[1]朱俊,郑文栋,葛泉波,等.基于多帧重建的电阻抗动态成像的触摸跟踪[J].智能系统学报,2024,19(6):1458-1467.[doi:10.11992/tis.202308027]
ZHU Jun,ZHENG Wendong,GE Quanbo,et al.Dynamic imaging of touch tracking based on multi-frame reconstruction in electrical impedance tomography[J].CAAI Transactions on Intelligent Systems,2024,19(6):1458-1467.[doi:10.11992/tis.202308027]
点击复制
ZHU Jun,ZHENG Wendong,GE Quanbo,et al.Dynamic imaging of touch tracking based on multi-frame reconstruction in electrical impedance tomography[J].CAAI Transactions on Intelligent Systems,2024,19(6):1458-1467.[doi:10.11992/tis.202308027]
基于多帧重建的电阻抗动态成像的触摸跟踪
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第6期
页码:
1458-1467
栏目:
学术论文—智能系统
出版日期:
2024-12-05
- Title:
- Dynamic imaging of touch tracking based on multi-frame reconstruction in electrical impedance tomography
- Keywords:
- electrical impedance tomography; tactile sensing; touch tracking; multi-frame; image reconstruction; dynamic imaging; trajectory writing; human-machine interaction
- 分类号:
- TP391
- 摘要:
- 触觉传感对于人机交互非常重要，为提高触摸传感的实时性与精确度，提出一种结合电阻抗成像技术的触摸交互方法。该方法利用多数据帧的动态图像重建方法，通过构建多帧正则化模型，充分挖掘相邻数据帧之间存在的时间相关性信息。为验证该方法的有效性，设计一套压阻式触觉传感系统，该系统采用多层组合结构，能够实现对触摸压力变化的实时响应，并进行了触摸压力的测量、离散触摸跟踪和连续触摸跟踪的实验研究。实验结果表明，与传统的单帧静态成像方法相比，所提出的多帧重建算法能显著减小运动过程中重建图像的位置误差、形变和伪影，与实际触摸位有更高的吻合度，能够为人机交互领域的触摸传感提供一种有效途径。
- Abstract:
- Touch sensing is of considerable importance to human–machine interaction. A touch interaction method integrating electrical impedance tomography (EIT) is proposed to enhance the real-time responsiveness and accuracy of touch sensing in human–machine interaction. This method employs a dynamic image reconstruction approach based on multiple data frames to construct a multiframe regularization model and fully mine the temporal correlation information between adjacent frames. An EIT-based resistive tactile sensing system is also designed to validate the effectiveness of this method. The system, which features a multilayer composite structure, responds to changes in touch pressure in real time. Experiments are conducted to discretely and continuously measure touch pressure and track touch points. Experimental results indicate that, compared with traditional single-frame static imaging methods, the proposed multiframe reconstruction algorithm notably reduces the positional error, deformation, and artifacts in the reconstructed images during motion, achieving a higher degree of conformity with the actual touch positions. This approach offers a promising solution for touch sensing in the field of human–machine interaction.
- 参考文献/References:
-
[1] EROL A, BEBIS G, NICOLESCU M, et al. Vision-based hand pose estimation: a review[J]. Computer vision and image understanding, 2007, 108(1/2): 52-73.
[2] MITRA S, ACHARYA T. Gesture recognition: a survey[J]. IEEE transactions on systems, man, and cybernetics, part C (applications and reviews), 2007, 37(3): 311-324.
[3] BERMAN S, STERN H. Sensors for gesture recognition systems[J]. IEEE transactions on systems, man, and cybernetics, part C (applications and reviews), 2012, 42(3): 277-290.
[4] WU Chenning, SOLEIMANI M. In-water handwriting in multi-medium using electrical impedance imaging[J]. IOP SciNotes, 2020, 1(2): 025001.
[5] CHENG Jingyuan, SUNDHOLM M, ZHOU Bo, et al. Smart-surface: large scale textile pressure sensors arrays for activity recognition[J]. Pervasive and mobile computing, 2016, 30: 97-112.
[6] YOON S H, HUO Ke, ZHANG Yunbo, et al. iSoft: a customizable soft sensor with real-time continuous contact and stretching sensing[C]//Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology. Québec: ACM, 2017: 665–678.
[7] ZHANG Yang, LAPUT G, HARRISON C. Electrick: low-cost touch sensing using electric field tomography[C]//Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Denver: ACM, 2017: 1–14.
[8] ZHANG Yang, HARRISON C. Pulp nonfiction: low-cost touch tracking for paper[C]//Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. Montreal: ACM, 2018: 1–11.
[9] PARK K, PARK H, LEE H, et al. An ERT-based robotic skin with sparsely distributed electrodes: structure, fabrication, and DNN-based signal processing[C]//2020 IEEE International Conference on Robotics and Automation. Paris: IEEE, 2020: 1617-1624.
[10] PARK H, PARK K, MO S, et al. Deep neural network based electrical impedance tomographic sensing methodology for large-area robotic tactile sensing[J]. IEEE transactions on robotics, 2021, 37(5): 1570-1583.
[11] ZHENG Enhao, LI Yuhua, ZHAO Zhiyu, et al. An electrical impedance tomography based interface for human–robot collaboration[J]. IEEE/ASME transactions on mechatronics, 2021, 26(5): 2373-2384.
[12] BARBER D C, BROWN B H. Applied potential tomography[J]. Journal of the British interplanetary society, 1989, 42(7): 391-393.
[13] VAUHKONEN M, VADáSZ D, KARJALAINEN P A, et al. Tikhonov regularization and prior information in electrical impedance tomography[J]. IEEE transactions on medical imaging, 1998, 17(2): 285-293.
[14] ADLER A, GUARDO R. Electrical impedance tomography: regularized imaging and contrast detection[J]. IEEE transactions on medical imaging, 1996, 15(2): 170-179.
[15] GOLDSTEIN T, OSHER S. The split bregman method for L1-regularized problems[J]. SIAM journal on imaging sciences, 2009, 2(2): 323-343.
[16] MA Gang, CHEN Haofeng, WANG Peng, et al. Multi-frame constrained block sparse Bayesian learning for flexible tactile sensing using electrical impedance tomography[J]. IEEE transactions on computational imaging, 2022, 8: 438-448.
[17] ADLER A, ARNOLD J H, BAYFORD R, et al. GREIT: a unified approach to 2D linear EIT reconstruction of lung images[J]. Physiological measurement, 2009, 30(6): S35-S55.
[18] ADLER A, LIONHEART W R B. Uses and abuses of EIDORS: an extensible software base for EIT[J]. Physiological measurement, 2006, 27(5): S25-S42.
[19] ZHENG Wendong, LIU Huaping, GUO Di, et al. Adaptive optimal electrical resistance tomography for large-area tactile sensing[C]//2023 IEEE International Conference on Robotics and Automation. London: IEEE, 2023: 10338-10344.
[20] CHEN Bo, ABASCAL J F P J, SOLEIMANI M. Extended joint sparsity reconstruction for spatial and temporal ERT imaging[J]. Sensors, 2018, 18(11): 4014.
[21] BOYLE A, ARISTOVICH K, ADLER A. Beneficial techniques for spatio-temporal imaging in electrical impedance tomography[J]. Physiological measurement, 2020, 41(6): 064003.
[22] CHENEY M, ISAACSON D, NEWELL J C, et al. NOSER: an algorithm for solving the inverse conductivity problem[J]. International journal of imaging systems and technology, 1990, 2(2): 66-75.
[23] ADLER A, DAI Tao, LIONHEART W R B. Temporal image reconstruction in electrical impedance tomography[J]. Physiological measurement, 2007, 28(7): S1-S11.
[24] GAGNON H, GRYCHTOL B, ADLER A. A comparison framework for temporal image reconstructions in electrical impedance tomography[J]. Physiological measurement, 2015, 36(6): 1093-1107.
[25] PARK K, KIM J. Neural-gas network-based optimal design method for ERT-based whole-body robotic skin[J]. IEEE transactions on robotics, 2022, 38(6): 3463-3478.
[26] PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: machine learning in python[J]. Journal of machine learning research, 2011, 12: 2825-2830.
备注/Memo
收稿日期:2023-8-20。
基金项目:国家自然科学基金国际合作重点项目（62120106005）；中国博士后科学基金项目（2022M711825）.
作者简介:朱俊，硕士研究生，主要研究方向为机器人触觉感知。E-mail：675679019@qq.com;葛泉波，教授，博士生导师，主要研究方向为信息融合、自主无人系统、人机混合系统和机器视觉。主持国家自然科学基金青年基金项目1项。E-mail：geqb@nuist.edu.cn;刘华平，教授，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。主持国家自然科学基金重点项目2项，发表学术论文100余篇。E-mail：hpliu@tsinghua.edu.cn。
通讯作者:刘华平. E-mail：hpliu@tsinghua.edu.cn
更新日期/Last Update:
2024-11-05