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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


