The invention discloses an intelligent networked automobile behavior identification method, which is used for improving the accuracy of an identification result of a continuous driving behavior sample. The method comprises the following steps: (1) decoding a GMM-HMM driving behavior identification model by using a Viterbi algorithm, solving an output probability P (I | lambda) of a model parameterlambda to an output driving behavior sequence I, and selecting a state with the maximum generation probability as a current driving behavior state value so as to obtain an identified driving behaviorsequence value I; (2) extracting a driving behavior sequence with a specified length by adopting a sliding time window method; taking the number of the driving behavior states in each time window asa basis for calculating the probability change of the driving behaviors; (3) processing subsequent observation data of the traffic vehicle subjected to lane changing operation; (4) adopting data of anI80 road section and a US101 road section in the NGSIM data set for training and testing; and after data preprocessing is completed, carrying out GMM data clustering and HMM training work. Accordingto the invention, the accuracy of a continuous driving behavior identification result can be improved.
一种智能网联汽车行为辨识方法,用于提高对连续驾驶行为样本辨识结果的准确性。它包括以下步骤:(1)运用维特比算法对GMM‑HMM驾驶行为辨识模型解码,求出模型参数λ对输出驾驶行为序列I的输出概率P(I∣λ),选取产生概率最大的状态作为当前的驾驶行为状态值,从而获得辨识驾驶行为序列值I;(2)采用滑动时窗的方法提取指定长度的驾驶行为序列;根据每个时窗中各驾驶行为状态数量来作为驾驶行为概率变化计算的依据;(3)对进行换道操作的交通车辆的后续观测数据进行处理;(4)采用NGSIM数据集中I‑80路段和US‑101路段的数据用于训练与测试;在完成数据预处理后,开展GMM数据聚类以及HMM的训练工作。本发明可以提高对连续驾驶行为辨识结果的准确性。
Intelligent networked automobile behavior identification method
一种智能网联汽车行为辨识方法
2020-11-03
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Intelligent networked automobile supervision platform
Europäisches Patentamt | 2021
|Intelligent networked automobile inversion control system
Europäisches Patentamt | 2023
|Intelligent networked automobile tail monitoring camera
Europäisches Patentamt | 2022
|