Building damage detection method and device based on image superpixel fusion
A detection method and detection device technology, which are applied in the field of remote sensing image fusion target detection, can solve problems such as application scenario limitations, and achieve the effects of solving the limitations, high accuracy and effectiveness.
Active Publication Date: 2020-10-16
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0009] For this reason, an object of the present invention is to propose a building damage detection method based on image superpixel fusion, which can still detect building damage when there is a large difference in the resolution of the synthetic aperture radar image and the optical image, With high accuracy and effectiveness, it solves the limitations of application scenarios
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
[0040] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.
[0041] Before describing the building damage detection method and device based on image superpixel fusion according to the embodiment of the present invention, let us briefly describe the defects in the related technology.
[0042] In related technologies, such as the proposed building damage detection algorithm based on multi-mutual information. Based on the geometric parameters of the buildings extracted from the pre-earthquake optical images, the algorithm simulates the shape of these buildings in the SAR image. By comparing w...
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 building damage detection method and device based on image superpixel fusion, wherein, the method comprises the following steps: at least one synthetic aperture radar image and at least one optical image are subjected to superpixel segmentation and mutual correspondence processing to extract the superpixels of a plurality of building damage detection images; According tothe superpixels of several building damage detection images, the confidence level of building damage in each building damage detection image is described by using BBA superpixels one by one. In orderto obtain the final building damage detection results, the BBA of the corresponding super pixels in the multi-building damage detection images is fused to obtain the final building damage detection results. This method can detect building damage even when the resolution of SAR image and optical image is different. The method has high accuracy and effectiveness and solves the limitation of application scene.
Description
technical field [0001] The invention relates to the technical field of remote sensing image fusion target detection, in particular to a building damage detection method and device based on image superpixel fusion. Background technique [0002] Superpixel segmentation is a new image segmentation method proposed in recent years, which can divide the image into a series of sub-regions with strong internal consistency, that is, superpixels. Compared with pixels, the shape and size of superpixels are not strict. , which means that superpixels can represent remote sensing images in a flexible way. The Belief Assignment Function (Basic Belief Assignment, BBA) is a function specially used for information fusion, which can not only describe the confidence of the category to which the data belongs, but also evaluate the reliability of the confidence description. [0003] In related technologies, such as the building damage detection method based on the fusion of SAR images and optica...
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): G06T7/00G06T5/50G06T7/10
CPCG06T5/50G06T7/0002G06T7/10G06T2207/10044G06T2207/10052G06T2207/20221G06T2207/30181
Inventor 李刚蒋骁何友
Owner TSINGHUA UNIV