Low illumination video image enhancement method based on multi-sensor fusion

A multi-sensor fusion, video image technology, applied in image enhancement, image analysis, graphics and image conversion, etc., can solve the problems of low registration accuracy, poor real-time performance, and inaccurate fusion of heterogeneous and multi-scale video images

Active Publication Date: 2019-01-22
CHANGCHUN UNIV OF SCI & TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a low-illuminance video image enhancement method based on multi-sensor fusion to solve the problems of low registration accuracy, poor real-time performance, and inaccurate fusion of heterogeneous and multi-scale video images, and improve the visibility of video images in low-illuminance environments , realizing the real-time fusion of heterogeneous and multi-scale video images, which not only retains the rich color information of visible light images, but also increases the information of infrared images, improving the quality of video images

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
  • Low illumination video image enhancement method based on multi-sensor fusion
  • Low illumination video image enhancement method based on multi-sensor fusion
  • Low illumination video image enhancement method based on multi-sensor fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] Include the following steps:

[0068] 1. In the case that the infrared imaging sensor and the visible light imaging sensor are fixed and collected at the same time, a set of infrared video and visible light video are collected, and the corresponding frames im1 and im2 of the infrared video and visible light video are read respectively; here, the infrared image size is 576 ×704, the size of the visible light image is 640×480;

[0069] 2. Image preprocessing

[0070] For the enhancement of the infrared image, the method used is to invert each pixel of the infrared image, and define a 576×704 unit matrix E. The specific implementation is as in formula 1;

[0071] im1=255*E-im1 (1)

[0072] The infrared image after taking the inversion is smoothed by means of difference filtering, and the difference filtering is carried out on the infrared image after taking the inversion, as shown in formula 2;

[0073]

[0074] 3. Generation of extreme point scale space

[0075] Th...

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 relates to a low-illuminance video image enhancement method based on multi-sensor fusion, belonging to the field of video image processing. According to the feature similarity between heterogeneous videos, the multi-scale SIFT algorithm is used for registration of heterogeneous images. According to the combination of multi-scale SIFT algorithm and ransac algorithm, an accurate transformation matrix can be obtained. Using this The transformation matrix interpolates each frame of the infrared video image and the visible light video image respectively, so that the images of different resolutions are transformed into images of the same resolution, thus solving the image registration of different resolutions. Then, a weighting algorithm based on α is used to realize the fast fusion of each frame of images, so that the fusion time of the images meets the real-time requirements of the video, and achieves the effect of real-time video display. The definition of the video is improved, and the information contained in the clear video is also rich and colorful, which is convenient for subsequent processing.

Description

technical field [0001] The invention belongs to the field of video image processing. Background technique [0002] Visible light videos taken in low-light environments have low visibility, and people cannot identify specific scenes and people based on the videos. This has brought inconvenience to many fields such as military affairs, medicine, civilian use, so the research of this technology has important effect. Low-light video image enhancement technology can be used in military navigation monitoring systems, or frontier night vision systems and applications of remote sensing images; in the medical field, it can be used to detect human cells or blood vessels, and then analyze the physical condition of the human body ; The application in the field of life is even more extensive, and can be used in the night shooting system of mobile phones, the monitoring system of shopping malls, the application of artificial intelligence (clear video is conducive to the identification an...

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 & AuthorityPatents(China)
IPC IPC(8): G06T5/00G06T5/50G06T3/00G06T3/40G06T7/30
CPCG06T3/0068G06T3/4038G06T5/002G06T5/50
Inventor朴燕王钥
OwnerCHANGCHUN UNIV OF SCI & TECH