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

SAR image change detection method based on multi-GPU task optimization

A technology for image change detection and task optimization, which is applied in the field of image processing, can solve problems such as the inability to meet the real-time processing requirements of synthetic aperture radar SAR image change detection, improve change detection speed and system resource utilization, improve change detection speed, The effect of high utilization of system resources

Active Publication Date: 2019-05-24
XIDIAN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to address the above-mentioned deficiencies in the prior art, and propose a method for SAR image change detection based on multi-GPU task optimization, which solves the problems of the prior art The problem that it cannot meet the real-time processing requirements of synthetic aperture radar SAR image change detection improves the detection speed of synthetic aperture radar SAR image change

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
  • SAR image change detection method based on multi-GPU task optimization
  • SAR image change detection method based on multi-GPU task optimization
  • SAR image change detection method based on multi-GPU task optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0041] combined with figure 1 , the steps of the present invention are further described in detail.

[0042] Step 1, read two synthetic aperture radar SAR images in real time I 1 , I 2 .

[0043] Step 2, for I 1 , I 2 Make scaling adjustments.

[0044] Alignment of two synthetic aperture radar SAR images I 1 , I 2 size, so that both are equal and the scenes of the two images are the same, the total number of horizontal pixels of the adjusted image is W, and the total number of vertical pixels is H.

[0045] Step 3, using multiple graphics processors GPU to obtain I 1 , I 2 The grayscale data matrix of .

[0046] In the video memory of the two graphics processors GPU, a width of high for The space is used to store the two-dimensional gray value array α 1 、α 2 ,in Indicates a round up operation.

[0047] Each graphics processing unit (GPU) a...

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 method of an SAR image change detection algorithm based on multi-GPU task optimization. The method comprises the steps of (1) reading two SAR images in real time; (2) carrying out scale adjustment on the image; (3) obtaining an image gray scale data matrix by utilizing a plurality of GPUs; (4) generating a logarithmic ratio difference image as an observation field; (5) performing initial binary segmentation on the observation field by the plurality of GPUs to obtain a mark field; (6) obtaining the prior probability of the mark field; (7) calculating a condition distribution probability by the plurality of GPUs; (8) re-marking the marking field; (9) judging whether a termination condition is met or not; And (10) obtaining a change detection result map. According tothe invention, the task decomposition is carried out by using the SAR change detection processing process, and the processing process is realized by using a plurality of graphic processing units (GPUs), so that the SAR image change detection speed is improved, and the method can be applied to real-time change detection of the SAR image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a synthetic aperture radar SAR (Synthetic Aperture Radar) image change detection based on task optimization of multiple graphics processors GPU (Graphics Processing Unit) in the technical field of image segmentation and image classification recognition method. The invention can be used to quickly detect the change information of the two time-phase synthetic aperture radar SAR images, thereby monitoring the changes of ground objects before and after earthquakes and the dynamic changes of crop growth states in real time. Background technique [0002] With the improvement of SAR image resolution, the running time of the image change detection algorithm executed on the central processing unit CPU (Central Processing Unit) becomes longer, so that it cannot meet the real-time requirements. Since the graphics processor GPU contains a large number of computing units ALU a...

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): G06T1/20G06F9/50G06T7/277G06T7/11
Inventor 李明朱呈良吴艳张鹏
Owner XIDIAN UNIV