KR102636413B1 - System and method for measuring tracking accuracy for tracking devices - Google Patents

Abstract

A tracking accuracy measurement system for a tracking device according to the present invention includes a mounting platform movement simulation unit that is equipped with a target test tracking device for measuring tracking accuracy to simulate movement, and a mounting platform movement simulation unit that is mounted on the mounting platform movement simulation unit to simulate a posture. A tracking situation photographing unit equipped with a platform posture simulation unit, an image capture device, and a weight to capture images of the tracking situation, a tracking target marker unit that is a tracking target that the tracking situation filming unit aims and captures, and an image of the tracking situation. It includes an image analysis unit that analyzes and derives tracking accuracy.

Description

Tracking accuracy measurement system and method for tracking devices {SYSTEM AND METHOD FOR MEASURING TRACKING ACCURACY FOR TRACKING DEVICES}

The present invention relates to a tracking accuracy measurement system and method for a tracking device, and in particular, to a tracking accuracy measurement system and method for a tracking device that allows tracking accuracy to be more easily measured through image analysis techniques.

Figure 1 is a diagram for explaining a GPS-based two-axis driving tracking device according to the prior art.

As shown in Figure 1, a traditional GPS-based tracking device includes a two-axis driving body, an antenna (radiator) installed in line with the rotation axis of the driving body, an elevation angle driving plate and an azimuth driving plate for controlling the driving body, and internal and external control and tracking. It is composed of a drive control unit to manage it, a power board to supply power, and DGPS and GYRO to use sensor information for GPS tracking.

At this time, tracking accuracy by two-axis driving is generally determined according to the results of various complex factors such as driving accuracy, driving speed, update cycle and accuracy of position information. The tracking accuracy of such equipment is frequently and rarely presented by simply accepting the figures presented by the manufacturer or simply checking the degree to which the distance from the target deviates from the target when performing tracking, thereby providing statistically accurate information. There is a need for a test method that can do this.

Therefore, the purpose of the present invention is to provide a tracking accuracy measurement system and method for a tracking device that can more easily measure tracking accuracy through image analysis techniques.

However, the problem to be solved by the present invention is not limited to the problems described above, and other problems may exist.

A tracking accuracy measurement system for a tracking device according to the first aspect of the present invention to solve the above-described problem includes a movement simulation unit of a mounting platform that simulates movement of a target test tracker for measuring tracking accuracy, and a movement simulation unit of the mounting platform. A tracking situation photographing unit equipped with a posture simulation unit, an image capture device, and a weight to capture images of the tracking situation, a tracking target that the tracking situation filming unit aims and captures. It includes a tracking target marker and an image analysis unit that analyzes the image of the tracking situation to derive tracking accuracy.

In some embodiments of the present invention, the mounting platform posture simulation unit is linked with a motion simulator with a degree of freedom of 6-DOF or more, an RF modem for remote control, a posture sensor for simulating posture, and a GPS antenna and receiver. It may include a motion controller that controls the motion simulator to simulate the posture of the mounting platform.

In some embodiments of the present invention, the tracking target marker has a circular shape and may be selected as the minimum color among colors existing in the surrounding area.

In some embodiments of the present invention, the tracking target mark unit includes a target mark standard installed at an identifiable distance in the image, and the image analysis unit determines the distance between the target mark standard and the target mark, and the tracking device and Based on the distance between target marks, angle information between the target mark and the target mark standard for measuring the tracking accuracy can be converted.

In some embodiments of the present invention, the image analysis unit may store images by GPS tracking when performing a test according to movement and posture changes in the mounting platform movement simulation unit and the mounting platform posture simulation unit according to a predetermined test scenario. You can.

In some embodiments of the present invention, the image analysis unit may set distance and angle conversion standards within the image for analysis of the stored image based on the converted angle information.

In some embodiments of the present invention, the image analysis unit sets the converted angle information to a first reference circle that is a reference circle base, and sets the second reference circle to have a size that is a predetermined multiple of the first reference circle. , a third reference circle having the angle of the tracking zone set when performing the test can be set.

In some embodiments of the present invention, the image analysis unit converts the captured image into a binary image, extracts an area corresponding to a predetermined extraction standard, and then determines the distance and angle within the extracted area within the set image. The error angle with the tracking target can be calculated based on the distance from the conversion standard.

In some embodiments of the present invention, the image analysis unit converts the captured RGB image into an HSV (Hue Saturations Value) image to adjust the saturation value and brightness value, and the RGB image for the pixel corresponding to the target mark. By calculating the color difference from the standard, pixels that fall within the reference point can be recognized as target marks.

In some embodiments of the present invention, the image analysis unit converts the HSV image whose saturation and brightness values have been adjusted back into an RGB image, and selects and extracts a masking area to be recognized as a target mark from the RGB image. The color difference from the RGB standard for the masking area can be calculated.

In some embodiments of the present invention, the image analysis unit calculates the average value of the R, G, and B colors for the masking area, and generates an image of the same size as the entire screen using the average value. The difference from the average value for each can be calculated, and a reference value for target recognition when analyzing images can be set based on the average and standard deviation of the difference.

In some embodiments of the present invention, the image analysis unit selects a target candidate for each image frame using the average value and the difference value, selects an area that satisfies a predetermined condition among the target candidates, and then selects a target candidate for orientation confirmation. The target candidate can be reselected by calculating the distance between the center of and the center of the selected area.

In some embodiments of the present invention, the image analysis unit extracts pixels for the target candidates based on a result of comparing the set reference value and the difference value, and converts the extracted pixels for the target candidates into a binary image. Convert, calculate boundary pixels for all objects in the converted image, and determine the circularity of the object based on the boundary pixels.

In some embodiments of the present invention, the image analysis unit may select objects connected between pixels in the converted binary image, calculate the area of the selected object, and then remove objects smaller than a certain area.

In some embodiments of the present invention, the image analysis unit compares the circularity judgment standard input by the user with the circularity of the object calculated based on the boundary pixel and selects the object exceeding the judgment standard as a candidate for the target. You can select.

In addition, the method performed by the tracking accuracy measurement system for a tracking device according to the second aspect of the present invention includes a movement simulation unit of a mounting platform for simulating movement of a target test tracker for measuring tracking accuracy, and movement of the mounting platform. Performing a test based on movement and posture changes through a mounting platform posture simulation unit mounted on the simulation unit to simulate the posture; Taking and storing an image of the tracking target marker by GPS tracking when performing the test; and deriving tracking accuracy by analyzing images of the tracking situation.

A computer program according to another aspect of the present invention for solving the above-described problem is combined with a computer as hardware, executes a tracking accuracy measurement method for the tracking device, and is stored in a computer-readable recording medium.

Other specific details of the invention are included in the detailed description and drawings.

Unlike existing tracking devices that calculate tracking accuracy based on information such as driving unit performance and sensor accuracy or perform tracking only in a stationary state, an embodiment of the present invention performs tracking in an actual operating environment and analyzes images. Through this, accuracy can be analyzed, measuring accuracy in an accurate operating environment and providing higher reliability.

In addition, an embodiment of the present invention utilizes core functions and has no limitations on driving devices such as 1-axis, 2-axis, and 3-axis, and the movement and movement of the mounting platform can be simulated in a real environment, allowing for various environments and It can be easily used to measure and compare tracking accuracy across devices.

In addition, an embodiment of the present invention can more realistically verify and improve the performance of the tracking device by simulating and analyzing tracking in a real environment, which will contribute to improving the actual performance of the tracking device in various application fields. You can.

In addition, an embodiment of the present invention is capable of measuring precise tracking accuracy and deriving results through image analysis, thereby improving the accuracy of the system and identifying and solving problems.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

The drawings attached below are intended to aid understanding of the present embodiment and provide examples along with a detailed description. However, the technical features of this embodiment are not limited to specific drawings, and the features disclosed in each drawing may be combined to form a new embodiment.
Figure 1 is a diagram for explaining a GPS-based two-axis driving tracking device according to the prior art.
Figure 2 is a configuration diagram of a tracking accuracy measurement system 100 according to an embodiment of the present invention.
Figure 3 is a diagram for explaining the mounting platform posture simulation unit 120 in one embodiment of the present invention.
Figure 4 is a diagram for explaining the tracking target marker 140 in one embodiment of the present invention.
Figure 5 is a diagram showing an example of setting a reference source in one embodiment of the present invention.
Figure 6 is a diagram for explaining video analysis content according to the first track mode in one embodiment of the present invention.
Figure 7 is a diagram showing an example of a process for generating a masking frame in an embodiment of the present invention.
Figure 8 is a diagram for explaining video analysis content according to the second track mode in one embodiment of the present invention.
Figure 9 is a diagram showing the results of binary image conversion processing in one embodiment of the present invention.
Figure 10 is a diagram showing the result of extracting only images that satisfy circularity in one embodiment of the present invention.
Figure 11 is a diagram showing an example of the final analysis result using the stored image.
Figure 12 is a flowchart of a method for measuring tracking accuracy according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, the background technology described above in FIG. 1 will be described in more detail, and then the present invention will be described in detail.

General GPS-based tracking devices are applied to a wide variety of fields and systems. The most core performance factors of these tracking devices include driving speed and tracking accuracy. There is little disagreement about calculating relatively accurate values for driving speed based on the time to reach the maximum driving speed and the driving time versus RPM after reaching the maximum driving speed. However, in the case of tracking accuracy, there are often various changes such as posture changes and movements of the system itself equipped with a tracking device, so it is difficult to accurately quantify the tracking accuracy at the moment of posture change or movement.

Figure 1 is an example of a two-axis drive tracking device in which an antenna (radiator) mounted on the center of the drive shaft is directed to a target point by two-axis drive. In this case, it can be converted into tracking accuracy by connecting an RF module or signal generator that radiates RF signals, installing a receiving device in the tracking direction, and measuring the received signal level. However, in this case, the radiation pattern of the antenna (radiator) mounted on the two-axis tracking device and the antenna radiation pattern of the receiver mounted for testing must be accurately known. The bigger problem is that in the case of a 2-axis tracking device, it must be measured in a situation that simulates the actual situation of posture change and movement, so it cannot be tested indoors, and multipath fading that occurs in an environment where RF is transmitted Signal distortion caused by should also be considered. Additionally, in order to accurately measure the received signal level, the sweep speed of the signal analyzer must be set very slowly, and measurement accuracy must be increased through averaging when necessary. As such, the measurement time is not sufficient because the two-axis tracking device measuring through RF signals must be measured in situations where the posture is changing or moving. Therefore, there is a need for another invention on how to accurately measure tracking accuracy for various reasons.

One embodiment of the present invention is a method for overcoming these measurement difficulties and analyzing accurate tracking accuracy through offline precise analysis after testing. A system that can measure tracking accuracy through an imaging device and an image analysis method in a relatively easy manner. suggests. The accuracy measurement method of a GPS-based two-axis driving tracking device according to an embodiment of the present invention is a test method that is not limited to the number of two-axis rotation axes and is almost unaffected by the environment, and can be used in various fields.

Hereinafter, a tracking accuracy measurement system 100 for a tracking device according to an embodiment of the present invention will be described with reference to FIGS. 2 to 11.

Figure 2 is a configuration diagram of a tracking accuracy measurement system 100 according to an embodiment of the present invention.

The tracking accuracy measurement system 100 according to an embodiment of the present invention installs a target mark that is easy to recognize by image at the location of the target to be tracked, mounts a motion simulator on a moving vehicle (or other moving object), and installs it on the top of the simulator. This is a method of testing by installing the test object in the test. At this time, a counter mass is installed to align the imaging device and the center of the rotating part in place of the original component (for example, a radiator) mounted at the center of the driving part. In other words, it configures test equipment and software that simulates the movement of a system equipped with an actual tracking device, captures and stores images at the location tracked by the tracking device, and allows easy and accurate analysis offline.

One embodiment of the present invention includes a mounting platform movement simulation unit 110, a mounting platform posture simulation unit 120, a tracking situation photographing unit 130, a tracking target marking unit 140, and an image analysis unit 150. do. Meanwhile, one embodiment of the present invention can be applied regardless of the number of axes, such as 2 axes or 3 axes, and to explain the operation of the present invention, 2 axes will be used as an example.

In one embodiment, the mounting platform movement simulation unit 110 is equipped with a target test tracking device for measuring tracking accuracy to simulate movement. The mounting platform movement simulation unit 110 can be equipped with a motion simulator and motion controller that simulates the posture of the mounting platform, a test object, a camera, etc. The mounting platform moving simulation unit 110 may be composed of a car or other moving body suitable for system testing, depending on the test object. At this time, the movement simulation can be selected to suit each operating environment because the required movement speed is determined depending on the operating environment in which the system is used and the test distance between the tracking equipment and the target.

In one embodiment, the mounting platform posture simulation unit 120 is mounted on the mounting platform movement simulation unit 110 to simulate the posture. At this time, the mounting platform posture simulation unit 120 may include a motion simulator, an RF modem, a posture sensor, a GPS antenna and receiver, and a motion controller.

Figure 3 is a diagram for explaining the mounting platform posture simulation unit 120 in one embodiment of the present invention.

The mounting platform posture simulation unit 120 is composed of a motion simulator with a degree of freedom of 6-DOF or more depending on the operating environment of the system (e.g., Roll/Pitch/Yaw change environment) and a motion controller that controls it. If a change in height is necessary, the test configuration can be configured by adding heave adjustment. Figure 3 shows the linkage structure of the mounting platform posture simulation unit 120. The RF modem is for cases where remote control is possible, and the control PC controls the motion simulator through linkage with the posture sensor (Gyro) and GPS receiver. This is a structure that simulates the posture of the mounting platform.

In one embodiment, the tracking situation capturing unit 130 is equipped with an image capturing device and a weight to capture images of the tracking situation.

The tracking situation photographing unit 130 is installed to replace the antenna mounted on the GPS-based two-axis driving tracking device. At this time, a mounting fixture and weight may be provided to have the same center of gravity as the antenna. It is sufficient for a video capture device to have a shooting speed of 30 FPS or more, which is the standard video capture device. If necessary, a video recording device with a shooting speed of 60FPS or higher can be used, and the captured video can be saved in memory or selected as equipment with an interface that allows real-time external transmission.

In one embodiment, the tracking target marker 140 is a tracking target that the tracking situation photographing unit 130 aims and photographs.

The tracking target marker 140 is a marker that becomes a tracking target that the tracking situation photographing portion 130, which is installed in place of a GPS-based two-axis driving device, aims and photographs during tracking. The target mark 141 may be selected as a color that is as close to the surroundings as possible depending on the surrounding color situation. To this end, in one embodiment of the present invention, the target mark 141 is selected as the minimum color among the surrounding images captured by the image capture device, and the target mark 141 is variably operated depending on the color of the surrounding situation. It may be configured as a display device. It is sufficient to select the size of the target mark 141 to be a few to several tens of pixels in the captured image depending on the image pixel and the distance between the tracking device and the tracking target mark 140. In addition, in order to distinguish it from surrounding similarly colored structures, the shape of the target mark 141 is circular to enable classification with surrounding images during analysis. In addition, in order to calculate accuracy regardless of the pixel, the tracking error in the image can be converted to distance and angle by using the target marker standard 142 at a predetermined distance (Td) apart from the tracking target marker 140. Let's do it. This tracking target marker 140 will be described again with reference to FIG. 4 described later.

In one embodiment, the image analysis unit 150 analyzes images of the tracking situation and derives tracking accuracy.

The video analysis unit 150 is composed of a video analysis PC and video analysis software to perform frame-by-frame analysis of the video offline using the video in which the tracking situation is captured. The image analysis PC is prepared as a PC capable of running image analysis software, and the image analysis software, which is the center of the present invention, is run to analyze the stored images to derive tracking accuracy.

At this time, the main functions required by the image analysis software for effective image analysis in one embodiment of the present invention are as follows.

- Measurement bias application function

- Circular setting and city for tracking confirmation by tracking range setting

- Color/Black&White playback

- Simultaneous display of circular tracking range for tracking confirmation along with video playback

- Tracking error measurement/city/storage by measuring the distance between the target and the circular center point of the tracking range

- Save and play back the analysis result screen as a video

- Statistical result analysis and illustration of tracking error as a result of analysis

The video analysis software performs the function of playing back the saved video along with a circle indicating the tracking range so that it can be easily checked whether the target is in the video using the error angle and information between pixels measured in advance. In addition, it performs a function of performing image processing to quantify tracking accuracy.

Hereinafter, the process of measuring tracking accuracy in the tracking accuracy measurement system 100 will be described in more detail with reference to FIGS. 4 to 11.

First, the tracking device and tracking accuracy measurement system 100 shown in FIG. 2 are installed at the test site, and then the target mark 141 and the reference bar 142 are installed at a distance that can be identified in the image, and then the target mark When the distance (Td) between the reference bar 142 and the target mark 141 is measured and the distance (D) between the tracking device and the target mark 141 is measured, the image analysis unit 150 tracks based on each distance. The angle (Ta) information between the target mark 141 and the target mark standard 142 for measuring accuracy can be converted.

Figure 4 is a diagram for explaining the tracking target marker 140 in one embodiment of the present invention.

As shown in Figure 4, when the distance between the tracking device and the tracking target is D, the pixel used for tracking accuracy measurement and the conversion of the separation distance between the target mark 141 and the reference bar 142 to be used for distance conversion are based on the following equation 1. It is calculated. At this time, D can be calculated by measuring the positions of two points using GPS.

[Equation 1]

Next, the image analysis unit 150 produces images by GPS tracking when performing a test according to movement and posture changes in the mounting platform movement simulation unit 110 and the mounting platform posture simulation unit 120 according to a predetermined test scenario. Save it.

Next, the image analysis unit 150 may use the converted angle information Ta to set distance and angle conversion standards within the image for analysis of the stored image. Figure 5 is a diagram showing an example of setting a reference source in one embodiment of the present invention.

Referring to FIG. 5, the image analysis unit 150 can set the converted angle information Ta as the first reference circle, which is the reference circle base, and this information and the positions of the target mark 141 and the target mark standard 142. By setting, it becomes possible to convert the distance and angle within the image and measure tracking accuracy excluding bias that occurs when installing the device. Additionally, the image analysis unit 150 may set the second reference circle to have a size that is a predetermined multiple of the first reference circle, and set the third reference circle to have the angle of the tracking zone set when performing the test.

- Circle 1 Radius(Green) = Standard Bar Distance (or Circle Basis)

- Circle 2 Radius(Cyan) = Circle 2 x 2

- Circle 3 Radius(Red) = Tracking Zone angle set during testing

Thereafter, the image analysis unit 150 may perform image analysis based on the two track modes.

Figure 6 is a diagram for explaining video analysis content according to the first track mode in one embodiment of the present invention.

First, in the case of the first track mode, the image analysis unit 150 converts the captured image into a binary image, extracts an area corresponding to a predetermined extraction standard, and then converts the distance and angle within the image set within the extracted area. The error angle with the tracking target can be calculated based on the distance from the reference.

In other words, the first track mode converts a simple black and white image into a binary image using the reference value entered by the user, and then checks the extraction standard (area & roundness) entered by the user to determine the target. This is a method of calculating the error angle by extracting the part to be recognized and measuring the distance from the original tracking range. The first track mode method can be used when the object selected (installed) as a target has a clear boundary from the surrounding background and has the advantage of fast analysis speed.

However, if the object selected (installed) as a target is not clearly distinguished from the surrounding background, only the selected object may not be extracted or multiple objects may be extracted. Figure 6 is an example of the first track mode, which has a function that can be set to remove black areas of 200 pixels or less and search only for objects with a roundness of 0.65 or more for each object.

Next, the second track mode is a method that allows you to select (install) and analyze an object that is not in the surrounding background and can be clearly distinguished when the object selected (installed) as a target does not have a clear boundary from the surrounding background. .

For precise analysis, the image analysis unit 150 converts the captured RGB image into an HSV (Hue Saturation Value) image and adjusts the saturation and brightness values to further distinguish it from the target. , the color difference Delta E from the RGB standard for the pixel corresponding to the target mark 141 is calculated, and the pixel that falls within the reference point can be recognized as the target mark 141.

This second track mode method is slow due to the large amount of calculations, but can extract the pixel selected as the target more accurately than the first track mode. In order to find the location of a target in the second track mode, it is necessary to find the area that you want to recognize as the target. For this purpose, after selecting the reference frame (S11), adjust the saturation and brightness values in advance so that the part selected as the target can be distinguished from the surrounding area (S12), and use the analysis standard extraction function to recognize the area you want to recognize as the target. Select (S13). After selection, statistical characteristics of the selected area are extracted and a masking frame is created (S14).

Figure 7 is a diagram showing an example of a process for generating a masking frame in an embodiment of the present invention.

Afterwards, the image analysis unit 150 converts the HSV image with the saturation and brightness values adjusted back into an RGB image. Additionally, the image analysis unit 150 may select and extract a masking area to be recognized as a target mark 141 from the RGB image and calculate the color difference between the masking area and the RGB standard.

At this time, the image analysis unit 150 can calculate the average value for each area of R, G, and B colors for the masking area, and generate an image of the same size as the entire screen using the average value (S15). And by calculating Delta E, which is the difference value from the average value for each of the R, G, and B colors (S16, S17), the average and standard deviation of Delta E in the masking area can be set as a reference value for target recognition in actual analysis. There is (S18, S19). At this time, the basic standard value can be calculated based on the following equation 2.

[Equation 2]

meanMaskedDeltaE = sqrt(deltaR^2 + deltaG^2 + delta B^2);

Delta E Threshold = meanMaskedDeltaE + 3 * stDevMaskedDeltaE

Considering the deviation of a specific color in the image and the error in the user's selection area, the user determines the standard value presented in Equation 2 above and makes the final input (S20, S21). Next, Figure 8 shows the above-described process as a flowchart.

Afterwards, the analysis process (S22) selects a candidate target for each image frame using the RGB standard and Delta E extracted from the analysis standard, selects an area that satisfies a predetermined condition among the target candidates, and selects a target candidate for orientation confirmation. The target candidate can be reselected by calculating the distance between the center and the centroid of the selected area.

To analyze the error, the Youngsan analysis department repeatedly extracts the target for each frame and calculates and shows the distance to the source for orientation confirmation. The procedures and principles are as follows. First, Delta E is calculated according to the following equation 3 using the previously calculated RGB standard.

[Equation 3]

Delta E = sqrt((dataR - RStandard)2+(dataG - GStandard)2+(dataB - BStandard)2)

And the image analysis unit 150 extracts pixels for target candidates based on the result of comparing the difference value with the reference value (tolerance) set upon confirmation by the user, and converts the pixels for the extracted target candidates into a binary image. Convert to

[Equation 4]

BW = (Delta E <= tolerance)

At this time, the image analysis unit 150 may select objects connected between pixels in the converted binary image, calculate the area of the selected object, and then remove objects smaller than a certain area. Figure 9 is a diagram showing the results of binary image conversion processing in one embodiment of the present invention.

Thereafter, the image analysis unit 150 may calculate boundary pixels for all objects in the converted image and determine the circularity of the object based on the boundary pixels. At this time, unlike this example (target shape is square), the actual antenna tracking signal simulator installs a random circular target when collecting images, so the circularity determination process in this case will be explained. To this end, the process of calculating the boundary length (perimeter) and determining the roundness metric can be done using Equation 5 below.

[Equation 5]

Boundary length operation: delta_sq = diff(boundary).^2

perimeter = sum(sqrt(sum(delta_sq,2)))

Circularity calculation: metric = 4*pi*area/perimeter^2

The circularity measured by Equation 5 is compared with the circularity judgment criteria entered by the user, and only objects that exceed the standard value are re-selected as target candidates.

The image analysis unit 150 may calculate and display the distance between the centroid of the final selected object and the center of the circle for orientation confirmation in units of pixels and angles. Figure 10 is a diagram showing the result of extracting only images that satisfy circularity in one embodiment of the present invention. Figure 11 is a diagram showing an example of the final analysis result using the stored image.

Hereinafter, a method performed by the tracking accuracy measurement system 100 for a tracking device according to an embodiment of the present invention will be described with reference to FIG. 12.

Figure 12 is a flowchart of a method for measuring tracking accuracy according to an embodiment of the present invention.

First, the mounting platform movement simulation unit 110, which is equipped with a target test tracking device for measuring tracking accuracy to simulate movement, and the mounting platform posture simulation unit 120, which is mounted on the mounting platform movement simulation unit 110 and simulates the posture. ) to perform tests based on movement and posture changes (S110).

Next, an image of the tracking target marker 140 by GPS tracking during test performance is captured and stored (S120).

Next, the tracking accuracy is derived by analyzing the video of the tracking situation (S130).

Meanwhile, in the above description, steps S11 to S130 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Additionally, some steps may be omitted or the order between steps may be changed as needed. In addition, even if other omitted content, the content described in FIGS. 2 to 11 and the content described in FIG. 12 can be mutually applied.

The tracking accuracy measurement method according to an embodiment of the present invention described above may be implemented as a program (or application) and stored in a medium in order to be executed in combination with a computer, which is hardware.

The above-mentioned program is C, C++, JAVA, Ruby, and It may include code encoded in a computer language such as machine language. These codes may include functional codes related to functions that define the necessary functions for executing the methods, and include control codes related to execution procedures necessary for the computer's processor to execute the functions according to predetermined procedures. can do. In addition, these codes may further include memory reference-related codes that indicate at which location (address address) in the computer's internal or external memory additional information or media required for the computer's processor to execute the above functions should be referenced. there is. In addition, if the computer's processor needs to communicate with any other remote computer or server in order to execute the above functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes regarding whether communication should be performed and what information or media should be transmitted and received during communication.

The storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers that the computer can access or on various recording media on the user's computer. Additionally, the medium may be distributed to computer systems connected to a network, and computer-readable code may be stored in a distributed manner.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

10: Tracking device
100: Tracking accuracy measurement system
110: Mounting platform moving simulation unit
120: Mounting platform posture simulation unit
130: Tracking situation recording unit
140: Tracking target marking unit
150: Video analysis unit

Claims (16)

A moving simulation unit of a mounted platform equipped with a target test tracker to measure tracking accuracy and simulating movement;
A mounting platform posture simulation unit mounted on the mounting platform movement simulation unit to simulate a posture,
A tracking situation recording unit equipped with a video recording device and a weight to capture images of the tracking situation,
A tracking target marking unit, which is a tracking target that the tracking situation photographing unit aims and photographs, and
It includes an image analysis unit that analyzes the image of the tracking situation and derives tracking accuracy,
The tracking target marker unit includes a target marker standard installed at an identifiable distance in the image,
The image analysis unit is based on the distance (Td) between the target mark and the target mark and the distance (D) between the tracking device and the target mark, between the target mark and the target mark for measurement of the tracking accuracy. A tracking accuracy measurement system for a tracking device that converts angle (Ta) information.
According to paragraph 1,
The mounting platform posture simulation unit,
Motion simulator with more than 6-DOF degrees of freedom,
Tracking accuracy for a tracking device comprising an RF modem for remote control, a posture sensor for simulating the posture, and a motion controller that controls the motion simulator through linkage with a GPS antenna and receiver to simulate the posture of the mounting platform. Measurement system.
According to paragraph 1,
A tracking accuracy measurement system for a tracking device wherein the tracking target marker has a circular shape and is selected as the minimum color among colors existing in the surrounding area.
delete According to paragraph 1,
The image analysis unit stores images by GPS tracking when performing a test according to movement and posture changes in the mounting platform movement simulation unit and the mounting platform posture simulation unit according to a predetermined test scenario. Tracking accuracy for a tracking device. Measurement system.
According to clause 5,
The image analysis unit sets distance and angle conversion standards within the image for analysis of the stored image based on the converted angle information.
According to clause 6,
The image analysis unit sets the converted angle information to a first reference circle that is the base of the reference circle, sets the second reference circle to have a size that is a predetermined multiple of the first reference circle, and sets the tracking zone set when performing the test. A tracking accuracy measurement system for a tracking device, wherein a third reference circle is set with an angle of .
According to clause 6,
The image analysis unit converts the captured image into a binary image, extracts an area corresponding to a predetermined extraction standard, and then tracks the image based on the distance within the image and the angle conversion standard set within the extracted area. A tracking accuracy measurement system for a tracking device that calculates the error angle with the target.
According to clause 5,
The image analysis unit converts the captured RGB image into an HSV (Hue Saturations Value) image to adjust the saturation value and brightness value, and calculates the color difference from the RGB standard for the pixel corresponding to the target mark to a reference point. A tracking accuracy measurement system for tracking devices that recognizes incoming pixels as target marks.
According to clause 9,
The image analysis unit converts the HSV image with the saturation and brightness values adjusted back into an RGB image, selects and extracts a masking area to be recognized as a target mark from the RGB image, and compares the RGB standard for the masking area with the RGB standard for the masking area. A tracking accuracy measurement system for tracking devices that calculates color differences.
According to clause 10,
The image analysis unit calculates the average value of the R, G, and B colors for the masking area, generates an image of the same size as the entire screen using the average value, and provides a difference value from the average value for each of the R, G, and B. A tracking accuracy measurement system for a tracking device that calculates (Delta E) and sets a reference value for target recognition when analyzing images based on the average and standard deviation of the difference values.
According to clause 11,
The image analysis unit selects a target candidate for each image frame using the average value and the difference value, selects an area that satisfies a predetermined condition among the target candidates, and then divides the center of the orientation confirmation circle and the center of the selected area. A tracking accuracy measurement system for a tracking device that reselects target candidates by calculating the distance.
According to clause 12,
The image analysis unit extracts pixels for the target candidates based on a result of comparing the set reference value and the difference value, converts the pixels for the extracted target candidates into a binary image, and all objects in the converted image. A tracking accuracy measurement system for a tracking device that calculates boundary pixels for and determines the circularity of the object based on the boundary pixels.
According to clause 13,
The image analysis unit selects objects connected between pixels in the converted binary image, calculates the area of the selected object, and then removes objects smaller than a certain area.
According to clause 13,
The image analysis unit compares the circularity judgment standard input by the user with the circularity of the object calculated based on the boundary pixel, and reselects the object exceeding the judgment standard as a candidate for the target. Tracking accuracy for a tracking device Measurement system.
delete