Building space fusion discrimination method and device based on multi-temporal high-resolution data
A building space, high-resolution technology, applied in the field of target recognition, can solve the problems of low recognition accuracy, waste of samples, manpower and material resources, etc., to achieve the effect of high accuracy, strong practicability, and the need to reduce the number of samples
Active Publication Date: 2021-12-14
北京市城市规划设计研究院 +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, deep learning requires a large number of samples, and the samples are generally only applicable to specific areas, resulting in low recognition accuracy and a waste of samples, manpower and material resources
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
[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.
[0047] figure 1 It shows the flow chart of the multi-temporal high-resolution data-based building space fusion discrimination method provided by the embodiment of the present application, figure 2It is a flow chart of another architectural space fusion discrimination method based on multi-temporal high-resolution data provided by the embodiment of this application, image 3 It is a schematic diagram of the fusion building space probability map of the area to be identified in the year to be mea...
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 embodiment of the present application discloses a method and device for building space fusion and discrimination based on multi-temporal high-resolution data. The method includes: inputting the remote sensing images of the base year into the deep learning building space recognition model to obtain the building space recognition results of the base year; inputting the remote sensing images of each month of the year to be measured into the deep learning building space recognition model to obtain the building space recognition results of each month of the year to be measured Spatial recognition results; according to the building space recognition results of the base year and the building space recognition results of each month of the year to be measured, the monthly fusion building space probability map of different spatial positions in the area to be recognized in the year to be measured is obtained; the building space changes under different thresholds Compared with the artificially interpreted architectural change patches, determine the optimal probability threshold for fusing the architectural space probability map; determine the architectural space in the area to be identified in the year to be measured according to the optimal probability threshold. The embodiment of this application uses the fusion of architectural spaces in different years The probability value determines the architectural space of the year to be identified, which has high accuracy and strong practicability.
Description
technical field [0001] The present application relates to the technical field of target recognition, in particular to a method and device for building space fusion and discrimination based on multi-temporal high-resolution data. Background technique [0002] As an important object of man-made features, buildings are an important part of geographic information, and are of great significance in digital city construction, smart city construction, database update, and urban population layout. The ever-growing high-resolution remote sensing images have been widely used in surveying and mapping, cartography, traffic navigation, urban planning, protection of marine rights and interests, digital city construction and other fields. [0003] In the prior art, most of the deep learning methods are used to identify the architectural space of high-resolution remote sensing images. However, deep learning requires a large number of samples, and the samples are generally only applicable to...
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): G06K9/00G06K9/62G06N3/04G06N3/08G06N7/00
CPCG06N3/08G06N3/047G06N7/01G06N3/045G06F18/241G06F18/2415
Inventor 胡腾云石晓冬解鹏飞李雪草刘小平张晓东何莲娜孙道胜吴兰若
Owner 北京市城市规划设计研究院