高速铁路周界入侵视频图像样本库  

Video Image Sample Library of HSR Perimeter Intrusion

作　　者：李传 谢征宇[1,2] 李永玲 秦勇 于格 孙雨萌[1] LI Chuan;XIE Zhengyu;LI Yongling;QIN Yong;YU Ge;SUN Yumeng(School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China;Zhongguancun Video and Security Industry Technology Alliance for Rail Transit,Beijing 100089,China;State Key Lab of Rail Traffic Control&Safety,Beijing Jiaotong University,Beijing 100044,China)

机构地区：[1]北京交通大学交通运输学院,北京100044 [2]中关村轨道交通视频与安全产业技术联盟,北京100089 [3]北京交通大学轨道交通控制与安全国家重点实验室,北京100044

出　　处：《中国铁路》2021年第3期136-143,共8页China Railway

摘　　要：随着高速铁路的大规模建设与运营,视频监控系统在铁路沿线的应用规模越来越庞大,产生的视频数据爆炸性增长。基于图像的目标检测算法能及时发现监控画面中入侵高铁周界的异物,对保证安全运营具有重要意义。通过建设高铁周界入侵视频图像样本库,利用统一的高铁场景视频图像数据、目标检测算法、算法运行环境和算法评价标准,测试不同场景、天气下目标检测算法的功能有效性和现场适用性,为相关部门提供智能分析算法的标准化测试,以推动铁路视频图像分析的快速发展。With the large-scale construction and operation of HSR,the application scale of the video surveillance system has been larger and larger along the railways,and the video data generated is in explosive growth.Image-based target detection algorithm can identify foreign objects intruding HSR perimeter in time,which is of great significance to ensuring safe operation.Through establishing the video image sample library of HSR perimeter intrusion,the functional effectiveness and field applicability of the target detection algorithm are tested under different scenes and weather conditions,by virtue of the unified HSR scene video image data,target detection algorithm,algorithm operation environment and algorithm evaluation standard,to provide the standardized test of the intelligent analysis algorithm for relevant departments,and promote the rapid development of the railway video image analysis.

关 键 词：高速铁路 周界 异物入侵 样本库 目标检测算法 

分 类 号：U298[交通运输工程—交通运输规划与管理]