基于机器视觉的车门锁闭状态监测系统设计  

Design of Door Lock Condition Monitoring System Based on Machine Vision

作　　者：兰英[1] 陈建国[1] 温爱红[1] LAN Ying;CHEN Jian-guo;WEN Ai-hong(College of Engineering and Technology,Chengdu University of Technology,Chengdu 614007,China)

机构地区：[1]成都理工大学工程技术学院

出　　处：《仪表技术与传感器》2019年第7期106-108,113,共4页Instrument Technique and Sensor

基　　金：四川省教育厅自然科学一般项目(16ZB0403,17ZB0066);成都理工大学工程技术学院院级基金项目(C122017019)

摘　　要：传统的轨道车门安全监测系统只能监测到驱动电机的参数,而无法实时监测车门的锁闭状态,因此设计了一种基于机器视觉的车门锁闭状态安全监测系统。该系统以树莓派Raspberry Pi-3B开发板为控制核心,利用高清摄像机和闪光灯采集车门关门过程中丝杆上撞块运动的视频和图像信息,经图像去噪算法处理后,将数据发送到服务器端,最终实现对车门锁闭状态的远程监测。实际测试结果表明,系统能有效监测到车门关门时撞块的运动信息,通过设定有效阈值,系统能准确判断出车门锁闭状态。The traditional rail door safety monitoring system can only monitor the parameters of the driving motor,but can not monitor the locking state of the door in real time.Therefore,a safety monitoring system based on machine vision for the locking state of the door was designed.The system used the Raspberry Pi Raspberry Pi-3B development board as the control core,and used HD cameras and flash to capture video and image information of the block motion on the screw during the door closing process.After the image denoising algorithm was processed,the data was sent to the server side,remote monitoring of the locked state of the door was finally achieved.The actual test results show that the system can effectively monitor the movement information of the collision block when the door is closed.By setting the effective threshold,the system can accurately determine the locked state of the door.

关 键 词：机器视觉 树莓派 摄像机 视频图像 

分 类 号：TP934[自动化与计算机技术]