Driving behaviour analysis is important for both intelligent transportation and public security. The authors propose to characterise driving behaviours by using the phase-space reconstruction (PSR) and the pre-trained convolutional neural network (CNN). PSR is first applied to the raw vehicle test data (VTD) to obtain the reconstructed trajectories. Second, the corresponding feature vectors are acquired by using the pre-trained CNN. Third, the t-distributed stochastic neighbour embedding (t-SNE) algorithm is applied to the feature vectors to validate their characterising ability. Finally, an index is proposed based on the aforementioned feature vectors for quantitative evaluation, i.e. driving style recognition and abnormal driving detection. Simulations are conducted to verify the effectiveness of the proposed scheme.
Driving behaviour characterisation by using phase-space reconstruction and pre-trained convolutional neural network
IET Intelligent Transport Systems ; 13 , 7 ; 1173-1180
2019-04-17
8 pages
Article (Journal)
Electronic Resource
English
convolutional neural nets , feature vectors , pre-trained CNN , intelligent transportation systems , driving style recognition , public security , learning (artificial intelligence) , behaviour analysis , pre-trained convolution neural network , driving behaviour characterisation , intelligent transportation , raw vehicle test data , t-SNE , image reconstruction , t-distributed stochastic neighbour embedding , stochastic processes , convolutional neural network , abnormal driving detection , image recognition , PSR , driver information systems , phase-space reconstruction
Metadata by IET is licensed under CC BY 3.0
Long short-term memory and convolutional neural network for abnormal driving behaviour recognition
IET | 2019
|Long short‐term memory and convolutional neural network for abnormal driving behaviour recognition
DOAJ | 2020
|Long short‐term memory and convolutional neural network for abnormal driving behaviour recognition
Wiley | 2020
|