一种基于视频分析的高速公路交通异常事件检测算法  

Highway Abnormal Event Detection Algorithm Based on Video Analysis

作　　者：姚兰 赵永恒 施雨晴 于明鹤 YAO Lan;ZHAO Yong-heng;SHI Yu-qing;YU Ming-he(College of Computer Science and Engineering,Northeastern University,Shenyang 110819,China;College of Software,Northeastern University,Shenyang 110819,China)

机构地区：[1]东北大学计算机科学与工程学院,沈阳110819 [2]东北大学软件学院,沈阳110819

出　　处：《计算机科学》2020年第8期208-212,共5页Computer Science

基　　金：国家自然科学基金(61433008,U1435216)。

摘　　要：交通领域的异常事件检测对于预防和及时处理交通事故有着重要作用。当前大多数交通异常事件检测都是通过人工完成的,耗费了大量的人力,同时实时性也较差。文中针对高速公路的交通场景特点,利用深度学习中的目标检测算法,对视频中的车辆目标进行提取,提出了结合运动特征和表观特征的多目标追踪算法;在此基础上,又提出了一种基于车辆轨迹特征的异常事件检测方法,其中的追踪算法减少了轨迹提取过程对背景环境变化的依赖。在异常事件检测算法中充分结合高速公路实际场景,加入滑动窗口机制,提升了对远距离和复杂场景下异常事件的检测能力。利用面向真实交通视频的数据,与现有的事件检测算法进行对比,实验结果证明,所提方法在事件检测的准确率、召回率和F值指标方面都有良好的性能表现,能够有效地完成高速场景下的交通异常事件检测。Abnormal event detection in a traffic scenario is significant for accident prevention,on-call solution and other applications.While currently,the detection approaches are neither labor efficient,nor real-timing.A multi-target tracking algorithm combining motion characteristics and apparent characteristic for vehicle trace in highway traffic scenario is derived by introducing target detection in deep learning and extracting targets in a video.An abnormal event detection method which is based on vehicle trajectory feature is proposed.The proposed tracking algorithm declines the dependent on background during the procedure of trajectory extraction.The abnormal event detection algorithm is designated adequately for highway scenario with an additional strategy of sliding window to improve the performance on abnormal detection for remote and complex scenes.Through the experiments on practical video repository,the proposed method is compared with existing methods and shows a highlighted performance in the terms of Precision,Recall rate and F-value index.This method turns out to be solid and efficient in abnormal event detection in highway traffic scenario.

关 键 词：视频监控 目标检测 目标追踪 异常事件检测 轨迹特征 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]