KR101701241B1 - Improving method for road information of fdb based on histogram similarity and improving apparatus thereof - Google Patents

Abstract

The present invention relates to a method and an apparatus for improving road information of digital terrain information based on histogram similarity. A method for improving road information of digital terrain information based on histogram similarity according to an embodiment of the present invention includes: inputting digital terrain information (FDB) and aerial image (S100); Generating a road histogram from the digital terrain information (S200); Generating a block histogram from the aerial image (S300); And estimating roads using the road histogram and the block histogram (S400). According to the present invention, it is possible to shorten the mission time and save the fuel by creating the movement route based on the improved road information in the mission planning stage of the unmanned robot.

Description

TECHNICAL FIELD [0001] The present invention relates to a method and an apparatus for improving road information of digital terrain information based on histogram similarity,

The present invention relates to a method and an apparatus for improving road information of digital terrain information based on histogram similarity, and more particularly, And more particularly, to a method and an apparatus for improving road information of digital terrain information based on histogram similarity.

As the development of science and technology and the emphasis on human life are spreading, the use of unmanned robots is increasing. In the field of defense, it will be operated as a mixed and unmanned system in which the defense robot substitutes the duties of the risk field based on the incentive system in the future. As a result of this trend, research on defense robots is being actively carried out globally, and the US and Israel, the leaders of robot technology, are already deploying and operating. Research and development are underway in Korea, centered on the National Defense Science Institute.

The robot's mission control consists of mission environment analysis, mission planning, mission execution / modification, and mission evaluation. A well-proven mission plan is required to successfully perform a mission. The mission planning stage is to integrate the information provided from the outside and the information held by the operator and analyze the mission environment based on the result of analyzing the mission environment, selecting the mission equipment, setting the execution time, specifying the mission location, Lt; / RTI > Assigning the optimal robot to a specific task is the same as the optimization problem, and it takes a lot of time to travel to the mission site among the various factors, so it is important to plan and generate the route.

The route plan is divided into grid units in consideration of maneuver / communication / threat factor when the destination of the mission is set by the operator, and the optimal route is created by calculating the cost per grid by A * algorithm. In general, the presence or absence of maneuver has the greatest influence. The determination of maneuverability uses the digital terrain information (FDB), which is the standard terrain information currently used in the Army. Digital terrain information consists of feature and attribute composed of points, lines and faces, and is used in paper mapping and various military weapons systems. Among the objects, the road object has attribute information such as road position, road width, crossing point, and packaging material, and has a high priority to a place where maneuver is possible. The Army Territorial Information Unit, which manages digital terrain information, updates the map periodically, but updates are slow because it targets all regions.

1 is a view showing digital terrain information, an aerial image, and a superimposed image of the same area in the present invention. The brown solid line of the digital terrain information means the road (see Fig. 1 (a)). In the images where the digital terrain information and the aerial image are superimposed, the central roads are relatively matched, the right roads are inconsistent, and the left roads are not identified (see Fig. 1 (c)). Generally, connected roads are packed in a dark gray-based color, which is the most basic and important element for identifying roads, but there is a problem in that digital color information of roads is missing in the digital terrain information, .

In addition, if there is a slight discrepancy between the digital terrain information and the images superimposed on the aerial image, it can be solved to some extent through the local route planning in the robot. However, since the unidentified road is not reflected, .

Patent Registration No. 10-1234371 (Feb.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a method and apparatus for improving inaccurate road information of digital terrain information on which path planning is based.

A method for improving road information of digital terrain information based on histogram similarity according to an embodiment of the present invention includes: inputting digital terrain information (FDB) and aerial image (S100); Generating a road histogram from the digital terrain information (S200); Generating a block histogram from the aerial image (S300); And estimating roads using the road histogram and the block histogram (S400).

The method of improving the road information of the digital terrain information based on the histogram similarity degree may further include outputting a result reflecting the estimation (S500).

The step S200 of generating the road histogram includes a step S210 of selecting a reference road from the digital terrain information; Extracting coordinates of the selected reference road (S220); And generating a road histogram using the road color corresponding to the road color of the aerial image (S230).

The step (S300) of generating the block histogram includes rotating the aerial image so that the reference road is arranged in the vertical direction (S310); Calculating a slope of the reference road using the coordinates of the selected reference road (S320); Rotating the aerial image with the calculated slope (S330); And dividing the rotated aerial image into N blocks and generating a block histogram for each of the divided blocks (S340).

The step S400 of estimating the road condition may include calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram S410; Determining whether the calculated Euclidean distance is equal to or greater than a preset reference value (S420); (S430) when the calculated Euclidean distance is equal to or greater than a preset reference value (Threshold); And estimating that the calculated Euclidean distance is not a road when the calculated Euclidean distance is less than a predetermined threshold value (S440).

The apparatus for improving the histogram similarity-based digital terrain information according to another embodiment of the present invention includes an input unit 100 including a digital terrain information input unit 110 and an aerial image input unit 120; A histogram generation unit 200 including a road histogram generation unit 210 and a block histogram generation unit 220; An estimator 300 for calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram, determining whether the calculated Euclidean distance is equal to or greater than a preset reference value, and estimating whether the road is a road or not; And an output unit 400 for outputting a result reflecting the road-state estimation.

As described above, according to the present invention, it is possible to shorten the mission time and save fuel by creating a route based on the improved road information in the mission planning stage of the unmanned robot.

In addition, it can supplement military landmark information of unidentified or inaccurate army to help military operations and various military weapons systems. It can also be applied to all areas where digital terrain information is used to supplement inaccurate terrain information. .

1 is a view illustrating digital terrain information, an aerial image, and a superimposed image of the same area in the present invention.
2 is a schematic flowchart of a method for improving road information of digital terrain information based on histogram similarity according to an embodiment of the present invention.
3 is a flowchart of a method for improving road information of digital terrain information based on histogram similarity according to an exemplary embodiment of the present invention.
4 is a block diagram of an apparatus for improving road information of digital terrain information based on histogram similarity according to another embodiment of the present invention.
FIG. 5 is a view illustrating a result of estimating roads according to the present invention. FIG.

It is to be understood that the words or words used in the present specification and claims are not to be construed in a conventional or dictionary sense and that the inventor can properly define the concept of a term to describe its invention in the best way And should be construed in accordance with the meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention and are not intended to represent all of the technical ideas of the present invention. Therefore, various equivalents It should be understood that water and variations may be present. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 2 is a schematic flowchart of a method of improving road information of digital terrain information based on histogram similarity according to an exemplary embodiment of the present invention. FIG. 3 is a flowchart illustrating a method of improving road information of digital terrain information based on histogram similarity according to an exemplary embodiment of the present invention FIG. Referring to FIGS. 2 and 3, a method of improving histogram similarity-based digital terrain information according to an exemplary embodiment of the present invention includes inputting digital feature information (FDB) and an aerial image (S100); Generating a road histogram from the digital terrain information (S200); Generating a block histogram from the aerial image (S300); Estimating roads using the road histogram and the block histogram (S400); And outputting a result reflecting the estimation (S500).

The step S200 of generating the road histogram includes a step S210 of selecting a reference road from the digital terrain information; Extracting coordinates of the selected reference road (S220); And generating a road histogram using the road color corresponding to the road color of the aerial image (S230).

과 중간점 또는 끝점

의 선형 보간법을 이용한다. 하기의 수학식 1에 의해 선형 보간법을 이용하여 기준 도로의 좌표들을 추출할 수 있다. That is, the position of the road in the digital terrain information is represented by a start point, a middle point, and an end point. Also, connecting them together leads to a road. In step S220 of extracting the coordinates of the reference road,

And midpoints or endpoints

Linear interpolation. The coordinates of the reference road can be extracted by linear interpolation according to the following equation (1).

을 이용하여 하기의 수학식 2에 의해 기준도로의 도로 히스토그램을 생성한다.
The coordinates of the reference road extracted as described above are the road color corresponding to the road color of the aerial image of the same area

The road histogram of the reference road is generated by the following equation (2).

는 특정 색상의 히스토그램이고,

는 색상 범위로서 0에서 255 사이의 값이고,

는

색상과 일치할 경우 0이 된다.
here

Is a histogram of a specific color,

Is a color range from 0 to 255,

The

If it matches the color, it becomes 0.

The step (S300) of generating the block histogram includes rotating the aerial image so that the reference road is arranged in the vertical direction (S310); Calculating a slope of the reference road using the coordinates of the selected reference road (S320); Rotating the aerial image with the calculated slope (S330); And a step (S340) of dividing the rotated aerial image into N blocks and generating a block histogram for each of the divided blocks.

In step S310 of rotating the aerial image, the aerial image is rotated such that the reference road is arranged in the vertical direction in order to increase the accuracy of the estimation.

In step S320 of calculating the slope of the reference road, the slope of the road is calculated from the starting point and the end point of the reference road by the following equation (3).

는 기준도로의 기울기이다.
here

Is the slope of the reference road.

The step S330 of rotating the aerial image with the calculated slope rotates the aerial image at a slope calculated by the following equation (4).

)을

크기의 블록

,

개로 분할한다. 이후, 하기의 수학식 5에 의해 각 블록에 대한 히스토그램을 생성한다.The step of dividing the rotated aerial image into N and generating a block histogram for each of the divided blocks (S340) includes a step of obtaining a rotated aerial image

)of

Block of size

,

. Then, a histogram for each block is generated by the following equation (5).

The step S400 of estimating the road condition may include calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram S410; Determining whether the calculated Euclidean distance is equal to or greater than a preset reference value (S420); (S430) when the calculated Euclidean distance is equal to or greater than a preset reference value (Threshold); And estimating that the road is not a road when the calculated Euclidean distance is less than a predetermined threshold value (S440).

The step of calculating the Euclidean distance (S410) calculates the Euclidean distance representing the degree of similarity between the road histogram and the block histogram according to the following equation (6).

If the calculated Euclidean distance is equal to or greater than a preset reference value (Threshold) (S430), it is determined whether the calculated Euclidean distance is equal to or greater than a preset reference value (S420) If it is less than the threshold (Threshold), it is estimated that the road is not a road (S440).

FIG. 4 is a block diagram of an apparatus for improving road information of digital terrain information based on histogram similarity according to another embodiment of the present invention. Referring to FIG. 4, the apparatus for improving histogram similarity-based digital terrain information according to another embodiment of the present invention includes an input unit 100 including a digital terrain information input unit 110 and an aerial image input unit 120; A histogram generation unit 200 including a road histogram generation unit 210 and a block histogram generation unit 220; An estimator 300 for calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram, determining whether the calculated Euclidean distance is equal to or greater than a preset reference value, and estimating whether the road is a road or not; And an output unit 400 for outputting a result reflecting the road-state estimation.

FIG. 5 is a screen for outputting a result of roadway estimation according to the present invention. In Fig. 5, a blue dotted line is a reference road, and a white block is an area estimated as a road. In FIG. 5, it can be seen that the left roads and the right roads that were not identified in FIG. 1 are estimated. It is possible to estimate the width of the reference road by considering the grid size and the resolution of the map.

It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory only and are not restrictive of the invention, as claimed, and will be fully understood by those of ordinary skill in the art. The present invention is not limited thereto. It will be apparent to those skilled in the art that various substitutions, modifications and variations are possible within the scope of the present invention, and it is obvious that those parts easily changeable by those skilled in the art are included in the scope of the present invention .

100 input unit
110 Digital terrain information input
120 aerial image input unit
200 histogram generator
210 road histogram generator
220 block histogram generator
300 estimator
400 output section

Claims (6)

A step (S100) of inputting digital terrain information (FDB, Feature DataBase) and an aerial image;
Generating a road histogram from the digital terrain information (S200);
Generating a block histogram from the aerial image (S300); And
Estimating roads using the road histogram and the block histogram (S400);
Wherein the histogram similarity-based digital terrain information includes at least one of the following: The method according to claim 1,
Outputting a result reflecting the estimation (S500);
Based on the histogram similarity-based digital terrain information. The method according to claim 1,
The step S200 of generating the road histogram includes a step S210 of selecting a reference road from the digital terrain information;
Extracting coordinates of the selected reference road (S220); And
Generating a road histogram using the road color corresponding to the road color of the aerial image (S230);
Based on the histogram similarity-based digital terrain information. The method of claim 3,
The step (S300) of generating the block histogram includes rotating the aerial image so that the reference road is arranged in the vertical direction (S310);
Calculating a slope of the reference road using the coordinates of the selected reference road (S320);
Rotating the aerial image with the calculated slope (S330); And
Dividing the rotated aerial image into N blocks and generating a block histogram for each of the divided blocks (S340);
Based on the histogram similarity-based digital terrain information. 5. The method of claim 4,
The step S400 of estimating the road condition may include calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram S410;
Determining whether the calculated Euclidean distance is equal to or greater than a preset reference value (S420);
(S430) when the calculated Euclidean distance is equal to or greater than a preset reference value (Threshold); And
Estimating that the calculated Euclidean distance is not a road when the Euclidean distance is less than a predetermined threshold value (S440);
Based on the histogram similarity-based digital terrain information. An input unit 100 including a digital terrain information input unit 110 and an aerial image input unit 120;
A histogram generation unit 200 including a road histogram generation unit 210 and a block histogram generation unit 220;
An estimator 300 for calculating a Euclidean distance representing a degree of similarity between the road histogram and the block histogram, determining whether the calculated Euclidean distance is equal to or greater than a preset reference value, and estimating whether the road is a road or not; And
An output unit 400 for outputting a result reflecting the roadway condition estimation;
Based on the histogram similarity-based digital terrain information.

Images