Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Design method of complex weather road scene recognition system based on deep learning

A deep learning and scene recognition technology, applied in the field of intelligent recognition, which can solve the problems of high recognition accuracy and difficulty

Pending Publication Date: 2021-02-12
XUZHOU NORMAL UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, there are many system designs for road scene recognition, but how to maintain high recognition accuracy under complex weather conditions is still a big problem

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
  • Design method of complex weather road scene recognition system based on deep learning
  • Design method of complex weather road scene recognition system based on deep learning
  • Design method of complex weather road scene recognition system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the implementation of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0033] as attached figure 1 As shown, the design method of complex weather road scene recognition system based on deep learning includes the following steps:

[0034] Step 1) obtain road image dataset;

[0035] Step 2) preprocessing the data set;

[0036] Step 3) dividing the data set into a training data set and a testing data set according to a certain ratio;

[0037] Step 4) modify the SSD model with the residual network ResNet-50;

...

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

The invention discloses a design method of a complex weather road scene recognition system based on deep learning. The design method comprises the steps of 1) obtaining a road image data set; 2) preprocessing the data set; 3) dividing the data set into a training data set and a test data set according to a certain proportion; 4) modifying the SSD model by using a residual network ResNet-50; 5) training the network by using the training data set; 6) testing the trained network by using the test data set; and 7) updating parameters to improve the accuracy of the model. According to the SSD target detection method, the SSD target detection algorithm is modified by using the residual network ResNet-50 to replace an original feature extraction network, so that the detection precision is improved, and the SSD target detection method has a satisfactory detection effect.

Description

[0001] Technical field: The present invention relates to a design method of a complex weather road scene recognition system based on a deep learning method, which belongs to the field of intelligent recognition technology. Background technique: [0002] The residual network is composed of a series of residual blocks, and the residual block is divided into two parts: direct mapping part and residual part. It generally consists of two or three convolution operations. As the depth of the network increases, there will be a degradation problem in ordinary neural networks, that is, when the network becomes deeper and deeper, the accuracy of training will tend to be flat, but the training error will become larger, which is obviously not too much. Fitting, because overfitting means that the training error of the network will continue to decrease, but the test error will become larger. In order to solve this degradation phenomenon, ResNet was proposed. The difference between the resid...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V20/52G06V2201/07G06N3/045G06F18/214
Inventor 马欣欣宋博
Owner XUZHOU NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com