Supercharge Your Innovation With Domain-Expert AI Agents!

Method for realizing post-disaster image visual question answering

An image vision and image technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve problems such as disaster situations, low resolution, evaluation and analysis, etc., to speed up planning and decision-making, reduce judgments, and make good decisions Promoting the effect of app value

Pending Publication Date: 2021-11-09
山东新一代信息产业技术研究院有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Satellite imagery is often taken from high altitudes, so the resolution is very low, making accurate hazard assessment analysis impossible

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
  • Method for realizing post-disaster image visual question answering
  • Method for realizing post-disaster image visual question answering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] Such as figure 1 As shown, the method for realizing post-disaster image visual question answering of the present invention uses images and videos collected by unmanned aerial vehicles to classify objects in the images, sets the type of questions, and extracts features from the images through visual algorithms and natural language algorithms And the semantic representation of the question, after combining the features, the task is formulated as a classification task to predict the answer to the question.

[0025] The visual question answering system integrating images collected by unmanned aerial vehicles has great potential in post-disaster damage assessment of major disasters, and can provide real-time data assessment and analysis to disaster-stricken areas. The main question answering scope of the visual question answering system is to provide and query relevant answers to the scene emptying. It can speed up the post-disaster recovery process, and through the on-site...

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 method for realizing post-disaster image visual question answering, and belongs to the technical field of post-disaster evaluation and analysis. The invention discloses a method for realizing post-disaster image visual question answering. The method comprises the following steps: collecting images and videos by using an unmanned aerial vehicle; classifying objects in the image; setting the type of the question; performing feature extraction and semantic representation of problems on the image through a visual algorithm and a natural language algorithm; and after the features are combined, formulating the tasks as classified task prediction question answers. According to the method for realizing post-disaster image visual question answering, the post-disaster recovery process can be accelerated; a post-disaster recovery scheme, a material transfer scheme and the like can be more quickly formulated through on-site understanding of post-disaster conditions, and the invention has good popularization and application values.

Description

technical field [0001] The invention relates to the technical field of post-disaster evaluation and analysis, and specifically provides a method for realizing post-disaster image visual question answering. Background technique [0002] Visual question answering is a multimodal question whose purpose is to find the correct answer given a specific image. The visual question answering system needs to model natural language questions and visual images. The visual question answering model needs to recognize related objects from the image and find the relationship between objects from the recognized multiple objects. [0003] This high-level scene understanding can facilitate the assessment and decision-making of post-disaster scenarios, such as: what is the condition of the roads, how many buildings are damaged, etc. This vital information can advance disaster recovery decisions or save many lives. In addition, the information provided by the visual question answering system ca...

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): G06F16/9032G06K9/00G06K9/62G06N3/04
CPCG06F16/90332G06N3/044G06F18/2415
Inventor 王雯哲高岩高明王建华
Owner 山东新一代信息产业技术研究院有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com