Vehicle lane changing intention prediction method considering vehicle complex interaction

The invention discloses a vehicle lane changing intention prediction method considering vehicle complex interaction. The method comprises the steps of performing real-time identification based on a video to obtain vehicle trajectory data and performing preprocessing; inputting the preprocessed vehicle track data into the constructed lane changing intention prediction model, and predicting to obtain a target vehicle lane changing intention; wherein the lane changing intention prediction model is obtained by training the CNN-LSTM model through historical video data based on the CNN-LSTM model. According to the method, the lane changing intention prediction accuracy can be improved based on the influence of complex interaction of different vehicle types on driving behaviors, and the accident risk caused by lane changing is effectively reduced. 本发明公开了一种考虑车辆复杂交互的车辆换道意图预测方法，包括：基于视频进行实时识别获取车辆轨迹数据并进行预处理；将预处理后的车辆轨迹数据输入构建完成的换道意图预测模型，预测得到目标车辆换道意图；其中，换道意图预测模型是基于CNN-LSTM模型通过历史视频数据对其进行训练得到。所述方法能够基于不同车辆类型的复杂交互作用对驾驶行为产生的影响，提