The invention discloses an SVM (support vector machine) algorithm-based driver intention recognition method. The method includes classifying categories of driver intention types, performing data collection according to the classified categories, classifying and numbering collected data by numbers, determining characteristic values and driver intention categories, subjecting the collected data to a dimension reduction process by a PCA (principal component analysis) method, selecting a proper kernel function to map a characteristic vector into a high-dimensional space to enable inseparable data to be separated from one another, subjecting parameters to training and off-line verification by a pre-classified SVM model, and finally, recognizing driver intention according to the data collected in real time. Thus, a recognition process is simplified, recognition error rate is decreased and vehicle-mounted safety is improved.
SVM (support vector machine) algorithm-based driver intention recognition method
2015-04-08
Patent
Electronic Resource
English
IPC: | 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 |
Driver Intention Recognition Based on Computer Vision
SAE Technical Papers | 2022
|Driver intention recognition method based on probability correction
European Patent Office | 2020
|Driver overtaking intention recognition method based on GM-HMM
European Patent Office | 2021
|