《中国康复理论与实践》

中国康复理论与实践 >

2018 , Vol. 24 >Issue 10: 1210 - 1214

DOI: https://doi.org/10.3969/j.issn.1006-9771.2018.10.016

康复工程与辅助技术

基于视觉信息的智能下肢假肢路况识别

  • 喻贝贝 ,
  • 孟青云 ,
  • 喻洪流 ,
  • 曹武警 ,
  • 赵伟亮
展开
  • 1.上海理工大学康复工程与技术研究所,上海市 200093;
    2.上海健康医学院,上海市 201318;
    3.上海康复器械工程技术研究中心,上海市 200093
喻贝贝(1993-),男,汉族,湖北孝感市人,硕士研究生,主要研究方向：下肢智能控制。

收稿日期: 2018-05-25

  网络出版日期: 2018-10-30

基金资助

1.国家自然科学基金项目(No. 61473193); 2.上海康复器械工程技术研究中心资助项目(No. 15DZ2251700)

收起

Road Condition Identification of Intelligent Lower Limb Prosthesis Based on Visual Information

  • YU Bei-bei ,
  • MENG Qing-yun ,
  • YU Hong-liu ,
  • CAO Wu-jing ,
  • ZHAO Wei-liang
Expand
  • 1. Institute of Rehabilitation Engineering and Technology, University of Shanghai for Science and Technology, Shanghai 200093, China;
    2. Shanghai University of Medicine&Health Sciences, Shanghai 201318, China;;
    3. Shanghai Engineering Research Center of Assistive Devices, Shanghai 200093, China

Received date: 2018-05-25

  Online published: 2018-10-30

Supported by

National Natural Science Foundation of China (No.61473193) and Shanghai Engineering Research Center of Assistive Devices Project (No.15DZ2251700)

Fold

摘要

目的 从纯视觉信息角度出发,对智能膝关节进行路况识别的研究。方法 整个实验环境采用卤素灯照明,使得设定的场景的光亮度和色温变化较小。将机器视觉模块嵌入智能膝关节的控制系统,通过摄像头实时采集路况图像数据,并将所采集的图像进行灰度化处理,利用归一化互相关算法(NCC)进行图像模式匹配,从而识别出对应的路况。结果 通过机器视觉模块识别平地、上/下坡、上/下楼梯5种路况的准确率分别为88.6%、85.3%、78.4%、87.5%、77.9%。识别效果较好,识别时间均在1 s以内,实时性较强。结论 基于纯视觉信息进行智能膝关节假肢路况识别具有有效性和可行性。

关键词： 智能膝关节; 路况识别; 机器视觉; 模式匹配

本文引用格式

喻贝贝 , 孟青云 , 喻洪流 , 曹武警 , 赵伟亮 . 基于视觉信息的智能下肢假肢路况识别[J]. 中国康复理论与实践, 2018 , 24(10) : 1210 -1214 . DOI: 10.3969/j.issn.1006-9771.2018.10.016

Abstract

Objective To carry out a research of terrain recognition on intelligent knee joint from the perspective of pure visual information.Methods The whole experimental environment was illuminated by halogen lamp, which made the brightness and color temperature of the set scene change less. The machine vision module was embedded in the intelligent knee joint control system. The road image data was collected by the camera in real time, and the captured image was processed in grayscale. The normalized cross correlation algorithm (NCC) was used to match the image pattern to identify the corresponding road conditions.Results The accuracy rates of the road vision, up/down hill, and up/down stairs recognized by the machine vision module were 88.6%, 85.3%, 78.4%, 87.5%, and 77.9%, respectively. The recognition effect was good, and the recognition time was within one second, real-time performance was strong.Conclusion The effectiveness and feasibility of intelligent knee joint prosthetic road condition recognition based on pure visual information is proved.

Key words： intelligent knee joint; terrain recognition; machine vision; pattern matching

参考文献

[1] 李瑨,喻洪流,曹武警,等. 智能假腿膝关节的控制方法研究及发展趋势[J]. 中国康复医学杂志, 2017, 32(8): 963-965.
[2] 龙亿. 下肢外骨骼人体运动预测与人机协调控制技术研究[D]. 哈尔滨:哈尔滨工业大学, 2017.
[3] 曹武警,喻洪流,胡杰,等. 基于不同信号源的智能膝关节控制方法研究[J]. 中国康复医学杂志, 2016, 31(10): 1129-1132.
[4] 第二次全国残疾人抽样调查领导小组. 2006年第二次全国残疾人抽样调查主要数据公报[J]. 中国康复理论与实践, 2006, 12(12): 1013.
[5] Xie HL, Liu ZB, Yang JY, et al.Modelling of magnetorheological damper for intelligent bionic leg and simulation of knee joint movement control[J]. Int J Simul Model, 2016, 15(1): 144-156.
[6] 魏艳琴,曹学军,杨平,等. 下肢截肢者穿戴假肢行走能力的评价[J]. 中国康复理论与实践, 2016, 22(7): 855-859.
[7] Sophyn S, Koganezawa K.Above knee prosthesis for ascending/descending stairs with no external energy source[C]. Assistive Robotics: Proceedings of the 18th International Conference on CLAWAR 2015, 2015: 35-42.
[8] 顾洪,李伟达,李娟. 智能膝关节假肢研究现状及发展趋势[J]. 中国康复理论与实践, 2016, 22(9): 1080-1085.
[9] Brantley JA, Luu TP, Nakagome S, et al.Prediction of lower-limb joint kinematics from surface EMG during overground locomotion[C]// IEEE International Conference on Systems, Man, and Cybernetics. IEEE, 2017.
[10] Shell CE, Klute GK, Neptune RR.Identifying classifier input signals to predict a cross-slope during transtibial amputee walking[J]. PLoS One, 2018, 13(2): e0192950.
[11] Gupta R, Agarwal R.Continuous human locomotion identification for lower limb prosthesis control[J]. Csi Transactions on Ict, 2018, 6(1): 17-31.
[12] 张腾宇,兰陟,樊瑜波. 智能膝关节假肢的技术发展与趋势分析[J]. 中国康复医学杂志, 2017, 32(4): 451-453.
[13] 张燕,许京,陈玲玲,等. 基于激光距离传感器的路况识别系统的设计[J]. 激光与红外, 2016, 46(3): 265-270.
[14] Yuan K, Wang Q, Wang L.Fuzzy-logic-based terrain identification with multisensor fusion for transtibial amputees[J]. IEEE/ASME Transactions on Mechatronics, 2014, 20(2): 618-630.
[15] Afzal T, Iqbal K, White G, et al.A method for locomotion mode identification using muscle synergies[J]. IEEE Trans Neural Syst Rehabil Eng, 2017, 25(6): 608-617.
[16] Shahmoradi S, Shouraki SB.A fuzzy sequential locomotion mode recognition system for lower limb prosthesis control[C]// Tehran, Iran: 25th Iranian Conference on Electrical Engineering, 2017.
[17] Liu Z, Lin W, Geng Y, et al.Intent pattern recognition of lower-limb motion based on mechanical sensors[J]. IEEE/CAA Journal of Automatica Sinica, 2017, 4(4): 651-660.
[18] 杨鹏,刘作军,耿艳利,等. 智能下肢假肢关键技术研究进展[J]. 河北工业大学学报, 2013, 42(1): 76-80.
[19] 陈伟,田一明,王喜太. 基于多信号特征和D-S证据理论融合的下肢运动模式识别[J]. 科技创新与应用, 2018(1): 25-27.
[20] 陈华斌,孔萌,吕娜,等. 视觉传感技术在机器人智能化焊接中的研究现状[J]. 电焊机, 2017, 47(3): 1-16.
[21] Cao W, Yu H, Zhao W, et al.Target of physiological gait: Realization of speed adaptive control for a prosthetic knee during swing flexion[J]. Technology & Health Care Official Journal of the European Society for Engineering & Medicine, 2017, 26(1): 1-12.
[22] Abdelkader I, Elsonbaty Y, Elhabrouk M.OpenMV: A python powered, extensible machine vision camera[C]// International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing, 2017.
[23] 赵飞翔,车彦洁. 基于OPENMV的室内扫地小车[J]. 魅力中国, 2017, 51: 168.
[24] 吴鹏,徐洪玲,宋文龙. 结合小波金字塔的快速NCC图像匹配算法[J]. 哈尔滨工程大学学报, 2017, 38(5): 791-796.
[25] 黄真宝,陈阳. 图像匹配中NCC算法的一种快速实现方法[J]. 信息化研究, 2011, 37(2): 48-52.
[26] 张佳恒,马利红,李勇,等. 卤素灯照明光栅衍射共路数字全息显微定量相位成像[J]. 中国激光, 2018(6): 1-11.
Options
文章导航

/

〈 〉