轨道交通动态异物轨迹追踪与预测研究  

Research on trajectory tracking and prediction of dynamic foreign bodies in rail transit

作　　者：何文韬 徐永能[1] 谭忠磷 HE Wentao;XU Yongneng;TAN Zhonglin(Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学,南京210094

出　　处：《兵器装备工程学报》2022年第9期109-114,共6页Journal of Ordnance Equipment Engineering

基　　金：国家自然科学基金项目(52072214)。

摘　　要：在列车运行过程中轨道上的异物是威胁列车运行安全的不确定性因素,而轨道周围具有移动特性的动态异物是威胁列车运行安全的另一不确定因素。因此,基于机器视觉技术,通过背景差分法对轨道周围的异物进行检测,利用融合混合高斯模型的3帧差分法对动态异物与静态异物进行区分,并采用具有信道和空间可靠性的判别相关滤波跟踪器(CSR-DCF)算法对动态异物的轨迹进行追踪,采用扩展卡尔曼滤波算法对追踪到的轨迹进行分析研究预测轨迹动态异物,使异物入侵检测方法更能满足轨道交通运行安全的需求。In the process of train operation,the foreign bodies on the track will affect the safety of train operation,which is an uncertain factor threatening the safety of train operation.The dynamic foreign bodies with moving characteristics around the track are another uncertain factor threatening the safety of train operation,so it needs to be further studied.Based on the machine vision technology,the foreign bodies around the track were detected by the background difference method.The dynamic foreign bodies and static foreign bodieswere distinguished by the three-frame difference method fused with the Gaussian mixture model.The trajectory of the dynamic foreign bodieswas tracked by the CSR-DCF algorithm,and the tracked trajectory was analyzed and studied by the extended Kalman filter algorithm to obtain the predicted trajectory of the dynamic foreign bodies.This method realized the trajectory tracking and prediction of dynamic foreign bodies in the rail transit,so that the foreign body intrusion detection method can better meet the needs of modern high-speed train operation safety.

关 键 词：轨道交通 动态异物 轨迹追踪 轨迹预测 机器视觉 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] U2[自动化与计算机技术—控制科学与工程]