CN112733621A

CN112733621A - Map high-precision information identification method

Info

Publication number: CN112733621A
Application number: CN202011560048.XA
Authority: CN
Inventors: 李麟; 温为国; 何海清; 康俊峰
Original assignee: Jiangxi Yufeng Intelligent Agricultural Technology Co ltd
Current assignee: Jiangxi Yufeng Intelligent Agricultural Technology Co ltd
Priority date: 2020-12-25
Filing date: 2020-12-25
Publication date: 2021-04-30

Abstract

The invention discloses a map high-precision information identification method, which comprises the following steps: s1, extracting roads, S2, unifying the colors of the roads, S3, eliminating characters in the roads, S4, smoothing the roads, S5, refining the roads, S6, vectorizing the roads, S7, and producing vectorized files and transmitting the vectorized files to terminal equipment. According to the map high-precision information identification method, the road is identified and extracted in a mode of combining the circularity and the color characteristics, characters in the road are removed in the extraction process, the road is smoothed, the accuracy and effectiveness of the road identification are guaranteed, and the display effect is improved.

Description

Map high-precision information identification method

Technical Field

The invention relates to the technical field of map identification methods, in particular to a map high-precision information identification method.

Background

The map is a graph which is drawn according to a certain drawing rule by using a drawing method and is integrated on a certain carrier through drawing to express the spatial distribution, the relation and the development change state in time of various things on the earth (or other celestial bodies).

The map is a graph or image which selectively represents a plurality of phenomena of Earth (Earth) (or other stars) on a plane or a spherical surface in a two-dimensional (2D) or multi-dimensional (3D) form and means according to a certain rule, has strict mathematical basis, symbol system and character annotation, and can scientifically reflect the distribution characteristics and the mutual relations of the natural and social economic phenomena by using the general principle of the map. The definition of the map at the present stage is as follows: the image symbol model reflecting the objective reality is expressed in a certain Math (Math) rule (namely modeling), symbolization and abstraction, or is called as a graphic mathematic model. The map is based on a certain mathematical rule, and uses map language to reduce and reflect the natural and human phenomena on the earth (or other stars) on the plane by drawing synthesis, and reflects the spatial distribution, combination, connection, quantity and quality characteristics of various phenomena and the development change of various phenomena in time.

In color maps, identifying and extracting a certain geographic element by using a difference in color is a relatively natural extraction method, and is also the most commonly used method in map identification. However, it is not easy for the computer to layer the datamation map obtained from the scanner according to colors, because the paper map may cause the color difference of the original same color content due to printing or use, and may cause the obtained color to slightly change due to the fact that the placement of the map cannot be absolutely flat during the scanning process. Although the color differences and changes can be ignored when people read the map and the map is correctly identified without being influenced by the color differences and changes, the differences and changes become a problem which cannot be ignored and even need to be solved intensively when the work is completed by a computer. Therefore, if the elements in the map are recognized by colors alone, many errors may be caused, resulting in a low recognition rate.

Disclosure of Invention

The invention mainly aims to provide a map high-precision information identification method which can effectively solve the problems in the background technology.

In order to achieve the purpose, the invention adopts the technical scheme that:

a map high-precision information identification method comprises the following steps:

s1, extracting roads;

s2, unifying the colors of the roads;

s3, eliminating characters in the road;

s4, smoothing the road;

s5, road refinement;

s6, road vectorization;

and S7, producing the vectorized file and transmitting the vectorized file to the terminal equipment.

Preferably, the step S1 of road extraction includes the steps of:

s11, scanning the map by a scanner and transmitting the map to a computer;

s12, according to the scanned map, according to the calculation formula of the image degree, the circularity of each road is calculated by using tool software;

s13, marking areas with the same or similar colors as the road;

and S14, extracting the road, rescanning the image, setting unmarked pixels as white pixels, calculating the circularity of each area of the label value, setting all the pixels of the connecting components of the area as the white pixels if the result is not between 0 and 0.2, otherwise, not changing, and outputting the road image.

Preferably, in step S2, the colors of the roads are unified, the legend of the map is used to extract the colors of the legend roads, the entire map is scanned to calculate the distances between the colors of the roads in the map example and the colors in the map, if the distance is smaller than a smaller threshold, the color in the map is determined to identify the road, and the color is replaced with white.

Preferably, in step S3, the characters in the road are erased, and the characters are erased by erosion and dilation operations using grayscale morphology.

Preferably, in the process of eliminating the text, the scanning can be carried out for a plurality of times until the noise is completely removed from the map.

Preferably, in the step S4, the image obtained in step S3 should be scanned first, and if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and during scanning, line scanning is performed first, and then line-by-line scanning is performed.

Preferably, the road refinement in step S5 is implemented by using Hilditch classical refinement algorithm.

Preferably, the road vector in step S6 is a contour tracing method.

Compared with the prior art, the invention has the following beneficial effects:

the high-precision map information identification method provided by the invention has the advantages that the method for identifying and extracting the road is realized by combining the circularity and the color characteristics, the characters in the road are removed in the extraction process, the road identification accuracy and effectiveness are ensured by the step of smoothing the road, and the display effect is improved.

Detailed Description

In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.

s1, extracting roads;

s2, unifying the colors of the roads;

s3, eliminating characters in the road;

s4, smoothing the road;

s5, road refinement;

s6, road vectorization;

The step S1 road extraction includes the steps of:

s11, scanning the map by a scanner and transmitting the map to a computer;

s13, marking areas with the same or similar colors as the road;

In step S2, unifying the colors of the roads, extracting the colors of the roads in the map by using the legend of the map, scanning the entire map to calculate the distances between the colors of the roads in the map and the colors in the map, if the distance is less than a small threshold, identifying the road marked by the color in the map, and replacing the color with white.

In step S3, characters in the road are erased, and the characters are erased by erosion and expansion operations using grayscale morphology.

In the process of eliminating text, the scan may be performed several times until the noise is completely removed from the map.

Step S4 is to smooth the road, the image obtained in step S3 should be scanned first, if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and during scanning, line scanning is performed first, and then line-by-line scanning is performed.

In step S5, the road refinement is performed by using Hilditch classical refinement algorithm.

The road vector in step S6 is a contour tracing method.

The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims

1. A map high-precision information identification method is characterized by comprising the following steps:

s1, extracting roads;

s2, unifying the colors of the roads;

s3, eliminating characters in the road;

s4, smoothing the road;

s5, road refinement;

s6, road vectorization;

2. The method of claim 1, wherein the method comprises: the step S1 road extraction includes the steps of:

s11, scanning the map by a scanner and transmitting the map to a computer;

s13, marking areas with the same or similar colors as the road;

3. The method of claim 1, wherein the method comprises: in step S2, unifying the colors of the roads, extracting the colors of the roads in the legend of the map, scanning the entire map to calculate the distances between the colors of the roads in the map example and the colors in the map, if the distance is smaller than a smaller threshold, determining that the color in the map identifies the road, and replacing the color with white.

4. The method of claim 1, wherein the method comprises: in step S3, the characters in the road are erased, and the characters are erased by erosion and expansion operations using grayscale morphology.

5. A map high-precision information identification method according to claim 4, characterized in that: in the process of eliminating the characters, the characters can be scanned for a plurality of times until the noise is completely removed from the map.

6. The method of claim 1, wherein the method comprises: in step S4, the image obtained in step S3 should be scanned first, and if the number of black pixels connected between two white pixels is less than 3, the black pixels are replaced with white pixels, and line scanning is performed first during scanning, and then line-by-line scanning is performed.

7. The method of claim 1, wherein the method comprises: in the step S5, the road refinement is implemented by using Hilditch classical refinement algorithm.

8. The method of claim 1, wherein the method comprises: the road vectorization in step S6 is to adopt a contour tracking method.