Floating vehicle map matching method based on hidden Markov model
A hidden Markov and map matching technology, applied in the field of data processing, can solve problems such as increasing algorithm time complexity, affecting model description ability, and inability to guarantee accuracy, so as to reduce time complexity, comprehensively describe context information, and The effect of accurate traffic flow information
Inactive Publication Date: 2018-02-27
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF6 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, when using the hidden Markov model for floating car map matching, firstly, the improper selection algorithm of the candidate matching points of the observation points will easily lead to a sharp increase in the time complexity of the algorithm. Improper matching will cause wrong matching. Finally, when the transition probability of candidate matching points before and after modeling, insufficient matching features or wrong feature selection will significantly affect the model's ability to describe the matching context, resulting in a significant drop in matching accuracy.
In summary, when using the hidden Markov model for floating car map matching, the inaccuracy of any of the three links in the candidate point selection algorithm, observation probability modeling of observation points, and forward and backward candidate point transition probability modeling cannot guarantee the matching. Accuracy
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
[0023] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.
[0024] see figure 1 and figure 2 , the embodiment of the present invention includes:
[0025] A kind of floating car map matching method based on Hidden Markov Model, mainly comprises the following steps:
[0026] 1. Input the track data of the floating car to be matched;
[0027] 2. For each observation point, select its candidate matching point set with a predetermined error radius;
[0028] 3. For each observation point, the observation probability is modeled using the feature that the distance between the observation point and its candidate points conforms to the Gaussian distribution;
[0029] 4. Calculate the transition probability bet...
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 a floating vehicle map matching method based on a hidden Markov model, and belongs to the technical field of data processing. The method comprises the steps that firstly, othercandidate matching point sets are selected for each observation point according to a preset error radius; secondly, observation probability is modeled for each observation point by means of the feature that the distances between observation point and candidate points of the observation point conform to Gaussian distribution; thirdly, transition probability between front and rear candidate matching points corresponding to the front observation point and the rear observation point is calculated by means of the distance similarity features of the front and rear observation points and the corresponding front and rear candidate points and average speed similarity features; finally, according to the calculated observation probability and transition probability, a correct road section sequence matched with given floating vehicle track data on an electronic map is determined. The floating vehicle map matching method can be used for quickly and accurately matching the floating vehicle track data low in positioning precision to the electronic map.
Description
technical field [0001] The invention discloses a floating car map matching method based on a hidden Markov model, belonging to the technical field of data processing. Background technique [0002] The floating car system is a new traffic information collection technology developed with the application of new technologies in intelligent transportation systems. The floating vehicle uses the GPS device to transmit vehicle information such as time, speed and position to the information processing center in real time. The information center provides relevant departments with road traffic conditions through the analysis of the information returned by the floating vehicle, and can be used as the basis for quantitative data analysis of various tasks such as congestion relief and urban road planning. [0003] Due to the influence of GPS sampling error, the position information returned by the floating car usually deviates from the driving track. Therefore, the data of the floating c...
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): G06K9/62
CPCG06F18/22G06F18/295
Inventor 燕雪峰宋承波
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS