检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:杨栋 李超 吴兴华 王椿钧 唐雯 YANG Dong;LI Chao;WU Xinghua;WANG Chunjun;TANG Wen(Graduate School,China Academy of Railway Science,Beijing 100081,China;Institute of Computing Technology,China Academy of Railway Science Corporation Ltd.,Beijing 100081,China)
机构地区:[1]中国铁道科学研究院研究生部,北京100081 [2]中国铁道科学研究院集团有限公司电子计算技术研究所,北京100081
出 处:《计算机测量与控制》2022年第8期25-30,49,共7页Computer Measurement &Control
基 金:中国国家铁路集团有限公司科技研究开发计划课题(N2021X003);国家重点研发计划项目(2020YFF0304100)。
摘 要:针对铁路安检X光图像判图高度依赖人工,时有发生漏检的问题,提出一种基于智能识别技术的铁路安检辅助分析装置;通过采用视频图像接口的硬件设计,解决与安检仪的适配问题;通过采用跟踪进程、分析进程、推送进程的多进程思路设计,解决60 Hz刷新率下的高精度分析显示问题;跟踪进程采用关键点差分算法实现安检X光图像跟踪,分析进程采用改进的残差网络(ResNet)实现特征提取,采用CenterNet算法实现禁限物品检测,推送进程通过检测键盘中断实现报警图像推送;经实验测试,该装置禁限物品识别准确率达92%,显示帧率达60帧/秒,可适配主流品牌安检仪,满足铁路车站安检辅助分析需求。Aiming at the problem that the judgment of railway security inspection X-ray image is highly dependent on manual work and sometimes misses the prohibited articles,a railway security inspection auxiliary analysis device based on intelligent recognition technology is proposed.Through the hardware design of the video image interface,the adapted problem of the security inspection instrument is solved.Through the multi-process designs of tracking process,analyzing process and pushing process,the problem of high-precision analysis and display under 60 Hz of the refresh rate is solved.The tracking process uses the key point difference algorithm to track the security inspection X-ray image,the analysis process uses the improved residual network(ResNet)to extract the features,the CenterNet algorithm is used to detect the prohibited articles,and the push process uses the detection keyboard interrupt to push the alarm image.The experimental test shows that the identification accuracy of items prohibited by the device reaches 92%and the display frame rate is up to 60 fps.It can be adapted to mainstream the majority security inspection instruments,the auxiliary analysis needs of security inspection in railway station is satisfied.
关 键 词:铁路安检 禁限物品检测 图像跟踪 卷积神经网络 辅助分析
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.7