Road network recognition quality improvement method based on superposition cutting
A quality and road network technology, applied in the field of road network identification quality improvement based on superposition cutting, can solve the problems of low road network quality, road discontinuity, dislocation, etc., and achieve the effect of improving the extraction quality
Pending Publication Date: 2022-07-12
上海城市交通设计院有限公司 +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to propose a method for improving the quality of road network recognition based on superimposition and cutting, aiming at solving the problem that in the road recognition algorithm, it is necessary to cut and predict the image, so that the pixels located near the cutting cannot obtain enough information during prediction , so that the quality of the road network predicted at the cutting point is low, resulting in road discontinuity, dislocation, etc.
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
[0027] The technical solutions of the present invention will be further described below based on specific embodiments.
[0028] Due to the limitation of hardware conditions, it is difficult to use a whole high-resolution remote sensing image as input to predict road information. Therefore, the high-resolution remote sensing image is cut first. Here, it is assumed that the size of the original image is M*N, and the image is cut into k*k small images. In order to make the size of each small image equal, we add a width of , with an all-zero pixel bar added to the right of the original image with a width of of all zero pixel bars. After slicing, we can get a total of Zhang Xiaotu, in order to finally assemble the thumbnail into the original image, we need to number the thumbnails. We set the pixel coordinates of the upper left corner of the original image to (0, 0), so the pixel with coordinates (m, n) is located in the mth row and nth column of the original image. we use...
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 road network recognition quality improvement method based on superposition cutting, which is characterized in that a complete remote sensing image is cut by using different cutting modes in a prediction stage, so that pixels located at the edge of a cutting line are located in a small image in a first cutting mode, and pixels located at the edge of the cutting line in a second cutting mode. Therefore, relatively complete information is obtained, and finally, the results of the two cutting predictions are linearly superposed. By adopting a two-time cutting mode, the pixels located at the edge of the cutting line under the first cutting mode, the pixels located at the inner part of the small image under the second cutting mode, and similarly, the pixels located at the edge of the cutting line under the second cutting mode, the pixels located at the edge of the cutting line under the first cutting mode, and the pixels located at the edge of the cutting line under the second cutting mode are located at the inner part of the small image under the second cutting mode. In this way, it can be guaranteed that complete information is obtained, and therefore the road extraction quality can be improved.
Description
technical field [0001] The invention belongs to the technical field of road recognition in remote sensing images, and in particular relates to a road network recognition quality improvement method based on superimposed cutting. road extraction quality. Background technique [0002] Road remote sensing information technology is an indispensable part of my country's modern urban and social and economic development. It is of great social scientific and technical significance to study the application of remote sensing road images and the methods of road information extraction. The design scope of automatic remote sensing road information extraction technology covers many fields and tasks such as urban planning, intelligent rail transit, updating of geographic information systems, and comprehensive utilization of land resources. [0003] Large-scale automatic road extraction using remote sensing images has received extensive attention in recent years. However, due to the large ...
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): G06V20/10G06V10/26G06V10/80G06V10/82G06K9/62G06N3/02
CPCG06N3/02G06F18/251
Inventor 张品立俞雪雷王智慧何千羽朱鲤陶莎王佳凯
Owner 上海城市交通设计院有限公司