CAJ | 학술논문

在利用柔性力敏传感器获取动态足底压力分布数据时，能够准确快速自动区分左右脚的数据将极大提升数据的可视性和分析的便利性。为此，提出了一种基于足底压力和脚印外观形状的左右脚动态识别方法。首先，基于足底动力学原理，利用连通域的图像分割算法对足底压力数据进行聚类分析，得到每一步压力脚印的时间和坐标范围；在此基础上进一步分离出完整的单步压力数据；最后利用单步压力数据刻画脚印轮廓，并根据轮廓的外观特征进行左右脚识别。本文提出的方法可应用于步态分析、临床辅助诊断、步态识别等领域。通过108个实测数据样本的测试表明：本文方法的识别率高达94.5%，并具有较好的鲁棒性。
재이용유성력민전감기획취동태족저압력분포수거시，능구준학쾌속자동구분좌우각적수거장겁대제승수거적가시성화분석적편리성。위차，제출료일충기우족저압력화각인외관형상적좌우각동태식별방법。수선，기우족저동역학원리，이용련통역적도상분할산법대족저압력수거진행취류분석，득도매일보압력각인적시간화좌표범위；재차기출상진일보분리출완정적단보압력수거；최후이용단보압력수거각화각인륜곽，병근거륜곽적외관특정진행좌우각식별。본문제출적방법가응용우보태분석、림상보조진단、보태식별등영역。통과108개실측수거양본적측시표명：본문방법적식별솔고체94.5%，병구유교호적로봉성。
Distinguishing the left and right footprint data accurately,rapidly and automatically by using the flexible force-sensitive sensor for acquiring the dynamic plantar pressure distribution data can greatly improve the visibility of data and the convenience of data analysis. Therefore,a novel method for footprints recognition based on the plan?tar pressure and the appearance shape features of the footprint is presented. The concrete implementation steps are as follows. Firstly,on account of the principle of the plantar kinetics,the connected component algorithm is applied to data clustering analysis,the coordinate and time range of the target footprint are obtained at the same time. Then we gain the complete plantar pressure data of each footprint and extract the appearance shape features of them. Fi?nally,footprint recognition is accomplished on the basis of the plantar pressure and the appearance shape features. The proposed method can be applied to many fields,such as gait analysis,clinical diagnosis and gait recognition. Experimental results of 108 samples in normal walking pattern show that the proposed method not only has a high recognition rate (94.5%),but also has strong robustness.