.2015.07.039
[6]	KOROKHIN V, VELIKODSKY Y, SHKURATOV Y , et al. Using LROC WAC Data for Lunar Surface Photoclinometry[J]. Planetary and Space Science, 2018,160:120-135. doi: 10.1016/j.pss.2018.05.020
[7]	张兴国, 刘晓磊, 李靖 , 等. BP神经网络下的限速交通标志实时检测识别[J]. 西安电子科技大学学报, 2018,45(5):136-142. doi: 10.3969/j.issn.1001-2400.2018.05.022
	ZHANG Xingguo, LIU Xiaolei, LI Jing , et al. Real-time Detection and Identification of Speed Limit Traffic Signs under the BP Neural Network[J]. Journal of Xidian University, 2018,45(5):136-142. doi: 10.3969/j.issn.1001-2400.2018.05.022
[8]	黎剑兵, 肖潇, 李小平 , 等. 一种新的结合环状区域划分的特征描述子[J]. 西安电子科技大学学报, 2016,43(2):64-69. doi: 10.3969/j.issn.1001-2400.2016.02.012
	LI Jianbing, XIAO Xiao, LI Xiaoping , et al. Local Coordinate Gradient Descriptor Based on Cyclic Division[J]. Journal of Xidian University, 2016,43(2):64-69. doi: 10.3969/j.issn.1001-2400.2016.02.012
[9]	LOWE D G . Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
[10]	LOWE D G . Fitting Parameterized Three-dimensional Models to Images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991,13(5):441-450. doi: 10.1109/34.134043
[11]	续拓, 李洁, 王颖 . 叠加信息熵游走数据聚类算法[J]. 西安电子科技大学学报, 2018,45(4):75-79. doi: 10.3969/j.issn.1001-2400.2018.04.014
	XU Tuo, LI Jie, WANG Ying . Clustering by Samples Movement in the Superposition Information Entropy Field[J]. Journal of Xidian University, 2018,45(4):75-79. doi: 10.3969/j.issn.1001-2400.2018.04.014
[12]	刘雨情, 肖嵩, 李磊 . 在线判别式超像素跟踪算法[J]. 西安电子科技大学学报, 2018,45(3):13-17. doi: 10.3969/j.issn.1001-2400.2018.03.003
	LIU Yuqing, XIAO Song, LI Lei . Online Discriminant Based Superpixel Tracking Method[J]. Journal of Xidian University, 2018,45(3):13-17. doi: 10.3969/j.issn.1001-2400.2018.03.003
[13]	NIELSEN F . Hierarchical Clustering[J]. Psychometrika, 2016,521(1):405-414.
[14]	DE SOUZA R S, MAIO U, BIFFI V , et al. Robust PCA and MIC Statistics of Baryons in Early Minihaloes[J]. Monthly Notices of the Royal Astronomical Society, 2018,440(1):240-248. doi: 10.1093/mnras/stu274
[15]	LIU L X, LIU Y, SHI G X . Evaluation of Quality of Teaching Based on BP Neural Network[J]. Journal of Chemical and Pharmaceutical Research, 2014,6(2):83-88.

编号	SIFT匹配点特征 (x₁,x₂,x₃,…,x₇₃)	匹配点坐标		高程值
编号	SIFT匹配点特征 (x₁,x₂,x₃,…,x₇₃)	左图坐标	右图坐标	高程值
1	(49.4200,16.2600,192,…,66)	(1.19423,2.91739)	(1.5290,3.3337)	(1689.6646)
2	(24.9800,20.4700,64,…,65)	(1.30565,4.69155)	(1.4831,6.5289)	(1417.2866)
3	(1.2025,49.8800,128,…,65)	(2.2391,3.14345)	(1.4806,5.3587)	(1636.9781)
4	(49.3247,64.0700,250,…,64)	(5.8586,3.6801)	(1.4007,6.5266)	(1398.8079)
5	(25.5880,85.3200,230,…,63)	(5.1953,2.4787)	(1.3760,1.3137)	(1559.0171)

算法	相对误差/%	运行时间/s
SURF+BP	13.00	66
SIFT+BP	5.24	50
文中算法	3.94	37