A kind of image fusion method and device of depth image and infrared image

A depth image and infrared image technology, applied in the field of image processing, can solve the problems of not having infrared image recognition camouflage, unable to obtain scene depth information, unable to obtain scene temperature information, etc., and achieve the effect of strong environmental adaptability

Active Publication Date: 2021-06-18
青柠优视科技(北京)有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Infrared and visible light image fusion technology utilizes information complementarity between sensors and combines the characteristic information of the two images. Although it can highlight infrared targets and enhance scene understanding, it cannot obtain the depth information of the scene.
[0007] There are not many existing depth image and visible light image fusion technologies. There is only one patent for foreground detection method that uses the depth image and visible light image fusion, but only uses the probability and statistics indicators of the depth information in the depth image, and does not The image after the fusion of the depth image and the visible light image has not been finally obtained, and the temperature information of the scene cannot be obtained, and the infrared image does not have a good ability to identify camouflage

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 kind of image fusion method and device of depth image and infrared image
  • A kind of image fusion method and device of depth image and infrared image
  • A kind of image fusion method and device of depth image and infrared image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] For ease of understanding, some terms used in the present invention are explained below, but should not be construed as limiting the present invention.

[0042]Multi-scale decomposition: According to the research results of physiologists on the human visual system and the statistical model of natural images, an "optimal" image representation should have multi-resolution features: that is, it can continuously approximate the image from coarse resolution to fine resolution , layered expression. As an effective image representation with multi-resolution features, multi-scale decomposition is often used in the field of image processing. The multi-scale decomposition method first decomposes the original image into high-frequency and low-frequency components, and then continues to decompose the decomposed low-frequency components. This iterative process continues, so that the image is decomposed into sub-images of various levels. Common multi-scale decomposition methods incl...

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

An image fusion method of a depth image and an infrared image, comprising the following steps: (1) obtaining an infrared image and a depth image respectively by an infrared sensor and a TOF depth sensor; (2) extracting a scene, a target object and even a scene based on depth information in the depth image The edge contour information of each component of the object; (3) The depth image and the infrared image that have completed the registration operation are decomposed at multiple scales with the same parameters to obtain image expressions of different scales; (4) The detailed information representing the source image Select an appropriate fusion rule for the high-frequency component to determine the fusion coefficient, and select an appropriate fusion rule for the low-frequency component representing the contour information of the source image to determine the fusion coefficient; (5) process the fused coefficient through the corresponding multi-scale inverse transformation, and combine it with the edge contour The information is fused to obtain a fused image. In practical application, this method is less affected by visible light intensity and has strong environmental adaptability.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image fusion method and device for a depth image and an infrared image. Background technique [0002] Due to the imaging characteristics and limitations of a single image sensor, it is difficult to complete tasks such as detection, tracking, and reconnaissance under different imaging conditions and background environments. Therefore, image fusion technology uses information complementarity between sensors to integrate the characteristics of the two images, which can highlight target temperature information or depth information and enhance scene understanding. It has become a research hotspot in information fusion technology. [0003] In the prior art, there is a method for fusing visible light panchromatic images and infrared remote sensing images, which discloses a multi-scale and multi-level method for fusing visible light panchromatic images and infrared remote s...

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): G06T5/50G06T7/13
CPCG06T5/50G06T2207/10028G06T2207/10048G06T2207/20221G06T7/13
Inventor 杨新辉宫睿
Owner 青柠优视科技(北京)有限公司
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