小天体探测器着陆图像匹配改进算法
|
摘要
针对小天体探测器着陆图像匹配信息存在数据量大、计算机存储空间有限等问题,提出一种基于改进BRISK和RANSAC的小天体探测器着陆图像匹配算法。首先,在Harris角点检测算法中引入尺度估计和尺度空间,在特征描述子建立阶段改进BRISK算法,提出降低相关性的采样点对选择策略,以减少计算量;然后,利用改进的RANSAC算法去除误匹配。在图像旋转、光照强度、高斯噪声、尺度因子的干扰影响下,仿真分析改进算法与基于BRISK的经典算法的匹配结果。分析结果表明:改进算法减少了计算量和存储空间,并在一定干扰情况下具有鲁棒性,可为后续视觉导航提供有效的陆标信息。
Aiming at the problems of large amount of data and limited storage space in landing image matching information of small celestial body probe,an algorithm based on improved BRISK and RANSAC is proposed.Firstly,scale estimation and scale space are introduced in the Harris corner detection algorithm.In the stage of feature descriptor,a sampling point selection strategy to reduce correlation is proposed to reduce the computational complexity.Under the influence of image rotation,light intensity,Gauss noise and scale factor,the matching results of improved algorithm and the classical algorithm based on BRISK are compared.The analysis results show that the improved algorithm can reduce the computational complexity and storage space.With robustness under certain disturbances,it can provide effective landmark information for subsequent visual navigation.
Aiming at the problems of large amount of data and limited storage space in landing image matching information of small celestial body probe,an algorithm based on improved BRISK and RANSAC is proposed.Firstly,scale estimation and scale space are introduced in the Harris corner detection algorithm.In the stage of feature descriptor,a sampling point selection strategy to reduce correlation is proposed to reduce the computational complexity.Under the influence of image rotation,light intensity,Gauss noise and scale factor,the matching results of improved algorithm and the classical algorithm based on BRISK are compared.The analysis results show that the improved algorithm can reduce the computational complexity and storage space.With robustness under certain disturbances,it can provide effective landmark information for subsequent visual navigation.
引文
[1]T Kubota,T Hashimoto,J Kawaguchi,et al.Navigation,guidance and control of asteroid sample return spacecraft:MUSES-C[J].NEC Research&Development,2001,42(2):188-192
[2]Y Cheng,J K Miller.Autonomous landmark based spacecraft navigation system[C]//Proceedings of the13th AAS/AIAA Spaceflight Mechanics Meeting.Washington D.C.:AIAA,2003:9-13
[3]N Trawny,A I Mourikis,S I Roumeliotis.Visionaided inertial navigation for pin-point landing using observations of mapped landmarks[J].Journal of Field Robotics,2007,24(5):257-378
[4]Steiner T J,Brady T M,Hoffman J A.Graph-based terrain relative navigation with optimal landmark database selection[C]//Proceedings of IEEE Aerospace Conference,2015.New York:IEEE,2015:1-12
[5]Harris C,Stephens M.A combined comer and edge detector[C]//Proceedings of the 4th Alvey Vision Conference.Machester,UK:Blackwel,1988:147-151
[6]S M Smith,M Brady.SUSAN:A new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78
[7]Rosten E,Drummond T.Machine learning for highspeed corner detection[C]//Proceedings of the 9th European Conference on Computer Vision.Berlin Heidelberg:Springer-Verlag,2006:430-443
[8]Lowe D G.Object recognition from local scaleinvariant feature[C]//Proceedings of the Seventh IEEEInternational Conference on Computer Vision.New York:IEEE,2002:1150
[9]Herbert B,Tinne T,Luc V G.SURF:speeded up robust features[C]//Proceedings of Computer VisionECCV.Berlin Heidelberg:Springer-Verlag,2006:404-417
[10]Rublee E,Rabaud V,Konolige K,et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceeding of the International Conference on Computer Vision,2011.New York:IEEE,2011:318-327
[11]Leutenegger S,Chli M,Siegwart R Y.BRISK:binary robust invariant scalable keypoints[C]//Proceedings of the International Conference on Computer Vision,2011.New York:IEEE,2011:2548-2555
[12]Fischler M A,Bolles R C.Random sample consensus:aparadigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395
[13]Lindeberg T.Scale-space theory:a basic tool for analyzing structures at different scales[J].Journal of Applied Statistics,1994,21(2):224-270
[14]许可可,朱文球,郭富禄.基于结构相似的RANSAC改进算法[J].计算机工程与应用,2016,52(12):168-171Xu Keke,Zhu Wenqiu,Guo Fulu.Improved RANSACalgorithm based on structural similarity[J].Computer Engineering and Applications,2016,52(12):168-171(in Chinese)
[15]NASA.Final Eros images:range 700meters[2018-11-10].http://nssdc.gsfc.nasa.gov/planetary/mission/near/near_eros_approach.html.
[2]Y Cheng,J K Miller.Autonomous landmark based spacecraft navigation system[C]//Proceedings of the13th AAS/AIAA Spaceflight Mechanics Meeting.Washington D.C.:AIAA,2003:9-13
[3]N Trawny,A I Mourikis,S I Roumeliotis.Visionaided inertial navigation for pin-point landing using observations of mapped landmarks[J].Journal of Field Robotics,2007,24(5):257-378
[4]Steiner T J,Brady T M,Hoffman J A.Graph-based terrain relative navigation with optimal landmark database selection[C]//Proceedings of IEEE Aerospace Conference,2015.New York:IEEE,2015:1-12
[5]Harris C,Stephens M.A combined comer and edge detector[C]//Proceedings of the 4th Alvey Vision Conference.Machester,UK:Blackwel,1988:147-151
[6]S M Smith,M Brady.SUSAN:A new approach to low level image processing[J].International Journal of Computer Vision,1997,23(1):45-78
[7]Rosten E,Drummond T.Machine learning for highspeed corner detection[C]//Proceedings of the 9th European Conference on Computer Vision.Berlin Heidelberg:Springer-Verlag,2006:430-443
[8]Lowe D G.Object recognition from local scaleinvariant feature[C]//Proceedings of the Seventh IEEEInternational Conference on Computer Vision.New York:IEEE,2002:1150
[9]Herbert B,Tinne T,Luc V G.SURF:speeded up robust features[C]//Proceedings of Computer VisionECCV.Berlin Heidelberg:Springer-Verlag,2006:404-417
[10]Rublee E,Rabaud V,Konolige K,et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceeding of the International Conference on Computer Vision,2011.New York:IEEE,2011:318-327
[11]Leutenegger S,Chli M,Siegwart R Y.BRISK:binary robust invariant scalable keypoints[C]//Proceedings of the International Conference on Computer Vision,2011.New York:IEEE,2011:2548-2555
[12]Fischler M A,Bolles R C.Random sample consensus:aparadigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381-395
[13]Lindeberg T.Scale-space theory:a basic tool for analyzing structures at different scales[J].Journal of Applied Statistics,1994,21(2):224-270
[14]许可可,朱文球,郭富禄.基于结构相似的RANSAC改进算法[J].计算机工程与应用,2016,52(12):168-171Xu Keke,Zhu Wenqiu,Guo Fulu.Improved RANSACalgorithm based on structural similarity[J].Computer Engineering and Applications,2016,52(12):168-171(in Chinese)
[15]NASA.Final Eros images:range 700meters[2018-11-10].http://nssdc.gsfc.nasa.gov/planetary/mission/near/near_eros_approach.html.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |