Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic detection method for traffic incident based on tendency indicator and fluctuation indicator

A traffic event and automatic detection technology, applied in traffic flow detection, road vehicle traffic control system, traffic control system, etc. detection, etc.

Active Publication Date: 2017-02-22
SUN YAT SEN UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When there is a detector failure on the road, it will cause its upstream and downstream to be unable to use this method for detection
At the same time, the start time and end time of traffic events are the key time nodes that characterize the event. At these time nodes, data such as occupancy rate and terminal alarms will also have certain characteristic changes. The traditional California algorithm does not consider before and after the key time nodes. A certain range of data volatility characteristic indicators
In general, the current detection methods cannot effectively detect traffic events, so that the changes in traffic conditions cannot be learned in time.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic detection method for traffic incident based on tendency indicator and fluctuation indicator
  • Automatic detection method for traffic incident based on tendency indicator and fluctuation indicator
  • Automatic detection method for traffic incident based on tendency indicator and fluctuation indicator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] refer to figure 1 , the present invention provides a kind of traffic event automatic detection method based on trend index and volatility index, comprising steps:

[0047] S1. Collect real-time traffic data through sensors;

[0048] S2. Preprocessing the real-time traffic data;

[0049] S3. Based on the preprocessed real-time traffic data, calculate the following real-time feature vectors: trend index, volatility index and upstream and downstream change index;

[0050] S4. Using the calculated real-time feature vector as an input sequence of the training model, and using the training model to calculate and obtain a corresponding output result as the detection result of the traffic incident.

[0051] Further as a preferred embodiment, it also includes the following steps:

[0052] S5, giving a timely alarm according to the detection result of the traffic incident.

[0053] Further as a preferred embodiment, it also includes the following steps:

[0054] S0. After ob...

Embodiment 2

[0081] This embodiment is a detailed example of the first embodiment. This embodiment takes the collected traffic data as an example to describe the prediction process of the training model in detail. Other calculation processes, etc., are similar in principle to the training process, and can refer to the description of Embodiment 1.

[0082] Through the occupancy sequence obtained at consecutive H times, the following historical feature vector can be calculated and obtained:

[0083] Trend indicators:

[0084] 1. For the occupancy sequence obtained at H consecutive times, the least squares method is used to fit the curve, and the calculated slope k is obtained;

[0085] 2. Calculate the number of decreasing trend moments in the occupancy rate sequence, that is, calculate the number of moments in which the trend of the current moment is decreasing compared with the previous moment in the occupancy sequence obtained at consecutive H moments:

[0086]

[0087] In the above...

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

No PUM Login to View More

Abstract

The invention discloses an automatic detection method for a traffic incident based on a tendency indicator and a fluctuation indicator. The automatic detection method comprises the following steps: S1, acquiring real-time traffic data by a sensor; S2, preprocessing the real-time traffic data; S3, calculating the following real-time feature vectors based on the preprocessed real-time traffic data: the tendency indicator, the fluctuation indicator as well as upstream and downstream change indicators; S4, using the real-time feature vectors obtained by calculation as an input sequence of a training model, and adopting the training model for calculating to obtain a corresponding output result serving as a detection result of the traffic incident. According to the automatic detection method disclosed by the invention, the real-time traffic data are acquired by the sensor, and can be used for detecting and judging the traffic incident, so that the change of a traffic state is acquired in time, and the time and the place of the traffic incident are accurately found in time; the automatic detection method can be widely applied to the field of detection of the traffic incidents.

Description

technical field [0001] The invention relates to the field of highway traffic event detection, in particular to an automatic detection method for traffic events based on trend indexes and volatility indexes. Background technique [0002] Glossary: [0003] Occupancy: [0004] Kurtosis: also known as kurtosis coefficient, characterizes the characteristic number of the peak value of the probability density distribution curve at the average value; [0005] Skewness: It is a measure of the skewed direction and degree of statistical data distribution, and it is a digital feature of the asymmetrical degree of statistical data distribution; [0006] Upstream and downstream: In this application, it refers to the upstream section and the downstream section of a certain location of the traffic route; [0007] Dirty data: It means that the data in the source system is not within the given range or meaningless to the actual business, or the data format is illegal, and there are irregu...

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
no application Login to View More
IPC IPC(8): G08G1/01
CPCG08G1/0125
Inventor 蔡恒兴钟任新徐若辰黄云萍罗佳晨
Owner SUN YAT SEN UNIV