A Band Registration Method for Satellite Multispectral Imagery Based on Statistical Distribution
A multi-spectral image, statistical distribution technology, applied in image analysis, image data processing, calculation, etc., can solve problems such as image registration that are not suitable for large grayscale differences, and achieve wide application, high precision, and improved speed. and robustness effects
Active Publication Date: 2016-03-23
CHINA CENT FOR RESOURCES SATELLITE DATA & APPL
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Image registration algorithms are often divided into two methods based on region and feature, but they are generally only suitable for images with small grayscale differences, reflecting the linear characteristics between data, and not suitable for images with large grayscale differences. Registration
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
[0017] The invention realizes the registration method based on the mutual information based on the statistical information of the gray distribution as the registration similarity measurement, it does not need to perform preprocessing such as segmentation and feature extraction on the image, and has a wide range of applications and high precision and better robustness. At the same time, in order to improve the registration accuracy and speed, the present invention organically combines the mutual information realization method and the image pyramid algorithm, so that the single registration process becomes a multi-resolution coarse-to-fine registration process.
[0018] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments. Such as figure 2 Shown, a kind of satellite multispectral image band registration method based on statistical distribution of the present invention, the steps are as follows:
[0019] (1) if ...
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 discloses a statistical distribution-based satellite multi-spectral image waveband registration method, which comprises the following steps: (1) performingdown-sampling on a reference image and to-be-registered images by using a gauss template function to generate not less than two layers of images with different resolutions respectively by taking any spectral image of the multi-spectral image as the reference image, and processing each to-be-registered image according to the following steps; (2) calculating the marginal probability distribution and the joint probability distribution of the reference image and the to-be-registered image on the first low-resolution image layer and calculating a negative mutual information value between the reference image and the to-be-registered image, and performing iterative optimization by taking negative mutual information as a target function to solve the minimal similarity measured value or a translation transformation parameter at the time when a specified iteration frequency is reached; and (3) solving a transformation parameter according to processing similar to the step 2 by using the transformation parameter obtained by the previous layer on the remaining high-resolution image layers from low resolution respectively and transforming and resampling the to-be-registered image on the last layer by using the transformation parameter to obtain the registered image.
Description
technical field [0001] The invention relates to a processing method for satellite multispectral image registration. Background technique [0002] Remote sensing technology has now been transferred to practical applications at the social and scientific level, including natural disaster management, climate change assessment, natural resource management, environmental protection, etc., all of which involve long-term monitoring of the earth's surface. In recent years, image registration has become very important in remote sensing applications. Image registration is a basic task in image processing, which refers to matching two or more images of the same object or scene from different times, different remote sensors, and different perspectives. Image registration is used in digital image processing to accurately align two or more digital images for analysis and comparison, involving knowledge in many fields such as physiology, computer vision, pattern recognition, and image unde...
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): G06T7/00
Inventor 吕江安郝雪涛孙业超
Owner CHINA CENT FOR RESOURCES SATELLITE DATA & APPL