[1]靳少卫,刘华平,王博文,等.开放环境下未知材质的识别技术[J].智能系统学报,2020,15(5):1020-1027.[doi:10.11992/tis.201903026]
 JIN Shaowei,LIU Huaping,WANG Bowen,et al.Recognition of unknown materials in an open environment[J].CAAI Transactions on Intelligent Systems,2020,15(5):1020-1027.[doi:10.11992/tis.201903026]
点击复制

开放环境下未知材质的识别技术(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第15卷
期数:
2020年5期
页码:
1020-1027
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2020-09-05

文章信息/Info

Title:
Recognition of unknown materials in an open environment
作者:
靳少卫12 刘华平3 王博文12 孙富春3
1. 河北工业大学 省部共建电工装备可靠性与智能化国家重点实验室,天津 300130;
2. 河北工业大学 河北省电磁场与电器可靠性重点实验室,天津 300130;
3. 清华大学 智能技术与系统国家重点实验室,北京 100084
Author(s):
JIN Shaowei12 LIU Huaping3 WANG Bowen12 SUN Fuchun3
1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China;
2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin 300130, China;
3. State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
关键词:
开放环境触觉感知声音数据距离度量支持向量机k-最近邻材质识别分类
Keywords:
open environmenttactile perceptionsound datadistance measurementsupport vector machinek-nearest neighbormaterial recognitionclassification
分类号:
TP391
DOI:
10.11992/tis.201903026
文献标志码:
A
摘要:
针对开放环境下未知物体材质识别的问题,本文提出一种利用欧氏距离区分未知类别和已知类别的物体材质识别方法框架,在该框架下利用支持向量机对物体材质进行识别,分类效果显著。该方法利用距离度量中的欧氏距离与阈值进行比较,距离的均值小于阈值的物体判定为已知类别物体材质,并进行分类;距离大于阈值的物体判定为未知类别物体材质,并利用支持向量机算法进行重新学习识别。本文在慕尼黑工业大学的触觉数据集中的声音数据上进行实验,对比了5种距离度量方法,选择了欧氏距离;与开集稀疏表示分类方法对比,显示出本文提出的方法在声音数据集上具有一定的优势;通过实验选出了合理的阈值,并最终实现了开放环境下识别所有物体材质。实验验证了该框架可以很好地解决开放环境下触觉感知信息的物体材质识别问题。
Abstract:
Considering the problem of unknown object material recognition in an open environment, this paper proposes an object material recognition method framework that uses the Euclidean distance to distinguish unknown and known categories. Under this framework, a support vector machine is used to recognize object materials, and the classification effect is remarkable. This method uses the Euclidean distance in the distance metric to compare the thresholds. Objects whose average distances are less than the threshold are classified as materials of a known class; objects with distances greater than the threshold are classified as materials of an unknown class and use a support vector machine algorithm for re-learning recognition. Experiments are conducted on sound data in a haptic data set by the Technical University of Munich. Five distance measurement methods are compared, and finally, the Euclidean distance is selected. A comparison with the open set sparse representation classification method shows that the method proposed in this paper has certain advantages on the sound data set. A reasonable threshold is selected through experiments, and finally all object materials are recognized in an open environment. Experiments verify that the framework can solve the problem of object material recognition of tactile perception information in an open environment.

参考文献/References:

[1] ZHANG Tao, LI Qing, ZHANG Changshui, et al. Current trends in the development of intelligent unmanned autonomous systems[J]. Frontiers of information technology and electronic engineering, 2017, 18: 68-85.
[2] ZHENG Wendong, LIU Huaping, WANG Bowen, et al. Cross-modal surface material retrieval using discriminant adversarial learning[J]. IEEE transactions on industrial informatics, 2019, 15(9): 4978-4987.
[3] ZHENG Wendong, WANG Bowen, LIU Huaping, et al. Bio-inspired magnetostrictive tactile sensor for surface material recognition[J]. IEEE transactions on magnetics, 2019, 55(7): 4002307.
[4] STRESE M, SCHUWERK C, IEPURE A, et al. Multimodal feature-based surface material classification[J]. IEEE transactions on haptics, 2017, 10(2): 226-239.
[5] NGUYEN H, OSBORN L, ISKAROUS M, et al. Dynamic texture decoding using a neuromorphic multilayer tactile sensor[C]//Proceedings of 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS). Cleveland, USA, 2018: 1-4.
[6] LIU Huaping, GUO Di, SUN Fuchun. Object recognition using tactile measurements: kernel sparse coding methods[J]. IEEE transactions on instrumentation and measurement, 2016, 65(3): 656-665.
[7] DENG Cheng, TANG Xu, YAN Junchi, et al. Discriminative dictionary learning with common label alignment for cross-modal retrieval[J]. IEEE transactions on multimedia, 2016, 18(2): 208-218.
[8] DRIMUS A, KOOTSTRA G, BILBERG A, et al. Design of a flexible tactile sensor for classification of rigid and deformable objects[J]. Robotics and autonomous systems, 2014, 62(1): 3-15.
[9] STRESE M, LEE J Y, SCHUWERK C, et al. A haptic texture database for tool-mediated texture recognition and classification[C]//2014 IEEE International Symposium on Haptic, Audio and Visual Environments and Games (HAVE) Proceedings. Richardson, USA, 2014: 118-123.
[10] 古丽娜孜·艾力木江, 乎西旦·居马洪, 孙铁利, 等. 基于支持向量的最近邻文本分类方法[J]. 智能系统学报, 2018, 13(5): 799-807
GULNAZ Alimjan, HURXIDA Jumahun, SUN Tieli, et al. The nearest neighbor text classification method based on support vector[J]. CAAI transactions on intelligent systems, 2018, 13(5): 799-807
[11] CHE Huimin, DING Bo, WANG Huaimin, et al. IKNN-SVM: a hybrid incremental algorithm for image classification[C]//Proceedings of 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AⅡE 2016). Beijing, China, 2016.
[12] DEMIDOVA L, SOKOLOVA Y. A novel SVM-kNN technique for data classification[C]//Proceedings of 2017 6th Mediterranean Conference on Embedded Computing (MECO). Bar, Montenegro, 2017: 1-4.
[13] STRESE M, BOECK Y, STEINBACH E. Content-based surface material retrieval[C]//2017 IEEE World Haptics Conference (WHC). Munich, Germany, 2017: 352-357.
[14] CAO Jiuwen, ZHAO Tao, WANG Jianzhong, et al. Excavation equipment classification based on improved MFCC features and ELM[J]. Neurocomputing, 2017, 261: 231-241.
[15] 张毅, 谢延义, 罗元, 等. 一种语音特征提取中Mel倒谱系数的后处理算法[J]. 智能系统学报, 2016, 11(2): 208-215
ZHANG Yi, XIE Yanyi, LUO Yuan, et al. Postprocessing method of MFCC in speech feature extraction[J]. CAAI transactions on intelligent systems, 2016, 11(2): 208-215
[16] LIU Huaping, SUN Fuchun, FANG Bin, et al. Multimodal measurements fusion for surface material categorization[J]. IEEE transactions on instrumentation and measurement, 2018, 67(2): 246-256.

备注/Memo

备注/Memo:
收稿日期:2019-03-21。
基金项目:国家自然科学基金重点项目(U1613212);河北省自然科学基金项目(E2017202035)
作者简介:靳少卫,硕士研究生,主要研究方向为磁性材料与器件、触觉感知识别;刘华平,副教授,博士生导师,IEEE SeniorMember、中国人工智能学会理事、中国人工智能学会认知系统与信息处理专业委员会秘书长,主要研究方向为机器人感知、学习与控制、多模态信息融合领域的研究。主持国家自然科学基金项目6项。发表学术论文200余篇;孙富春,教授,博士生导师,IEEE Senior Member、中国人工智能学会理事、中国人工智能学会智能控制与智能管理专业委员会副主任兼秘书长,主要研究方向为智能控制与机器人、非线性与复杂系统的建模与控制、网络控制系统、模式识别与智能系统、目标检测、识别与跟踪技术、多源信息融合。主持国家自然科学基金10余项。发表学术论文300余篇
通讯作者:刘华平.E-mail:hpliu@tsinghua.edu.cn
更新日期/Last Update: 2021-01-15