基于三分图匹配的智能车辆多传感器数据融合

Multi-sensor Data Fusion for Intelligent Vehicles Based on Tripartite Graph Matching

多传感器融合是提高智能车辆感知效果的有效途径,针对激光雷达、毫米波雷达和相机3种传感器数据匹配问题,传统匹配方法(如二分图匹配)无法获得高的精度,同时匹配鲁棒性差。为此,本文提出一种基于三分图匹配的智能车辆多传感器数据融合算法,将3种传感器数据匹配问题抽象为有权三分图匹配问题,通过拉格朗日松弛将原问题空间分解为子空间,进而利用代价矩阵模型确定子空间内的顶点和边的权重,结合感知误差模型和似然估计确定感知误差后验分布,最终利用拉格朗日乘子(Lagrange Multiplier,LM)模型完成数据匹配。最后利用nuScenes训练集和实车实验对本文所提匹配算法的效果进行了验证,在数据集上本文算法比常用算法在F1得分方面提升了7.2%,而在多种实车场景测试中,本文算法也同样具有较好的感知精度和鲁棒性。

Multi-sensor fusion is an effective way to improve intelligent vehicle perception.For the datamatching problem of the three types of sensors of LiDAR,millimeter-wave radar,and camera,traditional methods such as bipartite graph matching can’t achieve high precision,with poor matching robustness.Therefore,a multisensor data fusion algorithm for intelligent vehicles based on tripartite graph matching is proposed in this paper.The problem of data matching of the three sensors is abstracted as a weighted tripartite graph-matching problem.By us⁃ing Lagrange relaxation,the original problem space is decomposed into subspaces,the weights of vertices and edge inside which are determined then by the cost matrix model.Furthermore,combining the perceptual error model and likelihood estimation,the posterior distribution of perceptual errors is determined.Ultimately the Lagrange Multipli⁃er(LM)model is used for data matching.Finally,the effectiveness of the proposed matching algorithm is validated by the nuScenes training dataset and real-world vehicle tests.On the dataset,the proposed algorithm improves F1 scores by 7.2%compared to common algorithms.In various real-world vehicle scenarios,the proposed algorithm shows excellent perceptual accuracy and robustness across.