Unlock instant, AI-driven research and patent intelligence for your innovation.

A Text Description Generation Method for Infrared and Visible Light Images

A visible light and text technology, applied in the field of computer vision, can solve problems such as the inability to generate description sentences

Active Publication Date: 2022-04-29
WUHAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If ordinary visible light imaging equipment is used to collect scene information, the image description generation algorithm will not be able to generate correct description sentences later

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
  • A Text Description Generation Method for Infrared and Visible Light Images
  • A Text Description Generation Method for Infrared and Visible Light Images
  • A Text Description Generation Method for Infrared and Visible Light Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0067] In order to more clearly illustrate the purpose, technical solutions and beneficial effects of the present invention, further description will be given below in conjunction with the accompanying drawings and embodiments. It should be understood that the present invention should not be limited to the content disclosed in the embodiments, and the protection scope of the present invention is subject to the scope defined in the claims.

[0068] Technical problem: The present invention designs a text description generation method for infrared and visible light images, which can effectively utilize the complementary visual features provided by infrared images and visible light images, and make up for the shortcomings of traditional single-light algorithms that omit key target entities and insufficient scene descriptions....

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 generating text descriptions of infrared and visible light images. Text description, generating multiple different description texts; 2), building a text description generation network for infrared and visible light images, including a coding model for feature extraction of infrared and visible light images, a feature fusion model composed of a feedforward neural network, and an additive multi-head The image feature decoding model of the attention mechanism; 3) train the text description generation network; 4) input the test image pair into the trained text description generation network, and output its corresponding description text. The method of the invention can effectively utilize the complementary visual features provided by the infrared image and the visible light image, and makes up for the shortcomings of missing key target entities and insufficient scene description in the traditional single-light algorithm.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method for generating text descriptions of infrared and visible light images. Background technique [0002] With the rapid development of machine learning, especially deep learning technology in the field of artificial intelligence in recent years, computer vision, as a science of how to better understand and analyze images, has also shown a leap forward driven by data and computing power. progress. For example, in the task of image classification, the accuracy of the recognition of the object type by the machine running the deep learning algorithm has surpassed that of humans; in the task of target detection and localization, the algorithm based on deep learning has been widely used in intelligent video surveillance, robot navigation and based on Content image retrieval and other fields. [0003] The essence of the image description generation task is to complete t...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/143G06V10/80G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/253
Inventor 黄珺马泳马佳义樊凡王旭张灿
Owner WUHAN UNIV