Unlock instant, AI-driven research and patent intelligence for your innovation.

Staring infrared degraded image adaptive restoration method

A degraded image, self-adaptive technology, applied in image enhancement, image data processing, instruments, etc., can solve problems such as unfavorable image understanding and analysis, failure to use local feature information, and poor visual effect of restored images

Active Publication Date: 2016-11-16
NANJING LES ELECTRONICS EQUIP CO LTD
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing infrared image restoration methods have the following disadvantages: (1) Most of the existing infrared image restoration methods are only suitable for input images with high SNR. Use the understanding and analysis of images by humans or machines; (2) Most existing infrared image restoration methods use the same regularization parameter to regularize the entire image, without using local feature information, resulting in the loss of a large amount of detailed information in the restoration process ; (3) Most of the existing image restoration methods have a large amount of computation and are not easy to realize in real time by hardware

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
  • Staring infrared degraded image adaptive restoration method
  • Staring infrared degraded image adaptive restoration method
  • Staring infrared degraded image adaptive restoration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The focal plane array size of the infrared thermal imager is 640×512, and the working frame rate is 50 frames per second. The image processing platform adopts DSP+FPGA architecture, and the adaptive restoration method of staring infrared degraded images is implemented in the DSP processor to meet the needs of real-time processing.

[0051] It can be understood that, in step S1, the DSP processor input image is a 16-bit digital image, and the image size is 640×512. In the following description, i and j in the coordinates (i, j) of the image are respectively integers, and 1≤i≤512, 1≤j≤640.

[0052] In this embodiment, the image restoration process usually needs to be carried out according to a certain image degradation model, and a simple general image degradation model can model the image degradation process as an action on the original image f(x, y). The degenerate system H, the result of the joint action with a Gaussian noise n(x,y) results in a degraded image g(x,y)....

Embodiment 2

[0081] The focal plane array size of the infrared thermal imager is 320×256, and the working frame rate is 50 frames per second. The image processing platform adopts DSP+FPGA architecture, and the adaptive restoration method of staring infrared degraded images is implemented in the DSP processor to meet the needs of real-time processing.

[0082] It can be understood that, in step S1, the DSP processor input image is a 16-bit digital image, and the image size is 320×256. In the following description, i and j in the coordinates (i, j) of the image are respectively integers, and 1≤i≤256, 1≤j≤320.

[0083] In this embodiment, the image restoration process usually needs to be carried out according to a certain image degradation model, and a simple general image degradation model can model the image degradation process as an action on the original image f(x, y). The degenerate system H, the result of the joint action with a Gaussian noise n(x,y) results in a degraded image g(x,y)....

Embodiment 3

[0112] The focal plane array size of the infrared thermal imager is 640×512, and the working frame rate is 50 frames per second. The image processing platform adopts DSP+FPGA architecture, and the adaptive restoration method of staring infrared degraded images is implemented in the DSP processor to meet the needs of real-time processing.

[0113] It can be understood that, in step S1, the DSP processor input image is a 16-bit digital image, and the image size is 640×512. In the following description, i and j in the coordinates (i, j) of the image are respectively integers, and 1≤i≤512, 1≤j≤640.

[0114] In this embodiment, the image restoration process usually needs to be carried out according to a certain image degradation model, and a simple general image degradation model can model the image degradation process as an action on the original image f(x, y). The degenerate system H, the result of the joint action with a Gaussian noise n(x,y) results in a degraded image g(x,y)....

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 staring infrared degraded image adaptive restoration method and belongs to the field of image data processing. The method comprises the steps of building an image degradation model A; calculating an information entropy of an input image and an anisotropic diffusion coefficient of the input image; calculating a regularization coefficient lambda (i,j) at any coordinate (i,j) according to the information entropy and the anisotropic diffusion coefficient; and finally calculating a restored image according to the input image I, the image degradation model A and the regularization coefficient lambda (i,j). According to the method, the regularization coefficient is calculated according to a proportion of the information entropy and the anisotropic diffusion coefficient G in combination with characteristics of the information entropy and the anisotropic diffusion coefficient G, the method has a multi-scale restoration capability, functions of good image smoothing area regularization capability and poor image detail area regularization capability are realized, and image restoration is more accurate; and meanwhile, high-order operations and complex structures do not exist in the image restoration process, the calculation amount of an algorithm is small, and real-time hardware implementation is facilitated.

Description

technical field [0001] The invention belongs to the field of image data processing, and in particular relates to an adaptive restoration method for staring infrared degraded images. Background technique [0002] In the process of infrared image acquisition, transmission and processing, due to the influence of factors such as atmospheric disturbance, poor focus of the optical system, relative movement of the scene and imaging device, etc., the quality of the obtained image decreases and the image becomes blurred. In order to obtain images with high signal-to-noise ratio and high definition, it is necessary to restore the degraded image according to the image degradation model. [0003] Image restoration is a basic and premise processing process in the field of image processing, and occupies an extremely important position in primary visual processing. Scholars at home and abroad attach great importance to the research in this area. According to the known prior knowledge, ima...

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): G06T5/00
CPCG06T5/00
Inventor 白俊奇赵春光成伟明陈福玉苗锋朱伟司晓云刘文
Owner NANJING LES ELECTRONICS EQUIP CO LTD