Supercharge Your Innovation With Domain-Expert AI Agents!

Method and system for automatically colorizing night-vision images

一种图像、夜视的技术，应用在2D图像的生成、电视系统的零部件、图像增强等方向，能够解决无法使用大型数据库前期处理或后期处理等问题

Pending Publication Date: 2020-01-03
HELLA KG HUECK & CO
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Also, especially when processing video streams, coloring must happen in real-time, and preferably locally, thus making it impossible to use large databases or complex and time-consuming pre- or post-processing

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 and system for automatically colorizing night-vision images
  • Method and system for automatically colorizing night-vision images
  • Method and system for automatically colorizing night-vision images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] already discussed in the background section figure 1 A schematic diagram of a convolutional neural network according to the prior art is shown. As described above, the feature map 104 associated with the convolutional layer 103 is used to scan the sub-regions 102, 102' of the input image 101 . The feature map 104 is trained and used as a filter in order to detect local patterns in the input image 101 . The output of the convolutional layer 103 is then sub-sampled by a sub-sampling layer 105 in order to reduce the spatial resolution.

[0089] figure 2 A system for displaying a rendered image independent of current light conditions is shown. To achieve this, a NIR camera 201 - 1 and a color camera 201 - 2 are provided and connected to the processor 203 . Processor 203 is configured to receive images from either of the two cameras, to determine which image to display, to process the received image if necessary, and to display the output image on display 204 . The pro...

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

This application discloses a method as well as a system for generating a first color image (405) from a first night-vision image (NIR|n). First, predicted chrominance values (CVIS_Rec) are determined(S403), by using a prediction function (fPred), based on luminance values (LNIR_In) of the first night-vision image (NIRIn). Then the first color image (405) is generated by combining (S404) the luminance values (LNIR_In) of the first night-vision image (NIRIn) with the predicted chrominance values (CVIS_Rec).

Description

technical field [0001] The present application is directed to methods and systems for automatically colorizing night vision images. Background technique [0002] Night vision systems can be used in a variety of contexts, such as driver assistance systems, wildlife observation, military applications, security and surveillance systems, or picture or movie applications (eg, installed in smartphones or other mobile cameras). Night vision images capture the invisible radiation of objects and are often taken using an active source of invisible radiation which is then reflected by the corresponding object. [0003] Because at night or in low light conditions, light is absent or minimal, night vision images are monochromatic in appearance. The advantage of night vision images is that night vision images can be taken without visible light, based on capturing energy distribution or distance distribution (related to distance laws) by using eg infrared, ultrasound or radar. However, b...

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 Applications(China)
IPC IPC(8): G06T11/00G06K9/00H04N5/33
CPCG06T11/001G06N3/08G06T2207/10024G06T2207/20081G06T2207/20084G06N3/045
Inventor A·伯耐克M·格拉泽S·沙费尔
Owner HELLA KG HUECK & CO
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