基于贝叶斯核主成分分析的远距离地形标记方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (14096 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
屠珺, 王明军, 周俊, 李彦明, 刘成良. 基于贝叶斯核主成分分析的远距离地形标记方法[J]. 机器人, 2012, 34(1): 1-8.. TU Jun, WANG Mingjun, ZHOU Jun, LI Yanming, LIU Chengliang. Long-distance Terrain Labeling Based on Bayesian Kernel Principal Component Analysis. ROBOT, 2012, 34(1): 1-8..

摘要由于结构化室外场景外观特征分布存在动态不确定性以及映射偏移特性，因此在室外移动机器人自主导航的过程中采用预确定外观特征并不能非常有效地进行地形标记．为了解决此问题，提出了基于贝叶斯核主成分分析（BKPCA）的远距离地形标记方法．该方法融合了基于贝叶斯公式的聚类中心后验概率，且采用自定义的核函数，实现了原始特征数据结构在低维空间上的保持，能够提取出适合当前场景地形标记的外观特征．实验结果表明，BKPCA模型有效地提高了远距离地形标记的精度．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	屠珺
	王明军
	周俊
	李彦明
	刘成良

关键词 ：地形标记, 移动机器人, 自主导航, 核主成分分析

Abstract：When adopting predetermined appearance features in autonomous navigation of an outdoor mobile robot,terrain labeling may not be effectively done because of the dynamic uncertainty and the mapping deviation of appearance feature distribution in unstructured outdoor scenes.To solve this problem,a long-distance terrain labeling method based on Bayesian kernel principal component analysis(BKPCA) is proposed.The method incorporates the posterior probability of cluster centers using Bayesian formula and employs a self-defined kernel function.The method can implement the maintenance of the original data structure in the low dimensional space and can extract suitable appearance features for current scene labeling. The experimental result validates that the BKPCA model improves accuracy of long-distance terrain labeling.

Key words： terrain labeling mobile robot autonomous navigation kernel principal component analysis

收稿日期: 2011-04-02 录用日期: 2011-12-20

TP24

基金资助:国家863计划资助项目（2010AA101403）；国家自然科学基金资助项目（31071325）

通讯作者: 屠珺 E-mail: coke@sjru.edu.cn

作者简介: 屠珺（1982- ）男，博士．研究领域：机器视觉，模式识别，人工智能．
王明军（1981- ）男，博士．研究领域：机器视觉，模式识别，人工智能．
周俊（1974- ）男，博士，副教授．研究领域：机器视觉，模式识别，人工智能．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2012/V34/I1/1

[1] Matthies L.Stereo vision for planetary rovers:Stochastic modeling to near real-time implementation[J].International Journal of Computer Vision,1992,8(1):71-91.

[2] Pagnot R,Grandjean P.Fast cross-country navigation on fair terrains[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,1995:2593-2598.
[3] Singh S,Simmons R,Smith T,et al.Recent progress in local and global traversability for planetary rovers[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2000:1194-1200.
[4] Rieder A,Southall B,Salgian G,et al.Stereo perception on an off-road vehicle[C]//IEEE Intelligent Vehicle Symposium.Piscataway,NJ,USA:IEEE,2002:221-226.
[5] Ollis M,Huang W H,Happold M,et al.Image-based path planning for outdoor mobile robots[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2008:2723-2728.
[6] Jackel L D,Krotkov E,Perschbacher M,et al.The DARPA LAGR program:Goals,challenges,methodology,and phase I results[J].Journal of Field Robotics,2006,23(11/12):945-973.
[7] Procopio M J,Mulligan J,Grudic G.Learning terrain segmentation with classifier ensembles for autonomous robot navigation in unstructured environments[J].Journal of Field Robotics,2009,26(2):145-175.

[8] Dahlkamp H,Kaehler A,Stavens D,et al.Self-supervised monocular road detection in desert terrain[C/OL]//Proceedings of Robotics:Science and Systems.2006.[2010-09-16].http://robots.stanford.edu/papers/dahlkamp.adaptvision06.pdf.
[9] Happold M,Ollis M,Johnson N.Enhancing supervised terrain classification with predictive unsupervised learning[C/OL]//Proceedings of Robotics:Science and Systems.2006.[2010-09-16].http://www.roboticsproceedings.org/rss02/p06.pdf.
[10] Bajracharya M,Howard A,Matthies L H,et al.Autonomous off-road navigation with end-to-end learning for the LAGR program[J].Journal of Field Robotics,2009,26(1):3-25.

[11] Manduchi R,Castano A,Talukder A,et al.Obstacle detection and terrain classification for autonomous off-road navigation[J].Autonomous Robots,2005,18(1):81-102.

[12] Halatci I,Brooks A,Iagnemma K.Terrain classification and classifier fusion for planetary exploration rovers[C]//IEEE Aerospace Conference.Piscataway,NJ,USA:IEEE,2007:1-11.
[13] Felzenszwalb P F,Huttenlocher D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.

[14] Sridharan M,Stone P.Color learning and illumination invariance on mobile robots:A survey[J].Robotics and Autonomous Systems,2009,57(6/7):629-644.
[15] Leung T,Malik J.Representing and recognizing the visual appearance of materials using three-dimensional textons[J].International Journal of Computer Vision,2001,43(1):29-44.

[16] 王明军,周俊,屠珺,等.基于条件随机场的大范围地形感知框架.机器人,2010,32(3):326-333.Wang M J,Zhou J,Tu J,et al.Long-range terrain perception based on conditional random fields[J].Robot,2010,32(3):326-333.

[17] Güter S,Schraudolph N N,Vishwanathan S V N.Fast iterative kernel principal component analysis[J].Journal of Machine Learning Research,2007,8:1893-1918.
[18] Hui K H,Wang C H.Clustering-based locally linear embedding[C]//19th International Conference on Pattern Recognition.Piscataway,NJ,USA:IEEE,2008:1-4.