Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Night image coloring method and device, medium and equipment

An image coloring and image technology, applied in the field of image processing, can solve the problems of inconsistent coloring effect and great subjectivity, and achieve the effect of improving the coloring quality

Active Publication Date: 2021-08-24
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with this method is that the selection of reference images requires a certain amount of work. A good reference image can achieve more accurate coloring, while a bad reference image can easily lead to a coloring effect that does not match the reality, which is relatively subjective.

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
  • Night image coloring method and device, medium and equipment
  • Night image coloring method and device, medium and equipment
  • Night image coloring method and device, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] This embodiment discloses a nighttime image coloring method, based on which the coloring of nighttime images without reference can be realized, such as figure 1 As shown, the specific steps include:

[0085] Step 1), construct a coloring network. In this example, if figure 2 As shown, the coloring network includes an encoder, a decoder, a fully connected layer and a softmax layer. The encoder is used to extract features from the fusion image; the decoder is used to obtain the color distribution from the features extracted by the encoder. in:

[0086] The encoder includes a first embedding module and a first self-attention module. The first embedding module inputs the fused image, and performs an embedding operation on the fused image; the image after the embedding operation of the first embedding module is input to the first self-attention module, and the feature extraction is performed by the first self-attention module, and the extracted features are used as codes...

Embodiment 2

[0142] This embodiment discloses a nighttime image coloring device, which includes a network building module, a training module, an image acquisition module, a fusion module and a coloring module, and the functions of the above-mentioned modules are as follows:

[0143] Network building blocks for building shading networks. In this example, if figure 2 As shown, the coloring network in this embodiment includes an encoder, a decoder, a fully connected layer and a softmax layer. The encoder is used to extract features from the fused image; the decoder is used to obtain the color distribution from the features extracted by the encoder, and the coloring network The specific structure is as described in Example 1.

[0144] The training module is used to train the shading network to obtain a shading model.

[0145] The image acquisition module is used to acquire visible light images and infrared images taken from the same angle of view at night.

[0146] The fusion module is con...

Embodiment 3

[0150] This embodiment discloses a storage medium, which stores a program. When the program is executed by a processor, the nighttime image coloring method described in Embodiment 1 is realized, as follows:

[0151] Build a shading network, and train the shading network to obtain a shading model;

[0152] Obtain visible light images and infrared images taken at the same angle of view at night;

[0153] According to the preset fusion rules, image fusion processing is performed on nighttime visible light images and infrared images to obtain a fusion image to be colored;

[0154] The fused image to be colored is input into a shading model for feature extraction and no-reference shading.

[0155] In this embodiment, reference may be made to the above-mentioned Embodiment 1 for specific implementation of the above-mentioned processes, and details are not repeated here.

[0156] In this embodiment, the storage medium may be a magnetic disk, an optical disk, a computer memory, a re...

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 night image coloring method and device, a medium and equipment, and the method comprises the steps: constructing a coloring network, and training the coloring network to obtain a coloring model; obtaining a visible light image and an infrared image shot at the same visual angle at night; according to a preset fusion rule, performing image fusion processing on the night visible light image and the infrared image to obtain a to-be-colored fusion image; and inputting a fusion image to be colored into the coloring model, and carrying out feature extraction and non-reference coloring. According to the method and device, feature fusion is carried out on the visible light image and the infrared image, the scene detail information in the visible light image and the target feature information in the infrared image are synthesized, and based on the trained coloring model, the non-reference night image coloring method is realized, and the coloring quality of the night image can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a night image coloring method, device, medium and equipment. Background technique [0002] Night imaging technology refers to the use of photoelectric detection or imaging equipment to convert scenes invisible to the human eye into visible images under low illumination conditions at night, thereby expanding the visual observation range of the human eye under low illumination at night and realizing Acquisition, processing and display of covert information under low illumination at night. [0003] Night vision imaging technology has important applications in production and life, transportation, military and other fields. For example, in the field of traffic travel, the use of night technology can effectively expand the observation range of the human eye, further enhance the ability to identify targets, and greatly avoid traffic accidents in low-light environments; while i...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V10/44G06N3/045G06F18/2415G06F18/253
Inventor 王恺孙季丰林逸彬
Owner SOUTH CHINA UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products