Multidimensional data based detecting method of traffic abnormal spots

Abstract

The invention relates to a multidimensional data based detecting method of traffic abnormal spots. According to the method, for flow, speed and lane occupancy ratio data of each section, obtained by a microwave apparatus in a continuous period, historical jam probability of each section is calculated according to the speed data, positive and negative anomalies of each section are defined through comparing recent traffic state index values, anomaly degree is calculated for each section with the negative anomaly by means of a density-based local anomaly factor method, and weighted anomaly degrees are calculated according to positive and negative anomaly factors and are ranked. The method has the advantages that multi-index data is utilized, the uniformity in sample spatial data distribution is considered, local limitedness of the density-based local anomaly factor method is avoided the use of the features of traffic data, road abnormal spots can be effectively detected, the traffic administration is helped command the road traffic, service efficiency of roads is adjusted and optimized, and the method features high universality, high feasibility, high reliability and high applicability.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a method for detecting abnormal traffic points based on multidimensional data. Background technique [0002] With the rapid development of urban economy, the number of motor vehicles in urban traffic continues to increase. How to effectively regulate traffic flow, optimize road use efficiency, and ease road traffic conditions has become the focus of research in the field of urban intelligent transportation. One of the key technologies is to detect the abnormality of urban traffic, that is, to detect the abnormal road sections in urban traffic through certain technical means. The detection of abnormal points is the main content of urban traffic public information services, and it is also a necessary means for traffic management departments to deploy police forces and guide road traffic. The detection of traffic anomalies is generally based on the analysis of traffic flow...

AI Technical Summary

Problems solved by technology

The model-based method requires prior knowledge of what distribution the data obeys, and the detection of multi-dimensional data is poor; the proximity-based method is not suitable for large traffic data sets, is sensitive to parameter selection, and cannot meet the needs of uneven distribution of traffic data ; The detection result of the clustering-based method is related to the selection of the number of clusters, and misjudgment will occur. Even the DBSCAN method that does not need to pre-select the number of clusters will also misjudge the boundary samples of the cluster, and cannot Better reflect multi-dimensional data; density-based methods can be effectively applied to multi-dimensional traffic data with uneven distribution, and are not sensitive to the choice of parameters in traffic anomaly detection

Images