Learning and anomaly detection method based on multi-feature motion modes of vehicle traces

Abstract

The invention provides a method for learning and anomaly detection of trace modes by utilizing much feature information of a trace. Firstly, in the trace mode learning phase, similarities of motion directions and spatial positions between traces are considered at the same time, a typical trace motion mode is extracted by hierarchical agglomerative clustering, and is provided with high cluster accuracy; and the time efficiency is greatly improved through constructing a Laplacian matrix and reducing the dimensionality of the matrix. Then in the abnormity detection phase, a distribution area of scene starting points is learned through a GMM model, a moving window is used as a basic comparing element, differences of a trace to be detected and a typical trace in position and direction are measured by defining a position distance and a direction distance, and an on-line classifier based on the direction distance and the position distance is established. That the trace belongs to a starting point abnormity, a global abnormity or a local abnormity is determined online through a multi-feature abnormity detection algorithm; and due to the fact that starting point, direction and position feature differences are considered at the same time, and the global abnormity and the local child segment abnormity are considered, the learning and anomaly detection method based on multi-feature motion modes of the vehicle traces is higher in abnormity recognition rate when being compared to traditional methods.

Description

technical field [0001] The invention relates to a motion pattern learning method and an online abnormal trajectory detection method based on vehicle trajectory multi-features. First, the trajectory motion pattern is extracted by hierarchical clustering from coarse to fine, and each layer uses Bhattacharyya distance and improved Hausdorff distance based on line segment interpolation to measure the similarity of motion direction and spatial position between trajectories, and introduces Laplacian mapping to reduce calculation Complexity and automatically determine the number of clusters in each layer. On this basis, while considering the differences in starting point distribution, position and direction between the trajectory to be tested and the motion pattern, the starting point, global and local anomalies are judged online through the learned starting point distribution model and a classifier based on position distance and direction distance. Background technique [0002] I...

AI Technical Summary

Problems solved by technology

(1) The former learns the statistical distribution pattern of normal trajectories through a series of single Gaussian models, builds a Bayesian classifier, and then identifies abnormal behaviors through an incremental online anomaly detection method, but only considers the abnormal location of the trajectory space and does not consider the direction (2) The latter is to establish a trajectory model through C-HMM, divide each normal trajectory cluster into several regions, use GMM to learn the model parameters of each HMM state, set the abnormal threshold, and use the trajectory to be tested as the model's Input to judge trajectory anomalies, this method can only roughly detect anomalies with large differences, and it is difficult to identify complex local sub-segment anomalies

Images