Remote sensing image building extraction method based on attention mechanism and channel information
A technology of remote sensing image and extraction method, which is applied in the direction of mechanical equipment, combustion engines, computer parts, etc., can solve the problem of insufficient extraction accuracy, and achieve the effect of improving extraction accuracy
Active Publication Date: 2019-08-27
INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem to be solved by the present invention is to provide a method for extracting buildings from remote sensing images based on attention mechanism and channel information, so as to solve the shortcomings of existing methods that the extraction accuracy is not high enough
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
[0037] The specific implementation manners of the present invention will be described in detail below in conjunction with the accompanying drawings. However, the following examples are only used to illustrate the present invention in detail, and do not limit the scope of the present invention in any way. The programs involved or relied on in the following embodiments are conventional programs or simple programs in the technical field, and those skilled in the art can make conventional selections or adaptive adjustments according to specific application scenarios.
[0038] Such as Figure 1-3 Shown, a kind of remote sensing image building extraction method based on attention mechanism and channel information of the present invention comprises the following steps:
[0039] Step 1. Collect training samples: collect target images through remote sensing image acquisition equipment, mark and preprocess the target images so that the images meet the format requirements, and construct...
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 provides a remote sensing image building extraction method based on an attention mechanism and the channel information which aims to solve the technical problem that an existing buildingextraction method is low in precision. The method comprises the following steps of 1, collecting a training sample; 2, building a deep learning framework, and constructing a U-shaped network based onthe attention mechanism and the channel information; 3, performing enhancement processing on the training sample; 4, designing a loss function and optimizing the loss function; 5, training the U-shaped network to obtain a building extraction model; 6, extracting a building. The building extraction method has the beneficial technical effect that the building can be quickly and accurately extracted.
Description
technical field [0001] The invention relates to the technical field of image segmentation, in particular to a method for extracting buildings from remote sensing images based on attention mechanism and channel information. Background technique [0002] Building information plays an important role in applications such as military reconnaissance, geographic information system (GIS) data update, urban planning, disaster prevention, resource investigation, and digital city construction. With the development of remote sensing technology, a large amount of remote sensing data becomes possible. However, in ordinary RGB remote sensing images, it is difficult to extract buildings due to the complex background of roads and squares. Therefore, developing reliable and accurate building extraction methods has become an important and challenging research topic. [0003] In the past decades, many building extraction studies are based on traditional image processing methods. In feature e...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/176G06F18/217Y02T10/40
Inventor 胡钦涛毛耀周国忠段倩文何秋农周翕李志俊张超乔琦聂康
Owner INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI