全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

月面自主精确软着陆的景象匹配方法研究

Keywords: 尺度空间,FAST角点,二进制特征,多模板递阶跟踪

Full-Text   Cite this paper   Add to My Lib

Abstract:

为提高月球探测器自主软着陆的落点精度,利用绕月飞行器和着陆探测器下落图像,提出一种基于尺度信息的多模板递阶景象匹配方法.在月面图像尺度空间上快速提取FAST角点,并确定特征点精确尺度、位置和方向.在特征点邻域建立图像块采样模式,通过图像块像素比较形成二进制串特征描述子,利用海明距离(Hammingdistance)进行特征匹配.实验结果表明,目标在尺度缩放、旋转和光照变化等极端条件下,该算法能够实时完成月面着陆目标区域的准确识别和稳定跟踪,实现月球探测器的远距离、高精度自主导引着陆.

References

[1]  Dufournaud Y, Schmid C, Horaud R. Matching imageswith different resolutions[C]//Proceedings of the IEEE Computer Society Conference on CVPR. Hilton Head Island: IEEE Computer Society, 2000:612-618.
[2]  Rosten E, Drummond T. Machine learning for highspeed corner detection[C]//Proceedings of the 9th European Conference on Computer Vision. [S.l.]: ECCV, 2006,3951:430-443.
[3]  Elmar M, Gregory D H, Darius B, et al. Adaptive and generic corner detection based on the accelerated segment test[C]//Proceedings of 11th European Conference on Computer Vision. Crete, Greece: IEEE, 2010:183-196.
[4]  Taylor S, Drummond T. Multiple target localization at over 100 FPS [C]//Proceedings of British Machine Vision Conference. London: IEEE, 2009:216-226.
[5]  Michael C, Vincent L, Christoph S, et al. BRIEF: binary robust independentelementary features[C]//Proceedings of 11th European Conference on Computer Vision. Crete, Greece: IEEE, 2010:778-792.
[6]  周志强,汪渤.尺度不变特征在自寻的电视制导中的应用[J].电光与控制,2009,16(9):6-10. Zhou Zhiqiang, Wang Bo. Application of scale-invariant feature in television homing seeker[J]. Electronics Optics & Control, 2009,16(9):6-10.(in Chinese)
[7]  Bay H, Tuytelaars T. SURF: speeded up robust features[J]. Computer Vision and Image Understanding, 2008,110(3):346-359.
[8]  Ethan R, Vincent R, Kurt K, et al. ORB: an efficient alternative to SIFT or SURF[C] //Proceedings of 13th International Conference on Computer Vision. Spain: IEEE, 2011:2564-2571.
[9]  Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133