Small target super resolution reconstruction method for remote sensing image
A technology for super-resolution reconstruction and remote sensing images, which is applied in the field of high-efficiency algorithms for super-resolution image reconstruction of satellite remote sensing images, can solve problems such as image influence, and achieve the effects of fast algorithm speed, high deblurring efficiency, and improved spatial resolution.
Inactive Publication Date: 2009-07-08
WUHAN UNIV
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] However, the key issue in the current research on super-resolution images is still the impact of the amplification of high-frequency noise on the image in the process of image restoration.
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
[0036] 1. Theoretical basis
[0037] Satellite remote sensing imaging systems are inevitably subject to defocusing, undersampling, and system random noise caused by atmospheric disturbances, imaging system relative ground object scene motion, geometric deformation, etc., resulting in descaling and degradation of remote sensing images. The support domain of the observation image, the atmospheric disturbance layer brings serious deformation to the observation image. Super-resolution reconstruction is an algorithm for reconstructing images with better image quality and higher spatial resolution from images with poorer quality and lower resolution. It is actually an inverse problem. When performing inversion operation, the inversion does not necessarily have a solution, that is, a singular problem; in addition, the inversion equation may have multiple solutions. Both of these situations are known as the pathological nature of image restoration.
[0038] Theoretically, the suppor...
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 super-resolution reconstruction method for small targets in remote sensing images proposes a model for super-resolution image reconstruction of remote sensing images with reduced resolution. The spatial resolution is increased to 1.5 times that of the original image, and parasitic ripples are effectively suppressed; linear objects and empirical functions Estimate the de-definition parameter H of the atmospheric disturbance image; de-correlation and de-noising operator, redundant wavelet decomposition using mirror wavelet basis function, using its orthogonal correlation, based on the realization of morphological wavelet nonlinear wavelet coding in the wavelet domain, suppression of high frequency random noise; according to signal noise and signal energy spectral density, dynamically balance the influence of high-frequency noise signal and high-frequency detail signal on deblurring; deblurring operator, deconvolution does not need to know the precise optical transfer function of the system in advance. It can be applied to military target recognition in satellite images, detection of small targets and remote sensing image measurement of land resources.
Description
technical field [0001] The invention belongs to a high-efficiency algorithm for satellite remote sensing image super-resolution image reconstruction, and is mainly used in satellite image military target recognition, small target detection, remote sensing image measurement, and high-definition television (HDTV). Background technique [0002] In the process of satellite optical imaging, transmission, and acquisition of remote sensing images, due to the influence of atmospheric disturbance, defocus, and relative motion on the imaging system, the image will be degraded to varying degrees, typically blurring, distortion, and additive noise. Super-resolution reconstruction is an algorithm for reconstructing images with better image quality and higher spatial resolution from images with poorer quality and lower resolution. It is mainly used in satellite image military target recognition, small target detection and remote sensing image measurement. . In 2002, France successfully 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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01S7/48G01S17/89
Inventor 秦前清孙涛杨志高蒋志勇林立宇
Owner WUHAN UNIV