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:雷承学 申彩英[1] 王佳馨 于睿烨 LEI Chengxue;SHEN Caiying;WANG Jiaxin;YU Ruiye(Automobile and Traffic Engineering,Liaoning University of Technology,Jinzhou 121001,China)
机构地区:[1]辽宁工业大学汽车与交通工程学院,辽宁锦州121001
出 处:《现代车用动力》2024年第3期1-5,60,共6页Modern Vehicle Power
基 金:2022年辽宁省教育厅项目(LJKMZ20220978)。
摘 要:针对目前自动驾驶汽车行为预测对目标行为标注准确率低及压线行驶行为无法标注问题,首先通过建立车辆包围盒(Bounding Box)将车辆的形状描述出来,随后通过Bounding Box 4个顶点与车道线的相交关系来判断目标车是否有换道行为。对于无车道线的情况,首先通过自车轨迹左右拓展出虚拟车道线,通过Bounding Box与虚拟车道线的关系判断目标车是否有切入自车道的行为,随后进行标注。通过Bounding Box对目标行为进行标注可以将标注的准确率提高至80%,并且可以将压线行驶行为标注出来,为后续行为预测模型训练打下良好的基础。Aiming at the accuracy of target behavior prediction and the inability to label line driving behavior of autonomous vehicles,the shape of the vehicle is described by establishing Bounding Box,and then the intersection relationship between the four vertices of the Bounding Box and the lane line is used to judge whether the target vehicle has lane changing behavior.For the case with no lane lines,firstly,the virtual lane line is extended to the left and right by the self-vehicle track,and then determines whether the target vehicle has the behavior of cutting into the self-lane by the relationship between the Bounding Box and the virtual lane line,and then marks.Bounding Box labeling target behaviors can improve the accuracy of labeling and lay a good foundation for subsequent behavior prediction model training.
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