Scene classification method based on residual network training of transfer learning

A scene classification and network training technology, applied in the field of scene classification of residual network training, can solve the problems of long classification time and low algorithm classification accuracy, and achieve the effect of improving the accuracy.

Inactive Publication Date: 2019-05-21
北京航天云路有限公司
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Judging from the classification results, the shortcomings of the research results are tha

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
  • Scene classification method based on residual network training of transfer learning
  • Scene classification method based on residual network training of transfer learning
  • Scene classification method based on residual network training of transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention.

[0044] Such as figure 1 As shown, a scene classification method based on transfer learning residual network training according to an embodiment of the present invention includes the following steps:

[0045] S1. Collection of data sets, 80,000 pictures downloaded from the Internet, including 80 daily scene categories, each scene category contains 600-1100 pictures, the specific scenes, numbers and labels are as follows:

[0046] 0 / Terminal: airport_terminal 1 / Apron: landing_field

[0047] 2...

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 scene classification method based on residual network training of transfer learning. The method comprises: S1, collecting a data set; S2, importing the marked training data set; S3, taking the vector of the imported picture after preprocessing as the input of a ResNet 18 _ Place365 model; S4, loading a deep residual network model; S5, setting a square layer; S6, generating final prediction of square layer output through the fully connected softmax classifier, and outputting the category of the predicted picture; and S7, evaluating the scene classification method by taking the prediction accuracy of the algorithm on the test set picture as a final evaluation criterion. The beneficial effects of the invention are as follows: the invention provides a scene classification method based on residual network training of transfer learning. According to the method, the problem that training cannot be carried out when a neural network algorithm is deep in hierarchy is solved essentially, and the scene classification accuracy is improved limited by establishing a dynamic neural network algorithm and replacing a numpy module with PyTorch in a framework.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a scene classification method based on transfer learning residual network training. Background technique [0002] Scene classification, or scene recognition, is an important research direction in the field of scene understanding. Its basis is to divide different scene images into different categories according to their semantic information according to the organization principle of human vision. In the field of scene classification, the method of manually extracting image features has always been adopted. This method extracts single features and cannot describe various scenes well, resulting in low scene classification accuracy. [0003] Scene classification is to use machine learning methods to obtain the scene category represented by the picture. It plays a very important role in scene recognition. The application areas of scene recognition are mainly in remote sens...

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): G06K9/00G06K9/62G06N3/04G06N3/08
Inventor 徐汕刘强张晶亮杨端单酉姜桥
Owner 北京航天云路有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap