Frequent lane-change of vehicles can have a serious impact on traffic safety and traffic congestion. In the era of the internet of vehicles, it is helpful to regulate driver’s driving behavior by detecting frequent lane-change behaviors and promptly alerting the driver. In this paper, the accelerometer and gyroscope data collected by the smartphone inertial sensor is being used to analyze the lane-change behavior of the vehicles. The data is being trained by AdaBoost and combined with the sliding time window for frequency identification. The effectiveness of the proposed algorithm is being compared to that of SVM algorithm and BP neural network. The results show that AdaBoost algorithm is superior to SVM algorithm and BP neural network. Finally, the same experiment was conducted with the data collected by the high-precision inertial at the same time. When compared with the results of Adaboost algorithm, the practicability of the proposed method is further verified.
Detection of Frequent Lane-Change Behavior Using Smart Phone Inertial Sensor Data
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 401-410
09.12.2020
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Vehicle frequent lane change detection method based on lane level positioning
Europäisches Patentamt | 2022
|Europäisches Patentamt | 2021
|Lane Change Detection Using Naturalistic Driving Data
IEEE | 2021
|Data Acquisition using Smart Phone Applications
British Library Conference Proceedings | 2016
|Data Acquisition using Smart Phone Applications
SAE Technical Papers | 2016
|