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

Time-space isolated point-based vehicle abnormal track detection method

A detection method and isolated point technology, applied in traffic flow detection, road vehicle traffic control system, structured data retrieval, etc., can solve the problems of insufficient coverage and high false alarm rate, and achieve increased detection coverage, false positives, etc. The effect of reducing the alarm rate and reducing the detection time

Active Publication Date: 2018-07-31
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a vehicle abnormal trajectory detection method based on time-space isolated points for the problems of high false alarm rate and insufficient coverage of vehicle abnormal trajectory detection results in urban environments

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
  • Time-space isolated point-based vehicle abnormal track detection method
  • Time-space isolated point-based vehicle abnormal track detection method
  • Time-space isolated point-based vehicle abnormal track detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] A vehicle abnormal trajectory detection method based on time-space outliers. A taxi company’s GPS data set is used to train the abnormal trajectory detection method as an embodiment. The basic process is as follows figure 1 As shown, it specifically includes the following steps:

[0056] Step 1: Sort the data of the same vehicle ID into one category, and then sort them in chronological order. Will be like figure 2 The map area shown at longitude [121.25E,121.65E] and latitude [31.05N,31.35N] is gridded to form a matrix H, which is divided into 120*160 grids, each grid is 250m*250m . Use the mapping function τ(·) to convert all GPS raw data points into grid units, namely τ(p i )=g i , Where p i Is the GPS raw data point, g i Include row m, column n, and GPS time of the grid in the matrix. Divide each discrete point g i Connect the center of the grid to form a trajectory, and complete the data of the grid that this trajectory passes through, including row m, column n, and ...

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 a time-space isolated point-based vehicle abnormal track detection method. The method comprises the following steps of 1, preprocessing tracks, and performing duplicate removaland complementation on the grid tracks; 2, matching track pairs, and establishing an offline comparison track library; 3, performing track space and time support degree calculation on input to-be-detected tracks to obtain a suspected abnormal track point set and an abnormal track point set; 4, establishing a track point abnormality calculation function and a track abnormality calculation function; and 5, calculating and outputting track abnormality and abnormal sub-tracks in real time. By using space isolation and time isolation methods, real-time track abnormality and abnormal evidences aregiven; high abnormal detection coverage rate is achieved; the false alarm rate is low; and the method can be effectively applied to the real-time abnormal track detection of city vehicles.

Description

Technical field [0001] The invention belongs to the fields of intelligent transportation, big data mining and machine learning, and particularly relates to a vehicle abnormal trajectory detection method based on time-space isolated points. Background technique [0002] Anomaly trajectory detection is to mine outliers or anomalies in a data set. The common definition of anomalies was proposed by Hawkins in 1980, that is, anomalies are data that have serious deviations from other objects in the data set, and these data are not due to randomness. The deviation occurs because of the law of the data itself. In the urban transportation system, due to the complex road network, abnormal traffic incidents such as traffic accidents and road jams are often prone to spread into large-scale traffic problems, which makes it difficult to determine the model of abnormal vehicle instances in the city. The deviation in the establishment of the abnormal instance model will eventually lead to lower...

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): G06F17/30G08G1/01G06Q50/26G06Q50/30
CPCG06F16/2272G06F16/29G06Q50/26G08G1/0125G06Q50/40
Inventor 顾晶晶郑剑炜庄毅周强
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS