摘要
针对现有车辆解锁方式的一系列弊端,设计了一套基于人脸识别的车辆解锁系统。系统分为硬件和软件部分。硬件采用了模块化设计,并可与自动驾驶或高级驾驶辅助系统共用传感器;软件基于深度神经网络,具备人脸识别和活体检测功能。利用基于Raspberry Pi的模拟系统,验证了硬件方案的可行性和算法的有效性。
To solve the problems of existing vehicle-unlocking methods,a vehicle unlocking system based on face recognition was designed.The system consists of hardware and software.The modular hardware scheme could share sensors with autopilot or advanced driver assistance systems;the deep neural networks based software had the function of face recognition and living body detection.The feasibility of the scheme and the effectiveness of the algorithm are verified with a specially designed simulation system on Raspberry Pi.
作者
王振阳
程志伟
黄宏成
刘彦博
时良仁
Wang Zhenyang;Cheng Zhiwei;Huang Hongcheng;Liu Yanbo;Shi Liangren(National Engineering Laboratory of Automotive Electronics Control Technology,Shanghai Jiao Tong University,Shanghai 200240,China;Student Innovation Center,Shanghai Jiao Tong University,Shanghai 200240,China)
出处
《传动技术》
2019年第3期62-64,共3页
Drive System Technique
关键词
模式识别
人脸识别
车辆解锁
深度学习
pattern recognition
face recognition
vehicle unlocking
deep learning