基于帧间差分优化算法的雾天轨道异物检测方法  

Method for Detecting Track Abnormal Objects in Foggy Weather Based on Inter-frame Differential Optimization Algorithm

作　　者：王林峰 万衡 刘子仪 秦娜[2] 黄德青 张一鸣 WANG Linfeng;WAN Heng;LIU Ziyi;QIN Na;HUANG Deqing;ZHANG Yiming(不详;School of Railway Transportation,Shanghai Institute of Technology,201400,Shanghai,China)

机构地区：[1]上海应用技术大学轨道交通学院,上海201400 [2]西南交通大学电气工程学院,成都611756

出　　处：《城市轨道交通研究》2022年第10期192-193,197,共3页Urban Mass Transit

基　　金：国家自然科学基金联合基金项目(U1934221);国家自然科学基金面上项目(61773323);四川省科技计划项目(2019YJ0210);四川省科技计划项目(2019YFG0345)。

摘　　要：针对复杂环境和恶劣天气对轨道异物识别造成的干扰,提出帧间差分优化的雾天轨道异物检测方法。引入分权评价实现多帧连续识别的帧间差分优化算法。将该算法与其他检测算法进行消融试验,验证了优化算法的可行性。Aiming at the interference on abnormal objects recognition caused by complex environment and bad weather,a track abnormal objects detection method in foggy weather based on inter-frame differential optimization is proposed.Decentralized evaluation is introduced to realize the inter-frame differential optimization algorithm of multi-frame continuous recognition.Ablation experiments are performed with this algorithm and other detection algorithms to verify the feasibility of the optimized algorithm.

关 键 词：轨道异物 检测方法 帧间差分优化算法 雾天 

分 类 号：U216.3[交通运输工程—道路与铁道工程]