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

A method for identifying the loading type of green traffic compartments based on convolutional neural network

A technology of convolutional neural network and carriage, which is applied in the field of identifying the loading type of green-opening carriages based on convolutional neural network, which can solve problems such as application scenario limitations, achieve great adaptability, avoid poor level, and improve accuracy.

Active Publication Date: 2022-03-29
CHANGAN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, most studies have not established classification standards for vehicles in specific scenarios, and they all rely on classification standard documents formulated by the state, which makes the application scenarios have huge limitations

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
  • A method for identifying the loading type of green traffic compartments based on convolutional neural network
  • A method for identifying the loading type of green traffic compartments based on convolutional neural network
  • A method for identifying the loading type of green traffic compartments based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] The invention aims to realize the accurate identification of the green traffic compartment-loading type, and combines the target detection algorithm, unbalanced data set processing, etc. with the convolutional neural network model. Each part is detailed as follows:

[0065] Image import: A total of 3,397 side photos of vehicles were selected from the MySQL database of the Expressway Green Traffic Management Platform in Shaanxi Province and taken between 2018.12.1 and 2018.12.31. Figure 5 The shown green traffic image validity judgment standard judges the image quality, and the manual judgment determines 1373 valid images and 2024 invalid images, a total of 3397 images.

[0066] Unbalanced data processing: Remove invalid images, use the idea of ​​artificially synthesizing minority samples for effective images, and use data enhancement methods to increase the number of training samples. The so-called data enhancement, methods that can be used include: flipping the pictu...

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

A method for identifying the loading type of a green traffic compartment based on a convolutional neural network, comprising the following steps: step 1, obtaining a green traffic image; step 2, formulating a validity judgment standard for a green traffic image through a relative evaluation method in an image quality evaluation method; Step 3, increase the number of training samples; Step 4, carry out compartment target detection; Step 5, divide green traffic vehicles into 8 categories according to compartment-loading type; Step 6, train compartment-loading type classification; Step 7, classify The green traffic compartment that needs to be identified-loading type is determined. Aiming at the problem of unbalanced number of image types, the data oversampling method is used to process the unbalanced data to achieve the balance of the number of samples of each type. The problem that the randomly selected and eliminated data in the undersampling method may contain the key feature information of this class is avoided.

Description

technical field [0001] The invention belongs to the technical field of vehicle identification, and in particular relates to a method for identifying the loading type of a green-traffic compartment based on a convolutional neural network. Background technique [0002] The image classification algorithm is divided into traditional classification algorithms according to time, including: K-neighbor algorithm, SVM support vector machine, Bayesian algorithm, etc. With the great improvement of computer computing power, deep learning algorithm has gradually become the current mainstream application. The artificial neural network simulates the working principle of neurons in the brain, and finally obtains a network model that can learn autonomously. Convolutional neural network models mainly involve AlexNet network models, VGGNet network models, and ResNet network models. The target detection algorithm based on traditional image processing is insufficient in terms of data processin...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/764G06V10/82G06K9/62
CPCG06F18/217G06F18/241G06F18/254
Inventor 王萍张书颖靳引利孙铸韩万水王军杨干李文杰马党利
Owner CHANGAN UNIV