The invention relates to a distracted driving behavior identification method. The method comprises the following steps: obtaining distracted driving time sequence image data of a driver in a man-machine co-driving takeover state; the trained first model or the trained second model is utilized to firstly acquire spatial features of the time sequence image data, and spatial-temporal features are acquired on the basis of the spatial features; and carrying out fusion reinforcement on the spatial-temporal features and the spatial features so as to obtain distracted driving behavior features for distracted driving behavior category identification. According to the method, the distraction driving behavior of the driver can be accurately identified, the risk of taking over by mistake is reduced, and thus the driving safety is improved.
本发明涉及一种分心驾驶行为识别方法,所述方法包括下述步骤:获取人机共驾接管状态下驾驶人的分心驾驶时序图像数据;利用训练好的第一模型或训练好的第二模型首先获取时序图像数据的空间特征,在空间特征的基础上获取时空特征;将所述时空特征与空间特征进行融合加强,进而获得用于分心驾驶行为类别识别分心驾驶行为特征。所述方法能够实现准确识别驾驶人的分心驾驶行为、降低误接管风险,从而提升行车安全性。
Distraction driving behavior recognition method and device and storage medium
一种分心驾驶行为识别方法、装置及存储介质
2022-05-24
Patent
Elektronische Ressource
Chinesisch
IPC: | G06V / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Distraction driving behavior detection method and device, equipment and storage medium
Europäisches Patentamt | 2022
|Driver driving distraction behavior recognition method based on driving behavior data
Europäisches Patentamt | 2021
|Driving behavior recognition method, storage medium and vehicle
Europäisches Patentamt | 2024
|Risk driving behavior recognition system, method and device, and storage medium
Europäisches Patentamt | 2021
|