Robot object recognition based on learning and cognition with conceptual space
-
摘要: 针对复杂环境中机器人多类目标识别通常所依托的原始特征空间中数据区分度低、难以直接表达高层次特征知识的挑战性问题,采用概念空间知识表达方法,通过多传感器数据融合与特征提取建立基本特征空间,并运用高斯混合模型表示目标的各种属性,形成具有高层知识特性的概念空间,在此基础上进行高层知识的概念学习,增强多类目标在概念空间中的可区分性.利用支持向量机作为机器人的分类器,实现针对室内环境的多类目标物体的准确识别.实验结果表明:该方法不但有效地获取和表达待识别目标的高层特征知识,而且能有效提高机器人的目标识别与环境感知能力,展现出优越的分类识别性能.Abstract: In view of the challenging issue for robot multi-class object recognition in complex environments with original feature space because those features can only embody some low level knowledge with poor discriminative performance, an approach to robot object recognition was presented based on conceptual space methodology. At first, the basic feature space was built through multi-sensor data fusion and feature extraction, thus gaussian mixture models (GMM) was employed to model objects properties in order to build conceptual space with characteristic of high level knowledge so as to learn the concepts of objects and improve their discriminative performance. Then support vector machine (SVM) was used to carry out multi-class object recognition for robot in indoor clutter environment. The experimental results demonstrate that the proposed method can not only represent the high level knowledge of objects, but also improve the performance of object recognition and environment perception of robot effectively.
-
Key words:
- conceptual space /
- robot /
- multi-class object recognition /
- multi-sensor data fusion
-
[1] Flynn H.Machine learning applied to object recognition in robot search and rescue systems [D].Oxford,England:University of Oxford,2009 [2] 黄荣瑛. 机器人视觉系统模糊识别抓取物算法[J]. 北京航空航天大学学报,2009,35(2):197-200 Huang Rongying.Fuzzy recognition and object-capture algorithm for robot vision systems [J].Journal of Beijing University of Aeronautics and Astronautics,2009,35(2):197-200(in Chinese) [3] Tkach I,Bechar A,Edan Y.Switching between collaboration levels in a human-robot target recognition system [J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2011,41(6):955-967 [4] 韩崇昭,朱洪艳,段战胜,等. 多源信息融合[M]. 北京:清华大学出版社,2006:1-13 Han Chongzhao,Zhu Hongyan,Duan Zhansheng,et al.Multi-source information fusion [M].Beijing:Tsinghua University Press,2006:1-13(in Chinese) [5] Chella A,Frixione M,Gaglio S.Conceptual spaces for computer vision representations [J].Artificial Intelligence Review,2001,16(2):137-152 [6] Kira Z.Inter-robot transfer learning for perceptual classification [C]//van der Hoek,Kaminka,Lespérance,Luck and Sen.Proc of 9th Int Conf on Autonomous Agents and Multiagent Systems.Toronto:IFAAMAS,2010:13-20 [7] Gärdenfors P.Conceptual spaces:the geometry of thought [M].Cambridge:MIT Press,2000 [8] 陈鹏,符德江. 物体识别中的视点问题[J]. 心理科学进展,2006,14(1):12-17 Chen Peng,Fu Dejiang.The viewpoint debates in object recognition [J].Advances in Psychological Science,2006,14(1):12-17(in Chinese) [9] Felzenszwalb P F,Huttenlocher D P.Efficient graph-based image segmentation [J].International Journal of Computer Vision,2004,59(2):167-181 [10] Bishop C M.Pattern recognition and machine learning [M].Singapore:Springer,2006 [11] Chang C C,Lin C J.LIBSVM:a library for support vector machines [J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27 -
点击查看大图
计量
- 文章访问数: 1759
- HTML全文浏览量: 120
- PDF下载量: 562
- 被引次数: 0
下载:
