Intelligent networked automobile behavior identification method
An identification method and intelligent network technology, which is applied in the field of intelligent networked vehicle behavior identification, can solve the problem of low accuracy of identification results and achieve the effect of continuous identification
Inactive Publication Date: 2020-11-03
山东省网联智能车辆产业技术研究院有限公司
View PDF2 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the maximum likelihood method can only give the behavior with the greatest likelihood, but cannot express the possibility of behavior through probability, and can only realize the identification problem of a single driving behavior sample, and the accuracy of the identification results for continuous driving behavior samples lower
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] Attached below Figure 1 to Figure 11 , the main content of the present invention is described in detail.
[0035] (1) Use the Viterbi algorithm to decode the GMM-HMM driving behavior identification model, find the output probability P(I|λ) of the model parameter λ to the output driving behavior sequence I, and select the state with the highest probability as the current driving behavior state value, so as to obtain the identified driving behavior sequence value I.
[0036] (2) Use the method of sliding time window to extract the driving behavior sequence of specified length, such as figure 1 shown. The width of the sliding time window is set to 1s, the time step is set to 0.1s, and the time window collects 10 hidden states each time, and advances 1 sampling point each time it is updated. Assuming that the length of the intercepted sequence is n sampling points, the information of (n-1) nodes in the adjacently extracted two sequences is the same. The sampling freque...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an intelligent networked automobile behavior identification method, which is used for improving the accuracy of an identification result of a continuous driving behavior sample. The method comprises the following steps: (1) decoding a GMM-HMM driving behavior identification model by using a Viterbi algorithm, solving an output probability P (I | lambda) of a model parameterlambda to an output driving behavior sequence I, and selecting a state with the maximum generation probability as a current driving behavior state value so as to obtain an identified driving behaviorsequence value I; (2) extracting a driving behavior sequence with a specified length by adopting a sliding time window method; taking the number of the driving behavior states in each time window asa basis for calculating the probability change of the driving behaviors; (3) processing subsequent observation data of the traffic vehicle subjected to lane changing operation; (4) adopting data of anI80 road section and a US101 road section in the NGSIM data set for training and testing; and after data preprocessing is completed, carrying out GMM data clustering and HMM training work. Accordingto the invention, the accuracy of a continuous driving behavior identification result can be improved.
Description
technical field [0001] The invention relates to the technical field of intelligent networked vehicles, in particular to a behavior identification method for intelligent networked vehicles. Background technique [0002] With the rapid development of my country's road transport industry and the sharp increase in the number of motor vehicles, frequent traffic safety accidents lead to property losses and casualties, which have seriously affected people's production and life. The driver's driving behavior plays an important role in road traffic safety, so it is necessary to correctly identify the driver's behavior. But driving behavior is an ideology, which is difficult to obtain directly through instrumental measurement. Therefore, accurate and early recognition of driver behavior is crucial to the development of safe driving systems and the development of intelligent transportation. [0003] At present, using HMM (Hidden Markov Model) to identify driving behavior is still a r...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/16G08G1/01
CPCG08G1/0104G08G1/166G08G1/167
Inventor 罗映王金祥王淑超
Owner 山东省网联智能车辆产业技术研究院有限公司