KR20240044731A - Drone multi-interface video transmission/reception and control method, and system using the same - Google Patents

Abstract

The present invention relates to a method for transmitting, receiving and controlling multi-interface images of a drone, and a system using the same. The drone's multi-interface image transmission/reception and control method includes a first correction step in which the drone moves to a predetermined designated location and captures images according to predetermined standards; A second correction step in which the image collected in the first correction step is received by a server and matched with an image corresponding to the designated location stored in a database; A third correction step in which the drone receives corrected location information and video shooting settings from the server based on the matching result of the second correction step; After the correction step 3, the drone moves to a designated location according to a predetermined standard and captures an image; And the image captured in the image shooting step may include the location information of the drone and include an image and location information transmission step in which the drone is transmitted to a server.

Description

Drone multi-interface video transmission, reception and control method, and system using the same {DRONE MULTI-INTERFACE VIDEO TRANSMISSION/RECEPTION AND CONTROL METHOD, AND SYSTEM USING THE SAME}

The present invention relates to a method for transmitting, receiving and controlling multi-interface images of a drone, and a system using the same. More specifically, a drone's multi-interface image transmission/reception and control method that allows simultaneous transmission and reception of the drone's flight information data and captured multi-interface images and enables rapid 3D modeling data based on the obtained data, and a method using the same It's about the system.

A simulation system refers to a system that expresses physical systems and phenomena using a computer, model, or other equipment. When it is difficult or impossible to experiment with a real state or situation, a corresponding model is created and tested.

In order to understand and predict at a glance natural or human-made structures that occupy a huge space, such as buildings, factories or large facilities, road networks, and terrain, a method of constructing 3D modeling based on image data in a virtual space can be used. .

Recently, simulation systems are implemented in three dimensions using 3D CAD (Computer Aided Design). Here, 3D CAD uses a computer to design a three-dimensional object, expressing the object as information of lines, surfaces, and grains. The 3D CAD simulation system builds a virtual environment, a simulation environment, using various engineering data sets, including 3D CAD data.

In particular, these 3D models are needed to increase consistency and intuition between real and virtual factories. The method in which people directly perform programming, interviews, and data research to obtain a 3D model had the problem of limiting the spread of simulation as it required a lot of manpower, time, and resources.

Looking at the related prior art, the prior art (KR 10-2014-0087533 A) relates to a simulation system, and more specifically, to a manufacturing facility simulation system. It is possible to build a virtual factory capable of implementing continuous processes by modeling actual facilities with each virtual facility and combining each virtual facility, but because it must be programmed and modeled directly, this requires a lot of manpower, time, and resources. there is a problem.

Prior Art 2 (KR 10-1873289 B1) discloses a 3D simulation and monitoring system and method for manufacturing process management of an offshore plant. Mapping with 3D design data, the processor storing the update data and the 3D design data in an integrated database, and the processor creating a 3D simulation model based on the 3D design data and the update data. It includes a step to describe, but because it must be programmed and modeled directly, it also has the problem of requiring a lot of manpower, time, and resources.

Accordingly, the present inventors continued research to build 3D modeling based on image information obtained using a drone, and completed the present invention by integrating a high-quality image information processing and control system.

KR 10-2014-0087533 A KR 10-1873289 B1

The purpose of the present invention is to provide a multi-interface video transmission, reception and control method for a drone that can smoothly transmit and receive high-quality video information obtained from a drone, and can integrate and support drone control information with the video information.

The purpose of the present invention is to provide a method for transmitting, receiving and controlling multiple interface images of a drone to combine multiple interface images obtained from a drone so that 3D modeling can be implemented.

The purpose of the present invention is to enable 3D modeling of natural or artificial objects that change over time to three-dimensionally realize the overall change process and to recognize specific objects in each process.

Another object of the present invention is to provide a system capable of performing the above method.

In order to achieve the above object, a multi-interface image transmission, reception and control method of a drone according to an embodiment of the present invention includes a first correction step in which the drone moves to a predetermined designated location and captures an image according to a predetermined standard; A second correction step in which the image collected in the first correction step is received by a server and matched with an image corresponding to the designated location stored in a database; A third correction step in which the drone receives corrected location information and video shooting settings from the server based on the matching result of the second correction step; After the correction step 3, the drone moves to a designated location according to a predetermined standard and captures an image; And an image and location information transmission step in which the image captured in the image capturing step includes location information of the drone and is transmitted to a server.

In the multi-interface video transmission/reception and control method of the drone, there may be a plurality of designated locations, the drone may include a plurality of cameras, and a separate storage device.

In the second step of correction, the database may include a plurality of images with different video shooting settings for each specific location information, and the plurality of images may be matched with the captured image.

In the drone's multi-interface video transmission/reception and control method, after correction step 3, correction steps 1 to 3 are performed again, and if the location information and video shooting setting values after correction in correction step 3 are the same as the values before correction. It may be performing an imaging step.

The camera includes a camera module that generates the image data from an optical image, and the camera module includes a housing including a through hole in a side wall; A lens installed in the through hole; and a driving unit that drives the lens.

In the 3D modeling module, drawing an object to be photographed based on the image and location information corresponding to the designated location stored in the database, and transmitting the 3D modeling image to the user terminal based on the image information received from the drone. It may be.

After the video and location information transmission step, the server may further include a step of specifying and displaying a specific object in the image received from the drone according to a predetermined standard.

A drone's multi-interface video transmission/reception and control system according to another embodiment of the present invention may perform the above method.

A non-transitory computer-readable medium according to another embodiment of the present invention is a non-transitory computer-readable medium that stores instructions, which, when executed by a processor, may cause the processor to perform the method. there is.

The present invention provides a multi-interface video transmission, reception and control method for a drone that can smoothly transmit and receive high-quality video information obtained from a drone, and can integrate and support drone control information with the video information.

The present invention provides a method for transmitting, receiving, and controlling multiple interface images of a drone for combining multiple interface images obtained from a drone so that 3D modeling can be implemented.

The present invention enables 3D modeling of natural or artificial objects that change over time to three-dimensionally embody the overall change process, and enables recognition of specific objects in each process.

Another embodiment of the present invention provides a multi-interface video transmission/reception and control system for a drone that can perform the above method.

Figure 1 shows one embodiment of the present invention.
Figure 2 relates to a flow chart according to an embodiment of the present invention.
Figure 3 is a diagram showing an example of an image correction filter according to the present invention.
Figure 4 shows an HSV graph according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement it. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein.

Additionally, in describing the embodiments disclosed in this specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed descriptions will be omitted.

In addition, the attached drawings are only for easy understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the attached drawings, and all changes included in the spirit and technical scope of the present invention are not limited. , should be understood to include equivalents or substitutes.

Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Figure 1 is a conceptual diagram showing the method of the multi-interface video transmission, reception and control system of a drone according to an embodiment of the present invention.

The drone 1000 referred to in the present invention includes unmanned aircraft and is defined to include all moving objects that can be operated unmanned. In addition, the drone includes means for movement such as flying or driving, means for transmitting and receiving, and means for storing and processing data.

The multi-interface image transmission/reception and control method of the drone 1000 according to an embodiment of the present invention includes a first correction step (S1) in which the drone 1000 moves to a predetermined designated location and captures an image according to a predetermined standard. ; A second correction step (S2) in which the image collected in the first correction step is received by the server 100 and matched with an image corresponding to the designated location stored in the database 500; A correction step 3 (S3) in which the drone 1000 receives the corrected location information and video shooting settings from the server 100 based on the matching result of the correction step 2; After the correction step 3, the drone 1000 moves to a designated location according to a predetermined standard and captures an image (S4); And an image and location information transmission step (S5) in which the image captured in the image capturing step includes location information of the drone 1000 and is transmitted to the server 100.

In acquiring certain image information through the drone 1000 and implementing 3D modeling data based on the image information, one of the problems is the time it takes for the captured image to be captured even if the subject is fixed. , the problem is that errors in modeling occur due to the influence of the weather. In particular, there is a problem that errors caused by GPS location information can also cause distortion of the captured image.

In particular, when the subject is large and the appearance of the subject changes over time, such as a building under construction, errors occur in the captured image, making it difficult to clearly model the process of deforming the subject. .

Therefore, when applying the correction steps 1 to 3 disclosed in the present invention, the above problem can be solved.

In the correction step 1 (S1), the drone 1000 moves to a predetermined designated location and captures images according to predetermined standards. The predetermined designated location is designated by shooting an image along with certain location information on a driving route for photographing a designated subject, and it is generally desirable to set a plurality of designated locations.

The designated location may have image information collected according to various shooting setting values from the location information previously stored in the database 500.

The flight path of the drone 1000 may be set as a path to move to a plurality of designated locations. While the drone 1000 flies along the flight path, it may selectively collect images at regular intervals and necessarily collect images at the designated location.

In the correction step 2 (S2), the image collected in the correction step 1 is received by the server 100 and matched with the image corresponding to the designated location stored in the database 500.

The database 500 stores image information corresponding to the designated location by type, setting value, and date of the camera included in the drone. In the second step of correction, image information captured at a designated location from the drone 1000 is received through the server 100, and the captured image information and location information included in the shooting information are received through the image analysis unit 200. Based on this, images corresponding to the location information are extracted from the database 500 and compared and analyzed. Through this, errors in the position sensor of the drone 1000 or errors in setting values can be adjusted. In particular, the video collected with the drone (1000) must be used for 3D modeling, etc. through a series of processing steps, so despite external influences such as weather and time, the accurate location information of each video image and external influences must be taken into consideration. As camera settings are adjusted, it is important to ensure that consistent video images are obtained.

In the correction step 3 (S3), the drone 1000 receives the corrected location information and video shooting settings from the server 100 based on the matching result of the correction step 2.

The modified location information and video shooting information allow the location information or camera setting values of the drone 1000 to be adjusted by analyzing the captured image and the matched image through the settings correction module.

The video capture step (S4) refers to video capture along the driving path created by connecting a plurality of designated locations after performing the correction steps 1 to 3.

By continuing to shoot at regular intervals through the above video shooting step (S4), natural objects or artificial objects that change over time can be captured in the same image, and data that can be used to examine the degree of change through 3D modeling can be constructed. there is. For example, by proceeding with the above video recording step (S4) for a building under construction, the entire construction process can be implemented through 3D modeling and examined for each process.

The image captured in the image and location information transmission step (S5) includes the location information of the drone 1000 and is transmitted to the server 100. Since the image information includes location information about the time when the image was captured, 3D modeling is implemented using a certain tool based on this.

In the multi-interface image transmission/reception and control method of the drone 1000, the designated location may be plural, the drone 1000 may include a plurality of cameras 250, and a separate storage device.

The designated location is set in plural, and the flight path of the drone 1000 is set by connecting the designated location points.

The cameras may be set in plural and may be multiple cameras that prevent missing images or have different angles from each other. Additionally, the drone 1000 may further include a vision recognition module.

In the second step of correction, the database may include a plurality of images with different video shooting settings for each specific location information, and the plurality of images may be matched with the captured image.

The image matching is to extract the same image despite changes in the external environment, and the image analysis unit 200 views and learns the captured image and shooting settings values obtained from the drone 1000 to set the desired image form. In order to do so, it may be matched with various images according to specific location information.

The multi-interface image transmission, reception and control method of the drone 1000 involves re-performing correction steps 1 to 3 after correction step 3, and the location information and video shooting setting values after correction in correction step 3 are the values before correction. If it is the same as , the video recording step may be performed.

This is to ensure that the continuity of the image is maintained through repetition of the correction step.

The camera 250 may include a lens assembly, a filter, a photoelectric conversion module, and an analog/digital conversion module. The lens assembly includes a zoom lens, a focus lens, and a compensation lens. The focal length of the lens may be moved according to control of the focus motor (MF). The filter is an optical low pass filter. It may include an infrared cut filter. The photoelectric conversion module has an imaging device such as a CCD (Charge Coupled Device) and converts light from the optical system (OPS) into an electrical analog signal. The analog/digital conversion module may include a Correlation Double Sampler and Analog-to-Digital Converter (CDSADC) element.

The camera 250 includes a camera module that generates the image data from an optical image, and the camera module includes a housing including a through hole in a side wall; A lens installed in the through hole; and a driving unit that drives the lens.

Drawing an object to be photographed based on the image and location information corresponding to the designated location stored in the database in the 3D modeling module, and transmitting the 3D modeling image to the user terminal based on the image information received from the drone 1000. It may include.

In order to obtain various image data, the lens needs to be exposed to the outside of the camera device 250 or the housing. Since shooting must continue outside for a long time despite changes in the external environment, contamination of the lens easily occurs. there is a problem.

Therefore, considering the location where the camera is installed, a lens with strong contamination resistance is required. Therefore, the present invention sought to solve this problem by proposing a coating layer for coating the lens.

Preferably, the surface of the lens may be coated with a coating composition containing a compound represented by the following [Chemical Formula 1], an organic solvent, an inorganic particle, and a dispersant.

[Formula 1]

here,

L ₁ is a single bond, a substituted or unsubstituted arylene group with 6 to 30 carbon atoms, a substituted or unsubstituted alkylene group with 1 to 20 carbon atoms, a substituted or unsubstituted cycloalkylene group with 3 to 20 carbon atoms, or a substituted or unsubstituted group. It is selected from the group consisting of an alkenylene group having 2 to 20 carbon atoms, a substituted or unsubstituted cycloalkenylene group having 3 to 20 carbon atoms, and a substituted or unsubstituted alkynylene group having 2 to 20 carbon atoms,

When L ₁ is substituted, hydrogen, nitro group, halogen group, hydroxy group, alkyl group of 1 to 30 carbon atoms, cycloalkyl group of 1 to 20 carbon atoms, alkenyl group of 2 to 30 carbon atoms, alkynyl group of 2 to 24 carbon atoms, carbon number It is substituted with one or more substituents selected from the group consisting of an aralkyl group with 7 to 30 carbon atoms, an aryl group with 6 to 30 carbon atoms, and an alkoxy group with 1 to 30 carbon atoms. When substituted with a plurality of substituents, they are the same or different from each other.

When a lens is coated with the coating composition, it can exhibit excellent water repellency and contamination resistance, so that clearer images or videos can be collected even if the lens installed around a port crane is exposed to a contaminated environment for a long period of time.

The inorganic particles may be selected from the group consisting of silica, alumina, and mixtures thereof. The average diameter of the inorganic particles is 70 to 100 μm, but is not limited to the above example. After being formed as a coating layer on the surface of the lens, the inorganic particles can improve physical strength and maintain viscosity within a certain range to improve moldability.

The organic solvent is selected from the group consisting of methyl ethyl ketone (MEK), toluene, and mixtures thereof, preferably methyl ethyl ketone, but is not limited to the above examples.

As the dispersant, a polyester-based dispersant can be used. Specifically, a polyester-based dispersion stabilizer consisting of a copolymer of 2-methoxypropyl acetate and 1-methoxy-2-propyl acetate is TEGO-Disperse 670 (manufacturer) : EVONIK) can be used, but is not limited to the above example and any dispersant that is obvious to those skilled in the art can be used without limitation.

The coating composition may further include a stabilizer as other additives, and the stabilizer may include an ultraviolet absorber, an antioxidant, etc., but is not limited to the above examples and can be used without limitation.

More specifically, the coating composition for forming the coating layer may include a compound represented by Formula 1, an organic solvent, inorganic particles, and a dispersant.

The coating composition may include 40 to 60 parts by weight of the compound represented by Formula 1, 20 to 40 parts by weight of inorganic particles, and 5 to 15 parts by weight of a dispersant, based on 100 parts by weight of the organic solvent. If the range is within the above range, a synergistic effect of the water repellent effect due to the interaction of each component is expressed to a critical degree, and if it is outside the above range, the synergistic effect is rapidly reduced or almost non-existent.

More preferably, the viscosity of the coating composition is 1500 to 1800 cP. If the viscosity is less than 1500 cP, there is a problem that it is not easy to form a coating layer because it flows down when applied to the lens surface. If the viscosity is more than 1800 cP, a uniform coating layer is not formed. There is a problem that it is difficult to form.

[Preparation Example 1: Preparation of coating layer]

1. Preparation of coating composition

A coating composition was prepared by mixing methyl ethyl ketone with a compound represented by the following formula (1), inorganic particles, and a dispersant:

[Formula 1]

here,

L ₁ is an unsubstituted alkylene group having 5 carbon atoms.

A more specific composition of the antistatic composition is shown in [Table 1] below.

TX1 TX2 TX3 TX4 TX5 organic solvent 100 100 100 100 100 Compound represented by formula 1 30 40 50 60 70 inorganic particles 10 20 30 40 50 dispersant One 5 10 15 20

(unit weight)

2. Preparation of coating layer

The coating compositions of DX1 to DX5 were applied to one surface of the lens and then cured to form a coating layer.

[Experimental Example 1: Coating layer evaluation]

1. Surface appearance evaluation

Due to differences in viscosity of the coating composition, after manufacturing the coating layer, sensory evaluation was conducted to determine whether a uniform surface was formed. An evaluation was conducted as to whether a uniform coating layer was formed, and the evaluation was conducted according to the following criteria.

○: Formation of uniform coating layer

×: Formation of uneven coating layer

TX1 TX2 TX3 TX4 TX5 Sensory evaluation Υ ○ ○ ○ Υ

When forming a coating layer, if the viscosity is below a certain level, flow occurs on the surface of the lens, making it difficult to form a uniform coating layer after the curing process. Accordingly, the problem of lowering the production yield may occur. Additionally, even when the viscosity was too high, it was difficult to uniformly apply the composition, making it impossible to form a uniform coating layer.

2. Measurement of water repellency angle

After forming the coating layer on the surface of the lens, the results of measuring the water repellency angle are shown in Table 3 below.

Advancing contact angle (〃) Rest contact angle (〃) Receding contact angle (〃) TX1 117.1±2.9 112.1±4.1 < 10 TX2 132.4±1.5 131.5±2.7 141.7±3.4 TX3 138.9±3.0 138.9±2.7 139.8±3.7 TX4 136.9±2.0 135.6±2.6 140.4±3.4 TX5 116.9±0.7 115.4±3.0 < 10

As shown in [Table 3], after forming a coating layer using the coating compositions of TX1 to TX5, the results of measuring the contact angle were confirmed. TX1 and TX5 were measured to have receding contact angles of less than 10 degrees. In other words, it was confirmed that pinning of water droplets occurs when the coating composition falls outside the optimal range for manufacturing the coating composition. On the other hand, it was confirmed that no pinning phenomenon occurred in TX2 to 4, showing that excellent waterproofing effects can be achieved.

3. Contamination resistance evaluation

A lens on which the coating layer according to the above example was formed around the tank was attached to a model camera, and the camera was exposed to the environment around the tank containing seawater with a high salt concentration for 10 days in order to configure it like a port yard. As a comparative example (Con), the same lens without a coating layer was used, and in each example, a model camera was installed at the same location around the water tank.

Afterwards, the degree of contamination of the lens before and after the experiment was evaluated, and for objective comparison, the results were compared with the comparative example in which no coating layer was formed, and the results were evaluated with an index of 1 to 10 and are shown in [Table 4] below. As for the indices below, the lower the number, the better the contamination resistance.

Con TX1 TX2 TX3 TX4 TX5 Staining resistance 10 7 3 3 3 8

(Unit: index)

Referring to [Table 4] above, when forming a coating layer on a lens, image data can be collected in a form that is easy to analyze for a long period of time with high contamination resistance even if the lens is exposed to the outside while installing the camera in the external environment. You can see the point. In particular, it can be confirmed that in the case of TX2 to TX4, the contamination resistance by the coating layer is very excellent.

After the image and location information transmission step (S5), the server 100 may further include a step of specifying and displaying a specific object in the image received from the drone 1000 according to a predetermined standard.

This is so that the object recognition module 400 automatically recognizes specific objects constituting the subject while obtaining images of a continuously changing subject, such as a building under construction. Through this, it is possible to determine whether there is a risk in a building under construction or to evaluate whether the construction process is being carried out according to the design or intended process.

The object recognition module may apply a CNN algorithm previously learned based on video images, and in this case, the video image obtained from the drone 1000 may have an image correction filter applied. When the image correction filter is applied, the target needed to recognize an object can be more clearly recognized, thereby significantly reducing the error in the recognition rate. Accordingly, specific objects can be recognized and analyzed effectively in the subject based on the video image.

Figure 3 is a diagram showing an example of an image correction filter according to the present invention, and Figure 4 shows an HSV graph according to the present invention.

In addition, the CNN algorithm, which will be described later, can be applied or applied in the present invention to recognize image data or all objects that are targets in image data.

Figure 3 shows the types and functions of filters. In other words, the CNN algorithm may be a learning algorithm that uses multiple layers. In addition, the CNN algorithm can automatically learn filters that maximize image classification accuracy, and by adding new layers called convolutional layers and polling layers before the fully connected layer, the filtered image is obtained after applying the filtering technique to the original image. A classification operation can be performed on . The CNN algorithm is configured to apply a filtering technique to the original image by adding a new layer called a convolutional layer and a pooling layer before the fully-connected layer, and then perform a classification operation on the filtered image. You can.

At this time, the calculation formula for the image filter using the CNN algorithm is as shown in Equation 1 below.

[Equation 1]

(step,

G _ij : pixel in the ith row and jth column of the filtered image expressed as a matrix,

F: filter

X: image

F _H : Height of filter (number of rows),

F _W : Width (number of columns) of the filter.)

Preferably, the calculation equation for the image filter using the CNN algorithm is as shown in Equation 2 below.

[Equation 2]

(step,

G _ij : pixel in the ith row and jth column of the filtered image expressed as a matrix,

F': Application filter

X: image

_F'H : Height of filter (number of rows),

F' _W : Width (number of columns) of the filter.)

Preferably, F' is an application filter and may be a filter applied to the image data in order to learn image data including the drone 1000 and recognize feature points of the drone 1000 included in the image data. In particular, when recognizing the characteristic points of the drone 1000, it may be classified based on differences in shape and color, so an application filter may be necessary to effectively recognize shape and color. To meet this need, the application filter F' can be calculated by Equation 3 below.

[Equation 3]

(However, F: filter, ρ: coefficient, F': application filter)

At this time, the filter according to each F may be one of the edge detection, sharpen, and box blur matrices according to FIG. 4.

Preferably, the calculation formula for calculating ρ is as shown in Equation 4 below. At this time, ρ can be interpreted as a variable used to increase the efficiency of the filter, and its unit can be ignored.

[Equation 4]

However, the diameter of the lens of the camera device 250 used to capture the image is in mm, the f value of the lens is the aperture value (F number) of the lens, and the HSV average value is the color coordinates according to the image in the HSV graph. It can mean the average value of the value converted to a size value. Specific details about the HSV value are as follows.

According to FIG. 4, the HSV graph according to the present invention may mean a color space that reflects perceptual characteristics. H(Hue, 0~360°) can mean hue, S(Saturation, 0~100%) can mean saturation, and V(Value, 0~100%) can mean brightness. . Hue, saturation, and brightness values can be referred to as HSV values, which can be easily extracted using graphic tools such as Adobe Illustrator CC 2019.

The HSV average value according to the present invention can be obtained through the HSV three-dimensional coordinates of FIG. 15. That is, the HSV average value according to the present invention can be calculated based on the HSV value obtained through a graphic tool. The distance value of the HSV coordinates measured with the origin coordinates on the HSV three-dimensional coordinates as the reference point can constitute the above-described HSV average value. That is, the image according to the present invention includes an image of the drone 1000, and the HSV color coordinates of the image may be distributed in a certain area among the HSV three-dimensional coordinates. Therefore, the HSV average value according to the present invention may mean the distance value from the origin coordinate calculated based on the average coordinate using the average of the HSV coordinates for the color of a certain area.

[Experimental Example 2: Application filter evaluation]

The recognition accuracy of the drone 1000 when applying the application filter F' of the present invention to the image data according to the present invention is as follows. The table below is a numerical representation of the accuracy of recognition results based on whether or not filters are applied, based on requests from 10 experts in the relevant technology field.

No filter applied Apply filter F Apply filter F' Average Accuracy (Score) 75 90 97

[Table 5] above shows the average value of accuracy scores evaluated by experts for each case. This experimental example evaluates the accuracy of a learning module previously learned using the same big data, depending on whether or not a filter is applied.

In addition, this experimental example was tested with image data including 120 different drones (1000), and the recognition results were surveyed by 10 experts on the accuracy of dog recognition included in the image data.

As can be seen in [Table 5] above, when a filter is not applied, there is a possibility that an error will occur in image recognition, so the accuracy was evaluated to be relatively low. In comparison, the accuracy was somewhat higher when the general CNN filter F was applied, but it was confirmed that the accuracy was significantly improved when the applied filter F' was applied.

Therefore, it is possible to increase recognition of the target object from the image obtained by applying the application filter.

A multi-interface video transmission/reception and control system of the drone 1000 according to another embodiment of the present invention may perform the above method.

The server 100 or drone 1000 according to the present invention may include a processor 11, memory 12, and communication module 13.

The processor 11 may control other components by executing instructions stored in the memory 12. The processor 11 may execute instructions stored in the memory 12.

The processor 11 is a component that can perform calculations and control other devices. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), etc. Additionally, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and clock signal. However, while a CPU or AP consists of a few cores optimized for serial processing, a GPU can consist of thousands of smaller, more efficient cores designed for parallel processing.

The processor 11 can provide or process appropriate information or functions to the user by processing signals, data, information, etc. input or output through the components discussed above, or by running an application program stored in the memory 12.

The memory 12 stores data supporting various functions of the server 100. The memory 12 may store a number of application programs (application programs or applications) running on the server 100, data for operating the server 100, and commands. At least some of these applications may be downloaded from an external server via wireless communication. Additionally, the application program may be stored in the memory 12, installed on the server 100, and driven by the processor 11 to perform the operation (or function) of the server 100.

The memory 12 is a flash memory type, hard disk type, solid state disk type, SDD type (Silicon Disk Drive type), and multimedia card micro type. ), card-type memory (e.g. SD or XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), EEPROM (electrically erasable programmable read) -only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk may include at least one type of storage medium. Additionally, the memory 12 may include web storage that performs a storage function on the Internet.

The communication module 13 transmits and receives information to and from a base station or a camera including a communication function through an antenna. The communication module 13 may include a modulator, demodulator, signal processor, etc. Additionally, the communication module 13 can perform a wired communication function.

Wireless communication refers to communication using communication facilities already installed by communication companies and a wireless communication network that uses the frequencies of those communication facilities. At this time, the communication module 13 includes code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single carrier frequency division multiple access (SC-FDMA). It can be used in various wireless communication systems such as access), and in addition, the communication module 13 can also be used in 3rd generation partnership project (3GPP) long term evolution (LTE), etc. In addition, not only 5G communication, which has recently been commercialized, but also 6G, which is scheduled for commercialization in the future, can be used. However, this specification can utilize a pre-installed communication network without being limited to such wireless communication method.

In addition, short range communication technologies include Bluetooth, BLE (Bluetooth Low Energy), Beacon, RFID (Radio Frequency Identification), NFC (Near Field Communication), and Infrared Data Association (IrDA). ), UWB (Ultra Wideband), ZigBee, etc. may be used.

At this time, the communication module 13 can transmit and receive data in real time by directly communicating with the drone 1000 through wireless communication or short-distance communication. Accordingly, the drone 1000 may also include a component corresponding to the communication module 13 and communicate with the communication module 13 of the server 100.

A non-transitory computer-readable medium according to another embodiment of the present invention is a non-transitory computer-readable medium that stores instructions, which, when executed by a processor, may cause the processor to perform the method. there is.

Although the preferred embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims are also possible. falls within the scope of rights.

User terminal (1)
Processor(11)
Memory(12)
Communication module(13)
Server(100)
Image Analysis Department (200)
Camera device(250)
Setting correction module (300)
Object recognition module (400)
Database(500)
Drone (1000)

Claims (9)

The first stage of correction is for the drone to move to a pre-determined location and capture images according to pre-determined standards;
A second correction step in which the image collected in the first correction step is received by a server and matched with an image corresponding to the designated location stored in a database;
A third correction step in which the drone receives corrected location information and video shooting settings from the server based on the matching result of the second correction step;
After the correction step 3, the drone moves to a designated location according to a predetermined standard and captures an image; and
The video captured in the video shooting step includes the location information of the drone and is transmitted to the server, including the video and location information transmission step.
Multi-interface video transmission, reception and control method for drones. According to clause 1,
There are multiple designated locations,
The drone includes a plurality of cameras and a separate storage device.
Multi-interface video transmission, reception and control method for drones. According to clause 2,
In the second step of correction, the database includes a plurality of images with different video shooting settings for each specific location information, and matches the plurality of images with the captured image.
Multi-interface video transmission, reception and control method for drones. According to clause 3,
After correction step 3, correction steps 1 to 3 are performed again, and if the location information and video capture setting values after correction in correction step 3 are the same as the values before modification, the video capture step is performed.
Multi-interface video transmission, reception and control method for drones. According to clause 4,
The camera includes a camera module that generates the image data from an optical image,
The camera module is,
A housing including a through hole in a side wall;
A lens installed in the through hole; and
A driving unit that drives the lens; including
Multi-interface video transmission, reception and control method for drones. According to clause 4,
In the 3D modeling module, the object to be photographed is drawn based on the image and location information corresponding to the designated location stored in the database,
Including the step of transmitting a 3D modeling image to a user terminal based on image information received from the drone.
Multi-interface video transmission, reception and control method for drones. According to clause 4,
After the video and location information transmission stage,
It further includes the step of specifying and displaying a specific object in the server according to predetermined criteria in the image received from the drone.
Multi-interface video transmission, reception and control method for drones Carrying out the method according to any one of claims 1 to 7
Drone's multi-interface video transmission, reception and control system. A non-transitory computer-readable medium storing instructions, comprising:
When the instructions are executed by the processor,
causing the processor to perform the method of any one of claims 1 to 7.
Non-transitory computer-readable media.