基于AIS与机器视觉检测的船桥智能避碰系统  

Bridge Intelligent Collision Avoidance System Based on AIS and Machine Vision Detection

作　　者：李红卫 陈业程 LI Hongwei;CHEN Yecheng(Maritime College,Guangdong Communication Polytechnic,Guangzhou 510800,China;Guangdong Ship Automation Engineering Technology Research Center,Guangzhou 510800,China)

机构地区：[1]广东交通职业技术学院海事学院,广州510800 [2]广东省船舶自动化工程技术研究中心,广州510800

出　　处：《船舶标准化工程师》2023年第3期20-23,共4页Ship Standardization Engineer

基　　金：广东省教育厅普通高校重点领域专项项目(2021ZDZX1095);广东省教育厅普通高校特色创新项目(2020KTSCX241);广东省科技创新战略专项资金项目(pdjh2021b0782);校级大学生科技创新项目(GDCP-ZX-2020-001-N2)。

摘　　要：为提高目标识别率,基于自动识别系统(Automatic Identification System,AIS)与机器视觉检测的船桥智能避碰系统,提出针对大背景中微小船舶目标的检测方法,主要包括图像预处理、图像处理和目标识别。试验结果表明:单纯视觉检测目标识别率可达到98.52%,AIS与机器视觉检测设备共同工作情况下识别率可达到100%。研究成果可为船桥智能避碰系统的设计提供一定参考。In order to improve the target recognition rate,an intelligent collision avoidance system for bridges based on automatic identification system(AIS)and machine vision detection is proposed to detect small ship targets in a large background,mainly including image preprocessing,image processing,and target recognition.The experimental results show that the target recognition rate for visual detection alone can reach 98.52%,and the recognition rate can reach 100%when AIS and machine vision detection equipment work together.The research results can provide some references for the design of intelligent collision avoidance system for bridges.

关 键 词：智能避碰 机器视觉检测 微小目标检测 图像处理 

分 类 号：U665.3[交通运输工程—船舶及航道工程]