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

Unsupervised landform classification model training and landform map construction method

A classification model and training method technology, applied in neural learning methods, biological neural network models, maps/plans/charts, etc., can solve the problems of unsupervised, high cost of topographic map construction, and reduce costs, save time and labor. The effect of labeling costs

Active Publication Date: 2020-02-07
深圳中科保泰空天技术有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides an unsupervised method for training the landform classification model and constructing the landform map, so as to solve the problem of high construction cost of the existing landform map

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
  • Unsupervised landform classification model training and landform map construction method
  • Unsupervised landform classification model training and landform map construction method
  • Unsupervised landform classification model training and landform map construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application.

[0053] The technical solution provided by the embodiment of the present application is applied to the construction of the geomorphic map, and the construction process of the geomorphic map can be roughly divided into the training phase of the geomorphic classification model and the construction phase of the geomorphic map.

[0054] In the training phase of the landform classification model, the unlabeled landform sample training data set is input into the generative confrontation network to generate a large amount of target pseudo-geomorphology data, and the target pseudo-geomorphology data is used as the training data of the model to train the pre-trained landform classification model. In the process of model training, manual l...

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 embodiment of the invention is suitable for the technical field of artificial intelligence, and discloses an unsupervised landform classification model training and landform map construction method, comprising the steps: obtaining an unlabeled landform sample training data set; performing adversarial training on the generative adversarial network by using the unlabeled geomorphic sample training data set to obtain target pseudo-geomorphic data output by the generative adversarial network; wherein the target pseudo-geomorphic data is pseudo-geomorphic data output when the training effect ofthe generative adversarial network is optimal; training a pre-trained landform classification model by using the target pseudo-landform data; and after the training is completed, using a landform classification model to construct a landform map. According to the embodiment of the invention, manual labeling is not needed in the landform classification model training process, and the unlabeled sample data is directly used for model training, so that the labor cost of manual annotation is saved, and the landform mapping cost is reduced.

Description

technical field [0001] The application belongs to the technical field of artificial intelligence, and in particular relates to an unsupervised method for training a landform classification model and a method for constructing a landform map. Background technique [0002] A geomorphic map is a map showing various geomorphic signs. It can reflect the external morphological characteristics and causes, age, development process, development degree and mutual relationship of various landforms. [0003] At present, when the convolutional neural network model is used for the construction of geomorphic maps, it is necessary to use a large number of geomorphic sample images to train the corresponding model, and the geomorphic sample images used in the training need to be manually labeled. It takes a lot of time and labor cost to manually label a large number of landform sample images, which leads to the high cost of constructing the existing landform map. Contents of the invention ...

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): G06K9/62G06N3/08G09B29/00
CPCG06N3/08G09B29/005G06F18/214
Inventor 陈壮壮李坚强陈杰曾崛
Owner 深圳中科保泰空天技术有限公司
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