[1]朱文霖,刘华平,王博文,等.基于视-触跨模态感知的智能导盲系统[J].智能系统学报,2020,15(1):33-40.[doi:10.11992/tis.201908015]
 ZHU Wenlin,LIU Huaping,WANG Bowen,et al.An intelligent blind guidance system based on visual-touch cross-modal perception[J].CAAI Transactions on Intelligent Systems,2020,15(1):33-40.[doi:10.11992/tis.201908015]
点击复制

基于视-触跨模态感知的智能导盲系统(/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1期
页码:
33-40
栏目:
学术论文—智能系统
出版日期:
2020-01-01

文章信息/Info

Title:
An intelligent blind guidance system based on visual-touch cross-modal perception
作者:
朱文霖1 刘华平2 王博文1 孙富春2
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. 清华大学 智能技术与系统国家重点实验室, 北京 100084
Author(s):
ZHU Wenlin1 LIU Huaping2 WANG Bowen1 SUN Fuchun2
1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China;
2. State Key Lab. of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
关键词:
盲人用户电子手杖跨模态技术触觉数据集深度学习计算机视觉生成对抗网络
Keywords:
blind userselectronic canecross-modal technologytouchdata setdeep learningcomputer visionGANs
分类号:
TP391.4
DOI:
10.11992/tis.201908015
摘要:
盲人活动援助是盲人日常生活的重要组成部分。这些技术大多用于帮助盲人导航和躲避障碍物,很少有研究将地面信息转换成一种给用户直观感受的触觉信息。为了满足上述需求,本文提出了一种可以提供触觉反馈的盲人辅助地面识别智能导盲杖系统。试图利用深度生成对抗训练的方法来产生振动触觉刺激,使用改进的DiscoGAN训练了我们的端到端生成网络。为了训练我们的网络,构建了视触跨模态数据集GroVib。通过上机实验和实物实验来评估方案的可行性,通过上机实验结果表明参与者通过触觉识别地面的准确率为84.7%,触觉的平均真实感受得分为71.3,在真实场景实验中,参与者只需平均3.35次尝试就可以根据触觉反馈来识别地面。
Abstract:
Blind mobility aid is a primary part of the daily life for blind people. Most of these technologies are used to help them navigate and avoid obstacles, and few researches have been done to convert ground information into tactile sensation that gives the user an intuitive feeling. To meet the above requirements, we proposed an intelligent guided rod system, which can provide tactile feedback to assist the blind to recognize ground information. We attempted to generate the vibrotactile stimuli leveraging the power of deep generative adversarial training. Specifically, we used an improved DiscoGAN training an end-to-end generated network. To train the network, we also built GroVib, a visual touch cross-modal dataset. We set up computer experiments and physical experiments to evaluate the feasibility of the scheme. The results of computer experiments showed that the accuracy rate of the participants in recognizing the ground by tactile sense was 84.7%, and the average real feeling score of tactile sense was 71.3. In real scene experiments, the participants needed only 3.25 times of attempts on average to recognize the ground based on tactile feedback.

参考文献/References:

[1] CHOPRA S, HADSELL R, LECUN Y. Learning a similarity metric discriminatively, with application to face verification[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005:539–546
[2] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, USA, 2014: 2672–2680.
[3] MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv: 1411.1784, 2014.
[4] REED S, AKATA Z, YAN Xinchen, et al. Generative adversarial text to image synthesis[C]//Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York, USA, 2016: 1060–1069.
[5] BAHADIR S K, KONCAR V, KALAOGLU F. Wearable obstacle detection system fully integrated to textile structures for visually impaired people[J]. Sensors and actuators A: physical, 2012, 179: 297–311.
[6] SHIN B S, LIM C S. Obstacle detection and avoidance system for visually impaired people[C]//Proceedings of the 2nd International Workshop on Haptic and Audio Interaction Design. Seoul, South Korea, 2007: 78–85.
[7] BOUSBIA-SALAH M, BETTAYEB M, LARBI A. A navigation aid for blind people[J]. Journal of intelligent & robotic systems, 2011, 64(3/4): 387–400.
[8] HASANUZZAMAN F M, YANG Xiaodong, TIAN Yingli. Robust and effective component-based banknote recognition for the blind[J]. IEEE transactions on systems, man, and cybernetics, part C (applications and reviews), 2012, 42(6): 1021–1030.
[9] GUEST S, DESSIRIER J, MEHRABYAN A. The development and validation of sensory and emotional scales of touch perception[J]. Attention perception & psychophysics, 2011, 73(2): 531–550.
[10] KIM D Y, YI K Y. A user-steered guide robot for the blind[C]//Proceedings of 2008 IEEE International Conference on Robotics and Biomimetics. Bangkok, Thailand, 2009: 114–119.
[11] TIWANA M, REDMOND S, LOVELL N. A review of tactile sensing technologies with applications in biomedical engineering[J]. Sensors and actuators: a physical, 2012, 179(5):17–31.
[12] TANG T J J, LUI W L D, LI W H. Plane-based detection of staircases using inverse depth[C]//Proceedings of 2012 Australasian Conference on Robotics and Automation. New Zealand, 2012: 1–10.
[13] AL KALBANI J, SUWAILAM R B, AL YAFAI A, et al. Bus detection system for blind people using RFID[C]//Proceedings of the 2015 IEEE 8th GCC Conference & Exhibition. Muscat, Oman, 2015: 1–6.
[14] KULKARNI A, BHURCHANDI K. Low cost E-book reading device for blind people[C]//Proceedings of 2015 International Conference on Computing Communication Control and Automation. Pune, India, 2015: 516–520.
[15] THILAGAVATHI B. Recognizing clothes patterns and colours for blind people using neural network[C]//Proceedings of 2015 International Conference on Innovations in Information, Embedded and Communication Systems. Coimbatore, India, 2015: 1–5.
[16] NICHOLLS H, LEE M. A survey of robot tactile sensing technology[J]. The international journal of robotics research, 1989, 8(3):3–30.
[17] STRESE M, SCHUWERK C, IEPURE A, et al. Multimodal feature-based surface material classification[J]. IEEE transactions on haptics, 2017, 10(2): 226–239.
[18] LI Xinwu, LIU Huaping, ZHOU Junfeng, et al. Learning cross-modal visual-tactile representation using ensembled generative adversarial networks[J]. Cognitive computation and systems, 2019, 1(2): 40–44.
[19] ISOLA P, ZHU Junyan, ZHOU Tinghui, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 5967–5976.
[20] ZHU Junyan, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 2242–2251.
[21] KIM T, CHA M, KIM H, et al. Learning to discover cross-domain relations with generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia, 2017: 1857–1865.
[22] GRIFFIN D, LIM J. Signal estimation from modified short-time fourier transform[J]. IEEE transactions on acoustics, speech, and signal processing, 1984, 32(2): 236–243.
[23] UJITOKO Y, BAN Y. Vibrotactile signal generation from texture images or attributes using generative adversarial network[C]//Proceedings of the 11th International Conference on Human Haptic Sensing and Touch Enabled Computer Applications. Pisa, Italy, 2018: 25–36.
[24] HUANG G, WANG D, LAN Y. Extreme learning machines: a survey[J]. International journal of machine learning & cybernetics, 2011, 2(2): 107–122.
[25] LEE K A, HICKS G, NINO-MURCIA G. Validity and reliability of a scale to assess fatigue[J]. Psychiatry research, 1991, 36(3): 291–298.

备注/Memo

备注/Memo:
收稿日期:2019-08-21。
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:朱文霖,男,1994年生,硕士研究生,主要研究方向为新型磁性材料与器件、触觉交互;刘华平,男,1976年生,副教授,博士生导师,主要研究机器人感知、学习与控制,多模态信息融合。利用稀疏编码建立了机器人多模态融合感知与学习框架,在此基础上结合机器人的光学、红外、深度和触觉等不同模态信息开发了一系列多模态稀疏编码方法,并在移动机器人、灵巧机械臂等机器人平台上开展多模态感知融合的方法验证与应用。发表学术论文10余篇;王博文,男,1956年生,教授,博士生导师,主要研究方向为磁致伸缩材料与器件、振动发电技术、磁特性测试技术。承担国家自然科学基金等项目8项(其中主持5项)、省部级科研项目10项(其中主持8项);河北省科学技术突出贡献奖和省科技进步三等奖各1项。获专利授权6项;出版专著2部,发表学术论文200多篇
通讯作者:刘华平.E-mail:hpliu@tsinghua.edu.cn
更新日期/Last Update: 1900-01-01