基于多传感器的电动轮椅驾驶状态检测  

Driving Status Detection of Electric Wheelchairs Based on Multiple Sensors

作　　者：赵有鹏 赵伟军 柯旭 蒋宇 ZHAO Youpeng;ZHAO Weijun;KE Xu;JIANG Yu(School of Mechanical Engineering,Nanjing Institute of Technology,Nanjing,Jiangsu 211167,China;Technical Center of Nanjing Kangni Electromechanical Co.,Ltd.,Nanjing,Jiangsu 210038,China)

机构地区：[1]南京工程学院机械工程学院,江苏南京211167 [2]南京康尼机电股份有限公司,江苏南京210038

出　　处：《自动化应用》2023年第21期162-165,共4页Automation Application

摘　　要：电动轮椅的主要用户为老年及残障人士,这类人因认知和体能衰退,在驾驶时易疲劳、注意力不集中,有较高的驾驶风险。为提升电动轮椅的驾驶安全性,本文提出了一种基于多特征融合的驾驶状态检测方法。该方法通过惯性传感器和单目相机采集驾驶者的头部姿态和面部图像,提取头部、眼部特征,融合数据,最后利用多特征联合判定驾驶状态是否处于疲劳、分心状态。实验结果表明,电动轮椅驾驶状态检测系统具有良好的识别效果。The main users of electric wheelchairs are elderly and disabled individuals,who are prone to fatigue and lack of concentration during driving due to cognitive and physical decline,and have a high driving risk.To improve the driving safety of electric wheelchairs,this paper proposes a driving state detection method based on multi feature fusion.This method collects the driver's head posture and facial images through inertial sensors and monocular cameras,extracts head and eye features,fuses data,and finally uses multiple features to jointly determine whether the driving state is in a state of fatigue or distraction.Through driving experiments,it has been shown that the electric wheelchair driving status detection system has good recognition performance.

关 键 词：电动轮椅 多传感器融合 驾驶状态检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]