基于神经网络算法的机坪智能识别系统  

Airport Apron intelligent recognition system based on neural network algorithm

作　　者：冯嵩 吕佳晨 马骏 秦家宝 孙艺东 齐广连 刘然 赵少伟 Feng Song;Lv Jiachen;Ma Jun;Qin Jiabao;SunYidong;Qi Guanglian;Liu Ran;Zhao Shaowei(Tianjin Binhai International Airport,Tianjin,300000;Civil Aviation University of China,Tianjin,300300)

机构地区：[1]天津滨海国际机场,天津300000 [2]中国民航大学,天津300300

出　　处：《电子测试》2020年第20期20-22,共3页Electronic Test

摘　　要：基于安全节能理念,采用深度卷积神经网络算法,设计一套机坪智能识别系统,实现机坪照明智能控制。本系统主要通过神经网络算法,处理机坪高杆灯摄像头图像数据,进而实现根据机坪情况自动控制高杆灯的开关。系统主要工作流程为红外摄像头采集图像数据,经交换机、无线网桥、路由器等网络设备通过RTSP协议将实时图像数据发送到图像处理服务器。图像处理服务器运行神经网络算法,将处理得到的结果通过RS232接口发送给高杆灯自动控制装置,进而完成自动控制高杆灯的任务。Based on the concept of safety and energy saving,a set of apron intelligent recognition system is designed by using deep convolution neural network algorithm to realize the intelligent control of apron lighting.The system mainly uses neural network algorithm to process the camera image data of plateau high pole lamp,and then realizes the automatic control of high pole lamp switch according to the situation of aircraft apron.The main work flow of the system is to collect image data by infrared camera,and send real-time image data to image processing server through RTSP protocol through network devices such as switches,wireless bridges and routers.The image processing server runs the neural network algorithm,and sends the processing results to the automatic control device of high pole lamp through RS232 interface,thus completing the task of automatic control of high pole lamp.

关 键 词：图像处理 RTSP协议 神经网络 RS232 

分 类 号：V351.3[航空宇航科学与技术—人机与环境工程] TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]