Model identification method based on machine learning

Abstract

Disclosed is a model identification method based on machine learning. The method comprises the following steps: 1), carrying out vehicle detection by use of a background difference method, performing contour tracking on a motion object, obtaining external contour characteristics of the motion object, and performing vehicle predetermination and image preprocessing on an object image; 2), extracting vehicle characteristics: (2.1) extracting vehicle geometrical characteristics; and (2.2), extracting characteristics of seven invariant moments of a vehicle; 3), model classification training, i.e., training an input fifteen-dimensional model characteristic sample by use of a metric learning based KNN classifier, and obtaining four model classifications; and 4), model classification based on local linearity reconstruction error minimization, i.e., performing local linearity reconstruction error calculation and classification on a newly introduced test sample by use of a reconstruction error minimization method. The model identification method based on the machine learning, provided by the invention, is quite high in accuracy and good in real-time performance in case of quite a large number of types.

Description

technical field [0001] The invention relates to the field of intelligent traffic identification, in particular to a vehicle identification method. Background technique [0002] One of the key functions of an intelligent transportation system is the ability to accurately identify vehicle types. Vehicle type recognition is to actively classify vehicles by detecting the inherent parameters of the vehicle itself and using appropriate classification recognition algorithms under certain vehicle classification standards. Vehicle type recognition technology can be applied to various vehicle toll stations such as highways, bridges and roads, and automatic toll collection systems in large parking lots, thereby improving the utilization of traffic resources. It has very broad application prospects and important research in modern traffic monitoring and management. and application meaning. [0003] At present, the methods of vehicle recognition using video processing technology can be...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the existing vehicle identification methods that cannot meet the accuracy and real-time requirements when there are many types, the present invention provides a vehicle model based on machine learning that has high accuracy and good real-time performance when there are many types. recognition methods

Images