基于Rényi散度最大化的多特征闭环检测
|
摘要
相比单特征,多图像特征的组合提供更多的场景判别信息,可以提高检测精度,但需要设计合适的组合准则.文中提出多特征组合的加权方法,把特征组合的闭环检测精度表示为正确匹配和错误匹配的图像对在特征空间中距离分布的Rényi散度,最优特征组合为最大化Rényi散度.分析验证Rényi散度的参数与对应最优特征组合的闭环检测性能之间的关系.实验表明,文中方法可以提高闭环检测精度.当Rényi散度的参数取0.75~1时,最优特征组合性能最佳.
Multiple image features provide more discriminative information of the scenes compared with individual feature,and thus the performance of loop closure detection( LCD) is improved. However,a suitable combination criterion is vital. A weighting method of multiple feature combination is proposed.The accuracy of LCD of the feature combination is expressed as the Rényi divergence of the distance distributions of true matches and false matches in the feature space. The optimal feature combination maximizes the Rényi divergence. The relationship between the parameter of Rényi divergence and the performance of LCD of the optimal feature combination is analyzed and experimentally verified. The experiments show that the proposed method improves the performance of LCD significantly and the best performance is achieved with the parameter of Rényi divergence being from 0.75 to 1.
Multiple image features provide more discriminative information of the scenes compared with individual feature,and thus the performance of loop closure detection( LCD) is improved. However,a suitable combination criterion is vital. A weighting method of multiple feature combination is proposed.The accuracy of LCD of the feature combination is expressed as the Rényi divergence of the distance distributions of true matches and false matches in the feature space. The optimal feature combination maximizes the Rényi divergence. The relationship between the parameter of Rényi divergence and the performance of LCD of the optimal feature combination is analyzed and experimentally verified. The experiments show that the proposed method improves the performance of LCD significantly and the best performance is achieved with the parameter of Rényi divergence being from 0.75 to 1.
引文
[1]CUMMINS M,NEWMAN P.Probabilistic Appearance Based Navigation and Loop Closing//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2007:2042-2048.
[2]ANGELI A,DONCIEUX S,MEYER J A,et al.Real-Time Visual Loop-Closure Detection//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2008:1842-1847.
[3]张国良,姚二亮,汤文俊,等.一种自适应的Graph SLAM鲁棒闭环算法.信息与控制,2015,44(3):316-320,327.(ZHANG G H,YAO E L,TANG W J,et al.An Adaptive Robust Loop Closure Algorithm for Graph SLAM.Information and Control,2015,44(3):316-320,327.)
[4]梁志伟,陈燕燕,朱松豪,等.基于视觉词典的单目视觉闭环检测算法.模式识别与人工智能,2013,26(6):561-570.(LIANG Z W,CHEN Y Y,ZHU S H,et al.Loop Closure Detection Algorithm Based on Monocular Vision Using Visual Dictionary.Pattern Recognition and Artificial Intelligence,2013,26(6):561-570.)
[5]ENGEL J,SCHPS T,CREMERS D,et al.LSD-SLAM:LargeScale Direct Monocular SLAM//Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2014:834-849.
[6]MUR-ARTAL R,MONTIEL J M M,TARDOS J D.ORB-SLAM:A Versatile and Accurate Monocular SLAM System.IEEE Transactions on Robotics,2015,31(5):1147-1163.
[7]CUMMINS M,NEWMAN P.FAB-MAP:Probabilistic Localization and Mapping in the Space of Appearance.International Journal of Robotics Research,2008,27(6):647-665.
[8]MILFORD M J,WYETH G F.Seq SLAM:Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2012:1643-1649.
[9]LOWE D G.Distinctive Image Features from Scale-Invariant Keypoints.International Journal of Computer Vision,2004,60(2):91-110.
[10]VALGREN C,LILIENTHAL A J.SIFT,SURF&Seasons:Appearance-Based Long-Term Localization in Outdoor Environments.Robotics and Autonomous Systems,2010,58(2):149-156.
[11]BAY H,ESS A,TUYTELAARS T,et al.Speeded-Up Robust Features(SURF).Computer Vision and Image Understanding,2008,110(3):346-359.
[12]王云峰,翁秀玲,吴炜,等.基于贪心策略的视觉SLAM闭环检测算法.天津大学学报(自然科学与工程技术版),2017,50(12):1262-1270.(WANG Y F,WENG X L,WU W,et al.Loop Closure Detection Algorithm Based on Greedy Strategy for Visual SLAM.Journal of Tianjin University(Science and Technology),2017,50(12):1262-1270.)
[13]OLIVA A,TORRALBA A.Modeling the Shape of the Scene:A Holistic Representation of the Spatial Envelope.International Journal of Computer Vision,2001,42(3):145-175.
[14]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An Efficient Alternative to SIFT or SURF//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2011:2564-2571.
[15]刘国忠,胡钊政.基于SURF和ORB全局特征的快速闭环检测.机器人,2017,39(1):36-45.(LIU G Z,HU Z Z.Fast Loop Closure Detection Based on Holistic Features from SURF and ORB.Robot,2017,39(1):36-45.)
[16]WANG X L,ZHANG H,PENG G H.A Chordiogram Image Descriptor Using Local Edgels.Journal of Visual Communication and Image Representation,2017,49:129-140.
[17]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classification with Deep Convolutional Neural Networks.Communications of the ACM,2017,60(6):84-90.
[18]JIA Y Q,SHELHAMER E,DONAHUE J,et al.Caffe:Convolutional Architecture for Fast Feature Embedding//Proc of the 22nd ACM International Conference on Multimedia.New York,USA:ACM,2014:675-678.
[19]HOU Y,ZHANG H,ZHOU S L.Convolutional Neural NetworkBased Image Representation for Visual Loop Closure Detection//Proc of the IEEE International Conference on Information and Automation.Washington,USA:IEEE,2015:2238-2245.
[20]WANG X L,PENG G H,ZHANG H.Combining Multiple Image Descriptions for Loop Closure Detection.Journal of Intelligent&Robotic Systems,2017.DOI:10.1007/s10846-017-0755-7.
[21]VAN ERVEN T,HARREMOS P.Rényi Divergence and KullbackLeibler Divergence.IEEE Transactions on Information Theory,2014,60(7):3797-3820.
[22]CAMPOS F M,CORREIA L,CALADO J M F.Robot Visual Localization through Local Feature Fusion:An Evaluation of Multiple Classifiers Combination Approaches.Journal of Intelligent&Robotic Systems,2015,77(2):377-390.
[23]T.N.B.Corporation.The Nordlandsbanen Dataset[DB/OL].[2017-12-15].http://nrkbeta.no/2013/01/15/nordland sbanen-minute-by-minute-season-by-season.
[24]GLOVER A J,MADDERN W P,MILFORD M J,et al.FAB-MAP+Rat SLAM:Appearance-Based SLAM for Multiple Times of Day//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2010:3507-3512.
[2]ANGELI A,DONCIEUX S,MEYER J A,et al.Real-Time Visual Loop-Closure Detection//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2008:1842-1847.
[3]张国良,姚二亮,汤文俊,等.一种自适应的Graph SLAM鲁棒闭环算法.信息与控制,2015,44(3):316-320,327.(ZHANG G H,YAO E L,TANG W J,et al.An Adaptive Robust Loop Closure Algorithm for Graph SLAM.Information and Control,2015,44(3):316-320,327.)
[4]梁志伟,陈燕燕,朱松豪,等.基于视觉词典的单目视觉闭环检测算法.模式识别与人工智能,2013,26(6):561-570.(LIANG Z W,CHEN Y Y,ZHU S H,et al.Loop Closure Detection Algorithm Based on Monocular Vision Using Visual Dictionary.Pattern Recognition and Artificial Intelligence,2013,26(6):561-570.)
[5]ENGEL J,SCHPS T,CREMERS D,et al.LSD-SLAM:LargeScale Direct Monocular SLAM//Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2014:834-849.
[6]MUR-ARTAL R,MONTIEL J M M,TARDOS J D.ORB-SLAM:A Versatile and Accurate Monocular SLAM System.IEEE Transactions on Robotics,2015,31(5):1147-1163.
[7]CUMMINS M,NEWMAN P.FAB-MAP:Probabilistic Localization and Mapping in the Space of Appearance.International Journal of Robotics Research,2008,27(6):647-665.
[8]MILFORD M J,WYETH G F.Seq SLAM:Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2012:1643-1649.
[9]LOWE D G.Distinctive Image Features from Scale-Invariant Keypoints.International Journal of Computer Vision,2004,60(2):91-110.
[10]VALGREN C,LILIENTHAL A J.SIFT,SURF&Seasons:Appearance-Based Long-Term Localization in Outdoor Environments.Robotics and Autonomous Systems,2010,58(2):149-156.
[11]BAY H,ESS A,TUYTELAARS T,et al.Speeded-Up Robust Features(SURF).Computer Vision and Image Understanding,2008,110(3):346-359.
[12]王云峰,翁秀玲,吴炜,等.基于贪心策略的视觉SLAM闭环检测算法.天津大学学报(自然科学与工程技术版),2017,50(12):1262-1270.(WANG Y F,WENG X L,WU W,et al.Loop Closure Detection Algorithm Based on Greedy Strategy for Visual SLAM.Journal of Tianjin University(Science and Technology),2017,50(12):1262-1270.)
[13]OLIVA A,TORRALBA A.Modeling the Shape of the Scene:A Holistic Representation of the Spatial Envelope.International Journal of Computer Vision,2001,42(3):145-175.
[14]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An Efficient Alternative to SIFT or SURF//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2011:2564-2571.
[15]刘国忠,胡钊政.基于SURF和ORB全局特征的快速闭环检测.机器人,2017,39(1):36-45.(LIU G Z,HU Z Z.Fast Loop Closure Detection Based on Holistic Features from SURF and ORB.Robot,2017,39(1):36-45.)
[16]WANG X L,ZHANG H,PENG G H.A Chordiogram Image Descriptor Using Local Edgels.Journal of Visual Communication and Image Representation,2017,49:129-140.
[17]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classification with Deep Convolutional Neural Networks.Communications of the ACM,2017,60(6):84-90.
[18]JIA Y Q,SHELHAMER E,DONAHUE J,et al.Caffe:Convolutional Architecture for Fast Feature Embedding//Proc of the 22nd ACM International Conference on Multimedia.New York,USA:ACM,2014:675-678.
[19]HOU Y,ZHANG H,ZHOU S L.Convolutional Neural NetworkBased Image Representation for Visual Loop Closure Detection//Proc of the IEEE International Conference on Information and Automation.Washington,USA:IEEE,2015:2238-2245.
[20]WANG X L,PENG G H,ZHANG H.Combining Multiple Image Descriptions for Loop Closure Detection.Journal of Intelligent&Robotic Systems,2017.DOI:10.1007/s10846-017-0755-7.
[21]VAN ERVEN T,HARREMOS P.Rényi Divergence and KullbackLeibler Divergence.IEEE Transactions on Information Theory,2014,60(7):3797-3820.
[22]CAMPOS F M,CORREIA L,CALADO J M F.Robot Visual Localization through Local Feature Fusion:An Evaluation of Multiple Classifiers Combination Approaches.Journal of Intelligent&Robotic Systems,2015,77(2):377-390.
[23]T.N.B.Corporation.The Nordlandsbanen Dataset[DB/OL].[2017-12-15].http://nrkbeta.no/2013/01/15/nordland sbanen-minute-by-minute-season-by-season.
[24]GLOVER A J,MADDERN W P,MILFORD M J,et al.FAB-MAP+Rat SLAM:Appearance-Based SLAM for Multiple Times of Day//Proc of the IEEE International Conference on Robotics and Automation.Washington,USA:IEEE,2010:3507-3512.
© 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 |