论文部分内容阅读
为减少交通事件引起的交通延误,有效预防偶发性交通事件导致二次事故的发生,提出一种基于支持向量机(SVM)和数据融合技术的城市道路交通事件自动检测(AID)算法。利用车载激光测距仪采集本车与前车的距离,利用搭载全球定位系统(GPS)的浮动车采集本车瞬时速度。将这2种交通数据按一定的规则进行数据级融合,然后运用线性、多项式和径向基(RBF)3种核函数的SVM模型分别进行事件检测。最后,用实测数据对其进行验证。结果表明:核函数为RBF的非线性SVM模型检测率(DR)值最大,误判率(FAR)值最小,检测指标均优于经典算法,说明算法检测性能良好。
In order to reduce the traffic delay caused by traffic accidents and effectively prevent the occurrence of secondary accidents caused by occasional traffic accidents, an automatic urban traffic incident detection (AID) algorithm based on Support Vector Machine (SVM) and data fusion technology is proposed. The distance between the host vehicle and the vehicle in front of the vehicle is acquired by using the vehicle laser range finder, and the instantaneous speed of the vehicle is acquired by using a floating car equipped with a global positioning system (GPS). The two kinds of traffic data are merged according to certain rules and then the event detection is carried out by SVM models of three kinds of kernel functions: linear, polynomial and radial basis function (RBF). Finally, use the measured data to verify it. The results show that the non-linear SVM with kernel function RBF has the highest detection rate (DR) and the lowest false positive rate (FAR), and the detection indexes are better than the classical algorithms, indicating that the algorithm has good detection performance.