论文:2014,Vol:32,Issue(5):828-833
引用本文:
淡雪, 岳晓奎, 吴侃之. 航天器视觉导航多尺度B-Harris特征提取算法[J]. 西北工业大学
Dan Xue, Yue Xiaokui, Wu Kanzhi. Applying Multi-Scale B-Harris Algorithm to Vision Based Navigation for Spacecraft[J]. Northwestern polytechnical university

航天器视觉导航多尺度B-Harris特征提取算法
淡雪1,2, 岳晓奎1,2, 吴侃之1,2
1.西北工业大学 航天学院, 陕西 西安 710072;
2.航天飞行动力学技术重点实验室, 陕西 西安 710072
摘要:
在航天器视觉相对导航中,为了能够跟踪目标航天器,并对其的位姿信息进行实时、精确地观测和估计,首先需要针对相关图像建立稳定而快速的特征点提取与匹配算法,而特征点提取和匹配算法的准确性与实时性直接影响了航天器相对位姿的估计精度。针对SIFT算法计算量大,匹配时间长,不能满足航天任务高实时性的问题,提出了B-Harris(Binary Harris)算法,该方法结合SIFT算法的结构思想,通过采用多尺度Harris算子提取具有尺度不变的特征点;同时采用128位二进制描述子建立特征向量,组成B-Harris算法,使得特征点匹配时间大大降低。最后通过与SIFT算法的实验对比,证明了B-Harris算法能够适应航天器发生的旋转、尺度、视角等变化,并且在实时性方面明显优于SIFT特征点算法,能够满足航天任务的实时性要求。
关键词:    B-Harris    SIFT算法    视觉导航   
Applying Multi-Scale B-Harris Algorithm to Vision Based Navigation for Spacecraft
Dan Xue1,2, Yue Xiaokui1,2, Wu Kanzhi1,2
1. College of Astronautics, Northwestern Polytechnical University, Xi'an 710072, China;
2. National Key Laboratory of Aerospace Flight Dynamics, Xi'an 710072, China
Abstract:
A method for designing robust tracking controllers is proposed in this paper for a class of large-scale in-terconnected linear systems with uncertainties and time-delays.If the uncertainties satisfy the matching conditions,we can construct a decentralized tracking controller by using the solution of the Riccati equation.With the decen-tralized controller,the closed-loop system will asymptotically track the reference input,even if the systems containtime-delays in both states and controls.Numerical simulation results and their analysis have demonstrated the effec-tiveness of the approach proposed.
Key words:    B-Harris    SIFT(scale invariant feature transform)    vision-based navigation    algorithms    closed loopsystems    computer simulation    control    controllers    convolution    design    efficiency    eigenvalues andeigenfunctions    feature extraction    invariance    mathematical operctors    navigation    pixed    Riccati e-quations    spacecraft    statistics    Taylor series    time delay   
收稿日期: 2014-03-01     修回日期:
DOI:
基金项目: 国家自然科学基金(10772145);高等学校博士点专项科研基金(20106102110003)资助
通讯作者:     Email:
作者简介: 淡雪(1985-),女,西北工业大学博士研究生,主要从事飞行器动力学与相对导航研究。
相关功能
PDF(376KB) Free
打印本文
把本文推荐给朋友
作者相关文章
淡雪  在本刊中的所有文章
岳晓奎  在本刊中的所有文章
吴侃之  在本刊中的所有文章

参考文献:
[1] Roberto Alonso,John L Crassidis,John L Junkins. Vision-Based Navigation for Formation Flying of Spacecraft[R]∥AIAA-2000-4439
[2] 张淑琴. 空间交会对接测量技术及工程应用[M]. 北京:中国宇航出版社,2005: 17-20Zhang Shuqin. Measurement Technology and Engineering Application of Space Rendezvous and Docking[M]. Beijing: ChinaAstronautic Publishing House,2005: 17-20 (in Chinese)
[3] Moravec H P. Towards Automatic Visual Obstacle Avoidance[C]∥5th International Joint Conference on Artificial Intelligence,1997,584
[4] Beaudet P R. Rotationally Invariant Image Operators[C]∥Fourth International Conference on Pattern Recognition,Tokyo,1978: 579-583
[5] Scharstein D,Szeliski R,Zabih R. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms[J]. In-ternational Journal of Computer Vision,2002,47(1/2/3): 7-42
[6] David G,Lowe Object. Recognition from Local Scale-Invariant Features[C]∥International Conference Computer Vision. Cor-fu,Greece,1999: 1150-1157
[7] David G Lowe. Distinctive Image Features from Scale Invariant Keypoints[J]. Journal of Computer Vision,2004,60 (2): 91-110
[8] Lindeberg T. Scale-Space Theory: A Basic Tool for Analyzing Structures at Different Scales[J]. Journal of Applied Statistics,1994,21(2): 224-270
[9] Harris C,Stephens M. A Combined Corner and Edge Detection[C]∥Processings Fourth Alvey Vision Conference,1988: 189-192
[10] Schmid C,Mohr R,Bauckhage C. Comparing and Evaluating Interest Points[C]∥ICCV,1998: 230-235
[11] Schmid C,Mohr R,Bauckhage C. Evaluation of Interest Point Detectors[J]. International Journal of Computer Vision,2000,37(2): 151-172
[12] Mikolajczyk Krystian,Schmid Cordelia. Indexing Based on Scale Invariant Interest Points[C]∥Proceedings of the 8th IEEE In-ternational Conference of Computer Vision,2001: 525-531
[13] Calonder M,Lepetit V,Strecha C,Fua P. BREIEF: Binary Robust Independent Elementary Features[C]∥11th European Con-ference on Computer Vision,Heraklion,Crete,September 2010: 778-792
[14] Cover T M,Hart P E. Nearest Neighbor Pattern Classification[J]. IEEE Trans on Information Theory 1967,3(1): 21-27