Vehicle model dynamic identification method used in intelligent transportation system

Abstract

The invention discloses a vehicle model dynamic identification method used in an intelligent transportation system. The vehicle model dynamic identification method is characterized by comprising the following steps: a step a is a learning and training step of a vehicle model of a moving vehicle, wherein HOG and GIST characteristics are extracted after a resolution ratio is normalized, then classification learning is conducted through a support vector machine, and a first classifier identification model and a second classifier identification model are obtained correspondingly; a step b is an identification step of the vehicle model of the moving vehicle, wherein the moving vehicle is extracted according to a corresponding moving object partitioning algorithm, the extracted HOG and GIST characteristics are input to a first identification model and a second identification model respectively for primary prediction after the resolution ratio is normalized, and a first primary result and a second primary result are obtained respectively; a step c is a primary result fusion step, wherein the first primary result and the second primary result are input and fused through a D-S evidence theory fusion rule, a maximum probability value is obtained, and the identification of the vehicle model of the moving vehicle is finished. The vehicle model dynamic identification method used in the intelligent transportation system is simple in structure, low in complexity, high in algorithm efficiency, and particularly suitable for being used in the intelligent transportation system.

Description

technical field [0001] The invention belongs to the field of computer vision, is an important application technology in the field of intelligent transportation, and in particular relates to a multi-feature dynamic vehicle type recognition method based on machine learning. Background technique [0002] The machine learning algorithm is an adaptive learning algorithm, which can automatically fit the corresponding classification surface according to the eigenvalues ​​of different types of input training samples, so as to provide reliable prior knowledge for subsequent identification and detection work. The advantage of this method is that it can perform a good classification work under the condition of comprehensive sample characteristics and sufficient sample size, and at the same time, it has a strong tolerance for bad data and can adapt to a variety of different data environments. Therefore, machine learning algorithms are widely used in many image processing fields such as ...

AI Technical Summary

Problems solved by technology

[0005] With the continuous development of my country's transportation industry, the functions of intelligent transportation systems will become more and more perfect, and the requirements for the identification of dynamic vehicles will become higher and higher, but the environment for dynamic vehicle identification is becoming more and more complex.

Images