Multi-scale neural network infrared image colorization method based on attention mechanism

An infrared image and neural network technology, applied in the field of computer vision, can solve the problems of poor imaging quality, blurred edges and detailed information, etc., and achieve the effect of improving processing accuracy, multi-detail texture, improving the quality of structural information and visual perception effect.

Pending Publication Date: 2022-06-03
XI AN JIAOTONG UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the differences in imaging principles between infrared images and visible light images, directly applying the colorizatio

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
  • Multi-scale neural network infrared image colorization method based on attention mechanism
  • Multi-scale neural network infrared image colorization method based on attention mechanism
  • Multi-scale neural network infrared image colorization method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] refer to Figure 1-5 , the infrared image coloring method based on the attention mechanism proposed by the present invention mainly includes three steps of feature extraction, feature fusion and generation of colored images:

[0069] 1) figure 1 It is a schematic diagram of the overall framework of the present invention. The input of the neural network model to complete the infrared image coloring task is the infrared image I in , the output is the shaded image I out . During training, input infrared images are aligned with real color images. The network will learn a function (model) f satisfying the following relation:

[0070] f(I in ) = I out

[0071] Specifically, the network first passes through three downsampling convolution modules from the original input infrared image I in Four high-dimensional feature information F with different resolutions are extracted from 1 , F 2 , F 3 and F 4 , and then F through the attention module 1 , F 2 , F 3 and F ...

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 multi-scale neural network infrared image colorization method based on an attention mechanism, and the method comprises the steps: carrying out the feature extraction of an input infrared image under different resolution scales through a two-dimensional convolutional neural network, and carrying out the extraction of the extracted high-dimensional feature information through the attention mechanism, and finally carrying out fusion processing on the multi-scale information to obtain a predicted colorized infrared image. Compared with an existing infrared image colorization network, the method has the advantages that a neural network algorithm model is constructed based on an attention mechanism and a multi-scale hierarchical structure, and by adopting an improved spatial attention and multi-dimensional feature connection mechanism, the network model feature extraction capability can be improved while the model complexity is effectively reduced; by designing a composite loss function of pixel loss, edge loss and perception loss, the quality of the colorized infrared image is further improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an attention mechanism-based multi-scale neural network infrared image colorization method. Background technique [0002] Infrared image colorization is a research issue that has attracted much attention in the field of computer vision, and has broad application prospects in various systems such as security monitoring, unmanned systems, and military equipment. In particular, how to achieve high-quality, high-resolution, and multi-detail color infrared images is an urgent challenge for this technology. In recent years, artificial intelligence based on deep learning technology has developed rapidly, and breakthroughs have been made in the fields of object detection, image classification, and speech recognition. As one of the application hotspots of computer vision, infrared image colorization also benefits from the continuous innovation of deep neural network 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
IPC IPC(8): G06T11/40G06N3/04G06N3/08
CPCG06T11/40G06N3/08G06N3/048G06N3/045
Inventor 汪航孙宏滨程成张旭翀
Owner XI AN JIAOTONG UNIV
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