摄像头移动巡视中对生产工艺区域精准识别算法研究  

Research on Accurate Recognition Algorithm of Production Process Area in Camera Mobile Inspection

作　　者：刘长龙 陈征 张乐 徐元德 王威 张玺亮 蓝飞 LIU Changlong;CHEN Zheng;ZHANG Le;XU Yuande;WANG Wei;ZHANG Xiliang;LAN Fei(Tianjin Branch,CNO00C China Co.,Ltd.,Tianjin 300459;Engineering Technology Branch,CNOOC EnerTech-Drlling&Production Co.,Ltd.,Tianjin 300459)

机构地区：[1]中海石油(中国)有限公司天津分公司,天津300459 [2]中海油能源发展股份有限公司工程技术分公司,天津300459

出　　处：《计算机与数字工程》2024年第12期3735-3743,共9页Computer & Digital Engineering

基　　金：中海石油(中国)有限公司“十三五”科技重点项目“渤海油田稳产3000万吨,上产4000万吨关键技术研究”资助。

摘　　要：海上智能无人化远程监控时,云台摄像头移动巡视中要对智能注采工艺区域的管线、阀门、仪表等设备进行重点监控分析并拍照回传,因此,需要首先对该生产区域进行精准识别,论文设计并实现基于sift角点检测的视频区域重定位算法。首先,使用sift进行图像的角点检测,然后设计实现快速角点匹配策略进行匹配,考虑作业现场实时性需要,对上述两部分使用GPU加速实现,再使用设计的区域重定位算法,重新定位新视角下的区域,最后使用双目视觉进行验证,判断是否重定位正确,如果错误则进行修正。经过实验分析,该算法的重定位准确率为97.5%,目前该算法已部署到作业现场,且运行良好,丰富了平台智能化、数字化手段。During the intelligent unmanned remote monitoring on the sea,the PTZ camera should focus on monitoring and ana-lyzing the pipelines,valves,instruments and other equipment in the intelligent injection and production process area during the mo-bile inspection,and take photos and send them back.Therefore,it is necessary to accurately identify the production area first.This paper designs and implements the video area relocation algorithm based on SIFT corner detection.Firstly,siftis used for image cor-ner detection,and then a fast corner matching strategy is designed and implemented for matching.Considering the real-time needs of the operation site,GPU is used to accelerate the implementation of the above two parts,and then the designed area relocation al-gorithm is used to relocate the area from a new perspective.Finally,binocular vision is used to verify whether the relocation is cor-rect,and if the error is corrected.Through experimental analysis,the relocation accuracy of the algorithm is 97.5%.At present,the algorithm is deployed to the operation site and runs well.It enriches the intelligent and digital means of the plaform.

关 键 词：图像匹配 角点特征 双目验证 图形处理器加速 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]