SAR (Synthetic Aperture Radar) image changing and detecting method based on CUDA (Compute Unified Device Architecture) and steady WT (Wavelet Transform)
A technology of image change detection and stationary wavelet, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of not being able to meet the actual needs of the project and the poor real-time performance of SAR image change detection, and achieve easy understanding and enhancement. Large size, the effect of reducing the waste of space
Inactive Publication Date: 2015-07-01
XIDIAN UNIV
View PDF2 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is to aim at the shortcoming that the current SAR image change detection has poor real-time performance and cannot well meet the actual needs of engineering, and proposes a SAR image change detection method based on CUDA and stationary wavelet transform, which can improve the speed of signal processing, Realize the real-time detection function in engineering
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] The present invention will be further described below in conjunction with accompanying drawing:
[0019] refer to figure 1 , is a flowchart of the SAR image change detection method based on CUDA and stationary wavelet transform of the present invention. The SAR image transform detection method based on stationary wavelet transform comprises the following steps:
[0020] Step 1, obtain the first SAR image data and the second SAR image data, and transmit the first SAR image data and the second SAR image data to the GPU side; at the GPU side, convert each SAR image data acquired into corresponding GRAY Image data, get two pieces of GRAY image data.
[0021] The specific steps are:
[0022] The first SAR image data and the second SAR image data are acquired, and the first SAR image data and the second SAR image data are original SAR image data that need to perform SAR image change detection. The first SAR image data and the second SAR image data are respectively read in...
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
Login to View More Abstract
The invention belongs to the field of an SAR image transforming and converting technology, in particular to an SAR (Synthetic Aperture Radar) image changing and detecting method based on CUDA (Compute Unified Device Architecture) and steady WT (Wavelet Transform). The method comprises the specific steps of transmitting two SAR image data to a GPU (Graphics Processing Unit) end by the CPU; converting each SAR image data obtained into corresponding GARY image data; calculating the specific value different images Y of two GARY image data at the GPU end; comparing specific value different images Y to carry out two-dimensional WT to obtain all dimension low frequency components except a first scale; carrying out Bayes threshold division on all dimension low frequency components except a second scale, wherein S represents the number of scales when the multi-scale decomposition is carried out; carrying out inter-scale data fusion, so as to obtain the image data of change detection.
Description
technical field [0001] The invention belongs to the technical field of SAR image transformation detection, in particular to a SAR image change detection method based on CUDA and stationary wavelet transform, relates to the processing of Synthetic Aperture Radar (SAR) images, and can be used for real-time SAR image change detection. Background technique [0002] In SAR image change detection, due to the presence of coherent speckle noise in SAR images, it is necessary to suppress speckle noise. The general transformation detection method suppresses speckle noise through image filtering. Wavelet transform itself is a convolution operation, including The filtering process, but the discrete wavelet transform will cause image scaling, which will have a negative impact on the SAR image change detection results; CUDA platform, as a parallel platform for NVIDIA GPU, can make good use of the multi-core characteristics of GPU, obtain good parallelism, and improve image quality. proces...
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
Login to View More IPC IPC(8): G06T7/00G06T5/00
Inventor 李明杨纪伟李思宇吴艳张鹏左磊
Owner XIDIAN UNIV