KR20210116904A - Hidden camera detection system, method and computing device for performing the same - Google Patents

Abstract

Disclosed are a hidden camera detection system capable of easily detecting a hidden camera, and a method and a computing device for performing the same. According to one embodiment of the present invention, a hidden camera detection method is executed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors. The method comprises the following steps: receiving a CCD image and a thermal image of a suspicious place from a detection device; extracting an object boundary in the CCD image; displaying an outline on the thermal image; matching the object boundary of the CCD image with the outline displayed on the thermal image and overlapping the CCD image and the thermal image to generate an overlapping image; and determining an area where a hidden camera is hidden from the generated overlapping image.

Description

HIDDEN CAMERA DETECTION SYSTEM, METHOD AND COMPUTING DEVICE FOR PERFORMING THE SAME

Embodiments of the present invention relate to hidden camera detection techniques.

Recently, hidden camera crimes are becoming more intelligent and sophisticated, causing anxiety, and the anxiety of women, especially among the people, is increasing. Such a hidden camera can shoot video that infringes on the privacy of a large number of unspecified individuals due to its small size, and the recent hidden camera may be an Internet of Things (IoT) device connected to the Internet by wire or wireless to transmit image information.

For example, an IoT device, an ultra-small hidden camera, may be manufactured in the form of an object or in the form of a non-object. Object-type hidden cameras are USB (universal serial bus) memory type, hat type, car key type, wrist watch type, table clock type, smoke alarm type, wall clock type, glasses type, belt type, ballpoint pen type, wall painting type and various types of hidden cameras, such as a wall-mounted switch type. In addition, the non-object type hidden camera may be various non-object type hidden cameras such as an endoscope type and a module type.

These microscopic hidden cameras in the form of objects and non-objects may be installed in enclosed rooms and walls of buildings. Accordingly, there is a problem in that it is difficult for the general public to detect a hidden camera that is hidden in a small size with the naked eye.

Republic of Korea Utility Model Publication No. 20-0411448 (2006.03.08.)

Embodiments of the present invention are for detecting the hidden camera by detecting the heat source through the thermal imaging camera of the heat source generated when the hidden camera is operating.

According to an exemplary embodiment of the present invention, there is provided a method performed on a computing device having one or more processors, and a memory storing one or more programs executed by the one or more processors, wherein the method of photographing a stash from a detection device Receiving a CCD image and a thermal image; extracting an object boundary from the CCD image; displaying an outline on the thermal image; generating an overlapping image by matching a boundary of an object of the CCD image with an outline displayed on the thermal image and superimposing the CCD image and the thermal image; and determining an area where the hidden camera is hidden from the generated overlapping image.

The step of extracting the boundary of the object from the CCD image may include: recognizing the object in the CCD image through a first machine learning module; and detecting the boundary of the object from the CCD image in which the object is recognized through a second machine learning module.

The displaying of the outline on the thermal image may include correcting emissivity information of the thermal image; performing an automatic level adjustment process on the corrected thermal image; resizing the pre-processed movie image to a preset size; and detecting and displaying an outline from the resized thermal image.

In the calibrating the emissivity information of the thermal image, the brightness distribution may be normalized by normalizing the emissivity of different materials in the thermal image to 1.0.

The performing the automatic level adjustment process may include calculating a density level of each pixel for the corrected thermal image, and resetting the color to the corresponding pixel according to the calculated density level. .

The step of detecting and displaying the contour may include calculating the brightness level of each pixel by grayscale processing the resized thermal image, and extracting pixels corresponding to discontinuities of the brightness level. have.

The generating of the overlapping image may include adjusting the transparency of the CCD image to overlap the CCD image.

The step of determining the area hidden by the hidden camera may include: extracting an area having the highest temperature within the boundary of the object of the generated overlapping image; determining the extracted area as a hidden area by a hidden camera; and providing an overlapping image indicating the hidden area to the user.

The providing to the user may include: receiving image selection information from a smart device; and providing the CCD image or the superimposed image displaying the hidden area to the smart device according to the image selection information.

According to another exemplary embodiment of the present invention, there is provided a computing device including one or more processors and a memory for storing one or more programs executed by the one or more processors, a CCD image obtained by photographing a hidden location from a detection device. and a communication module for receiving the thermal image. a boundary detection module for extracting an object boundary from the CCD image; an image conversion module for displaying an outline on the thermal image; an image overlapping module that matches a boundary of an object of the CCD image with an outline displayed on the thermal image, and generates an overlapping image by superimposing the CCD image and the thermal image; and an image analysis module for determining an area in which a hidden camera is hidden from the generated overlapping image.

The boundary detection module includes: a first machine learning module for recognizing an object in the CCD image; and a second machine learning module configured to detect a boundary of the object in the CCD image in which the object is recognized.

The image conversion module may include: a preprocessing module for correcting emissivity information of the thermal image and performing an automatic level adjustment process on the corrected thermal image; an image resizing module for resizing the pre-processed movie image to a preset size; and a region display module that detects and displays an outline from the resized thermal image.

The pre-processing module may normalize the brightness distribution by normalizing the emissivity of different materials in the thermal image to 1.0.

The pre-processing module may calculate a density level of each pixel for the corrected thermal image, and reset the color of the corresponding pixel according to the calculated density level.

The area display module may grayscale the resized thermal image to calculate a brightness level of each pixel, and extract a pixel corresponding to a discontinuity of the brightness level.

The image overlapping module may overlap the CCD image by adjusting the transparency of the CCD image.

The image analysis module extracts the area with the highest temperature within the boundary of the object of the generated overlapped image, determines the extracted area as the area hidden by the hidden camera, and uses the overlapped image displaying the hidden area to the user. can be provided to

The communication module may receive the image selection information from the smart device, and provide the CCD image or the superimposed image displaying the hidden area to the smart device according to the image selection information.

According to another exemplary embodiment of the present invention, a detection apparatus including a photographing unit for photographing a hidden place to obtain a CCD image and a thermal image; and receiving the CCD image and the thermal image from the detection device, extracting a boundary of an object from the CCD image, and displaying an outline on the thermal image, the boundary of the object of the CCD image and displayed on the thermal image There is provided a hidden camera detection system including an analysis server that matches the contour and overlaps the CCD image and the thermal image to generate an overlapping image, and determines an area in which a hidden camera is hidden from the generated overlapped image.

The hidden camera detection system may further include a smart device for receiving and displaying a thermal image displaying the hidden area.

According to embodiments of the present invention, the hidden camera may be detected by detecting a heat source through the thermal imaging camera of a heat source that is generated when the hidden camera is operating.

In addition, by superimposing the CCD image captured by the CCD camera and the thermal image captured by the thermal imager, the outline of the object in the thermal image can be clearly displayed to express the detail of the object.

1 is a configuration diagram for explaining a hidden camera detection system according to an embodiment of the present invention;
2 is a configuration diagram for explaining a detection device of a hidden camera detection system according to an embodiment of the present invention;
3 is a configuration diagram for explaining an analysis server of a hidden camera detection system according to an embodiment of the present invention;
4 is a diagram showing the configuration of a boundary detection module and an image conversion module in the analysis server according to an embodiment of the present invention;
5 is a view showing a screen of a smart device provided with a hidden camera detection service according to an embodiment of the present invention;
6 is a flowchart illustrating a hidden camera detection system according to an embodiment of the present invention;
7 is a block diagram illustrating and describing a computing environment including a computing device suitable for use in example embodiments;

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to provide a comprehensive understanding of the methods, apparatus, and/or systems described herein. However, this is only an example, and the present invention is not limited thereto.

In describing the embodiments of the present invention, if it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, the terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to intentions or customs of users and operators. Therefore, the definition should be made based on the content throughout this specification. The terminology used in the detailed description is for the purpose of describing embodiments of the present invention only, and should in no way be limiting. Unless explicitly used otherwise, expressions in the singular include the meaning of the plural. In this description, expressions such as “comprising” or “comprising” are intended to indicate certain features, numbers, steps, acts, elements, some or a combination thereof, one or more other than those described. It should not be construed to exclude the presence or possibility of other features, numbers, steps, acts, elements, or any part or combination thereof.

Also, terms such as first and second may be used to describe various components, but the components should not be limited by the terms. The above terms may be used for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

Meanwhile, an embodiment of the present invention may include a program for performing the methods described in this specification on a computer, and a computer-readable recording medium including the program. The computer-readable recording medium may include program instructions, local data files, local data structures, and the like alone or in combination. The medium may be specially designed and configured for the present invention, or may be commonly used in the field of computer software. Examples of computer-readable recording media include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and program instructions specially configured to store and execute program instructions such as ROMs, RAMs, flash memories, and the like. Hardware devices are included. Examples of the program may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

1 is a block diagram illustrating a hidden camera detection system according to an embodiment of the present invention, and FIG. 2 is a block diagram illustrating a detection apparatus of a hidden camera detection system according to an embodiment of the present invention, FIG. 3 is a configuration diagram for explaining an analysis server of a hidden camera detection system according to an embodiment of the present invention, and FIG. 4 shows the configuration of a boundary detection module and an image conversion module in the analysis server according to an embodiment of the present invention It is a drawing.

1 to 4 , the hidden camera detection system according to an embodiment of the present invention may include a detection device 100 , a smart device 200 , and an analysis server 300 .

The detection device 100 , the smart device 200 , and the analysis server 300 may communicate with each other as they are connected using a communication network.

In some embodiments, the communication network comprises the Internet, one or more local area networks, wire area networks, cellular networks, mobile networks, other types of networks, or a combination of these networks. and can utilize known communication methods that can be delivered in a short distance such as Bluetooth, Zigbee, and Infra-red.

The detection apparatus 100 is for photographing a place where the hidden camera is likely to be hidden, and may include a photographing unit 110 and a transmission unit 120 .

The photographing unit 110 may include a CCD camera (not shown) for acquiring a CCD image and a thermal imaging camera (not shown) for acquiring a thermal image. The photographing unit 110 may photograph a place where the hidden camera is likely to be hidden. Here, the CCD camera is a camera for photographing an object in the visible region (0.4~0.7㎛), such as the human eye, and the thermal imaging camera is a thermal infrared camera (3~5㎛, 7~ 12㎛) wavelength band.

The transmitter 120 may transmit the captured CCD image and the thermal image to the analysis server 300 through a network.

The smart device 200 is a terminal for Internet or mobile access, and may include, for example, any device capable of Internet or mobile access, including a PC such as a desktop or a laptop computer, a mobile terminal such as a smart phone, or a tablet. have. The smart device 200 may perform data communication using the analysis server 300 and wireless communication.

In addition, the smart device 200 may be installed with an application for providing a hidden camera detection service. The application may be stored in a computer-readable storage medium of the smart device 200 . The application includes a predetermined set of instructions executable by the processor of the smart device 200 . The command may cause the processor of the smart device 200 to perform an operation according to an exemplary embodiment. The computer-readable storage medium of the smart device 200 includes components of an operating system for executing a set of instructions, such as the application, on the smart device 200 . For example, such an operating system may be Apple's iOS or Google's Android.

Here, the application for providing the hidden camera detection service may provide an input interface (eg, a selection among a plurality of menus, toggle) through which a user can select a captured image, and select an image through the input interface information can be entered. For example, an input interface for selecting a CCD image and an overlapping image may be provided to the user. Here, the CCD image or the superimposed image may be selected through the image selection information.

In addition, the application for providing the hidden camera detection service may display the analysis information processed by the analysis server 300 through a display unit (not shown).

For reference, the input module (not shown) is a configuration basically included in the smart device 200 , and the user of the smart device 200 uses input means (eg, keyboard, key pad, mouse, touch screen, etc.) It is possible to receive input data generated by physically manipulating it.

On the other hand, the application for providing the hidden camera detection service may provide a function for uploading analysis information to a preset web server in addition to the function described above. In addition, it is possible to provide a function to report to the police according to the analysis information.

The analysis server 300 may include a communication module 310 , a storage module 320 , a boundary detection module 330 , an image conversion module 340 , an image overlapping module 350 , and an image analysis module 360 . .

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the “module” may mean a logical unit of a predetermined code and a hardware resource for executing the predetermined code, and does not necessarily mean physically connected code or a single type of hardware. .

The communication module 310 may communicate with the detection device 100 through a network. The communication module 310 may receive the CCD image and the thermal image photographed from the detection device 100 . Also, the communication module 310 may perform data communication with the smart device 200 through a network. The communication module 310 may receive image selection information from the smart device 200 . The communication module 310 may transmit the analysis information to the smart device 200 . Here, the CCD image or the superimposed image may be provided to the smart device 200 through the image selection information.

The storage module 320 may store the CCD image, the thermal image, and the superimposed image received from the detection device 100 . Also, the storage module 320 may store analysis information.

The boundary detection module 330 may detect the boundary of the object part in the CCD image. The boundary detection module 330 may include a first machine learning module 331 and a second machine learning module 332 .

The first machine learning module 331 may recognize an object from the CCD image received through the communication module 310 . When a CCD image is input, the first machine learning module 331 may recognize an object from the input CCD image based on already learned images (ie, objects).

In an exemplary embodiment, the first machine learning module 331 may use an object recognition algorithm or the like with machine learning or deep learning technology. Here, the object recognition algorithm is a part of algorithm methodologies used in machine learning, for example, RCNN, R-FCN, SSD, YOLO, etc. may be used.

The second machine learning module 332 may receive the CCD image in which the object is recognized from the first machine learning module 331 and detect the boundary of the object part in the CCD image in which the object is recognized. When the CCD image in which the object is recognized is input, the second machine learning module 332 is configured to detect the boundary of the object in the CCD image in which the input object is recognized based on already learned data (ie, object boundary information). can

In an exemplary embodiment, the second machine learning module 332 may use a convolutional neural network (CNN) as a machine learning or deep learning technique. In this case, the second machine learning module 332 may be a neural network trained to detect and output the boundary of the object from the CCD image in which the input object is recognized when the CCD image in which the object is recognized is input. Since the convolutional neural network is a known technology, a detailed description thereof will be omitted.

The image conversion module 340 may convert the thermal image to overlap the thermal image and the CCD image. The image conversion module 340 may include a preprocessing module 341 , an image resizing module 342 , and a region display module 343 .

The preprocessing module 341 may correct emissivity information of the thermal image. Specifically, the preprocessing module 341 may normalize the brightness distribution by normalizing the emissivity of different materials to 1.0 in the thermal image. Here, emissivity information is a rate at which energy is radiated from a material, and when 100% of the energy contained in the material is radiated to the outside, the emissivity coefficient becomes 1.0. For example, when a material having an emissivity of 0.97 is 100 degrees, when it is observed using infrared rays, it is measured to be 97 degrees, and correction for 3 degrees is required. Accordingly, the brightness distribution can be normalized by standardizing the emissivity of different materials to 1.0 in the thermal image using the known material emissivity information.

In addition, the preprocessing module 341 may perform automatic level adjustment (Auto Gain Control) and pseudo-color processing to intuitively recognize the temperature in the normalized thermal image. For example, a thermal imaging camera can express a value of 0 to 0x3FFF for each pixel constituting an image with 14 bits. However, in general, the detected temperature is a partial temperature of room temperature, and only data values ranging from 0x1000 to 0x1400 are used for thermal imaging. A blurred image is generated by input to the sensor. Accordingly, by performing the automatic level adjustment process on the thermal image, it is possible to generate a clear image. For example, the preprocessing module 341 may calculate an average value of each pixel for the entire thermal image, and then redefine the calculated average value as a pixel value of the corresponding pixel. In addition, the thermal imaging camera will display a monochromatic image. Accordingly, a color image may be generated by performing pseudo-color processing on the thermal image. For example, the preprocessing module 341 may calculate a density level of each pixel for the entire thermal image, and then assign a color to the corresponding pixel according to the calculated density level.

The image resizing module 342 may resize the pre-processed thermal image to a preset size. The image resizing module 342 may resize the pre-processed thermal image to the size of the CCD image. That is, since the thermal image overlaps the CCD image, it may be resized to the same size as the CCD image. In an exemplary embodiment, the image resizing module 342 may resize the preprocessed thermal image 384 x 288 to a size of 1280 x 720. Here, the image resizing module 342 may apply a bi-linear algorithm to which 2x2 is applied.

The region display module 343 may display a region (outline) in the resized thermal image. The area display module 343 calculates the brightness level of each pixel by gray-scale processing the resized thermal image, and then extracts the pixel corresponding to the discontinuity of the brightness level to emphasize the pixel. Thus, the region can be displayed on the thermal image.

The image overlapping module 350 may superimpose the thermal image converted based on the boundary of the object detected by the boundary detection module 330 by alpha blending. That is, in the general thermal image, the boundary of the object is blurred, making it difficult to recognize the object. Accordingly, by performing the alpha blending process on the converted thermal image based on the boundary of the object detected from the CCD image, it is possible to generate an overlapping image so that the object can be clearly distinguished from the thermal image.

Specifically, the image superposition module 350 matches the boundary of the object of the CCD image detected by the boundary detection module 330 with the area displayed in the thermal image, and then adjusts the transparency of the CCD image to obtain the converted thermal image and An overlapping image may be generated by superimposing the CCD image. Accordingly, by superimposing the boundary of the object of the CCD image captured by the CCD camera on the thermal image, the outline of the object in the thermal image can be clearly displayed to express the detail of the object.

The image analysis module 360 may determine a position where the hidden camera is hidden in the generated overlapping image. Specifically, the image analysis module 360 may extract a region having the highest temperature within a displayed region of the generated overlapping image and determine the region as a region in which the hidden camera is hidden. That is, since the hidden camera hidden in a specific object is heated by the heat source when it is operated, the hidden camera can be detected by detecting the heating region.

Also, the image analysis module 360 may generate analysis information including an overlapping image indicating a location where the hidden camera is hidden. For example, the image analysis module 360 may display the location where the hidden camera is hidden on the superimposed image and provide it to the user's smart device 200 .

5 is a diagram illustrating a screen of a smart device provided with a hidden camera detection service according to an embodiment of the present invention.

As shown in FIG. 5 , the analysis server 300 may provide (a) a CCD image or (b) a superimposed image to the smart device according to the image selection information input from the user's smart device 200 . Referring to FIG. 5 , the outline of the object 1 may be clearly displayed in the thermal image, and the hidden camera may be detected by extracting the region S having the highest temperature within the recognized object.

According to the disclosed embodiment, by superimposing the CCD image photographed by the CCD camera and the thermal image image photographed by the thermal imaging camera, the outline of the object is clearly displayed in the thermal image image to express the detail of the object.

6 is a flowchart illustrating a hidden camera detection system according to an embodiment of the present invention. The method illustrated in FIG. 6 may be performed, for example, by a computing device 12 having one or more processors and a memory storing one or more programs executed by the one or more processors. To this end, the hidden camera detection method may be implemented in the form of a program or software including one or more computer-executable instructions and stored in the memory.

In addition, in the illustrated flowchart, the method is described by dividing the method into a plurality of steps, but at least some of the steps are performed in a different order, are performed in combination with other steps, are omitted, are performed in separate steps, or are shown One or more steps not included may be added and performed.

Referring to FIG. 6 , the analysis server 300 receives a CCD image and a thermal image of the hidden place from the detection device 100 ( S601 ).

Next, the analysis server 300 extracts the boundary of the object from the CCD image through the machine learning module (S602). Specifically, the analysis server 300 may recognize the object in the CCD image through the first machine learning module 331 , and the object in the CCD image in which the object is recognized through the second machine learning module 332 . boundaries can be detected.

Next, the analysis server 300 displays an outline on the thermal image through the image conversion module 340 (S603). Specifically, the analysis server 300 may correct emissivity information of the thermal image through the pre-processing module 341 , and perform automatic level adjustment and pseudo-color processing on the corrected thermal image. In addition, the analysis server 300 resizes the thermal image image preprocessed through the image resizing module 342 to a preset size, and detects and displays the outline in the thermal image image resized through the area display module 343. have.

Next, the analysis server 300 matches the boundary of the object of the CCD image with the contour displayed on the thermal image, and creates an overlapping image by overlapping the CCD image and the thermal image ( S604 ).

Finally, the analysis server 300 determines the area in which the hidden camera is hidden in the generated overlapping image (S605). Specifically, the analysis server 300 may extract the highest area within the boundary of the object of the generated overlapping image, and determine the extracted area as the area where the hidden camera is hidden. In addition, the analysis server 300 may provide the user with an overlapping image in which the hidden area is displayed.

According to the disclosed embodiment, the hidden camera can be detected by detecting the heat source through the thermal imaging camera of the heat source generated when the hidden camera is operating. In addition, by superimposing the CCD image photographed by the CCD camera and the thermal image photographed by the thermal imaging camera, the outline of the object can be clearly displayed in the thermal image image to express the detail of the object.

7 is a block diagram illustrating and describing a computing environment 20 including a computing device suitable for use in example embodiments. In the illustrated embodiment, each component may have different functions and capabilities other than those described below, and may include additional components in addition to those described below.

The illustrated computing environment 20 includes a computing device 22 . In one embodiment, computing device 22 may be smart device 200 . Also, in one embodiment, computing device 22 may be analysis server 300 .

The computing device 22 includes at least one processor 24 , a computer readable storage medium 26 , and a communication bus 28 . The processor 24 may cause the computing device 22 to operate in accordance with the exemplary embodiments discussed above. For example, the processor 24 may execute one or more programs stored on the computer-readable storage medium 26 . The one or more programs may include one or more computer-executable instructions that, when executed by the processor 24, configure the computing device 22 to perform operations in accordance with the exemplary embodiment. can be

Computer-readable storage medium 26 is configured to store computer-executable instructions or program code, program data, and/or other suitable form of information. The program 30 stored in the computer readable storage medium 26 includes a set of instructions executable by the processor 24 . In one embodiment, computer-readable storage medium 26 includes memory (volatile memory, such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash It may be memory devices, other forms of storage medium that can be accessed by computing device 22 and store desired information, or a suitable combination thereof.

Communication bus 28 interconnects various other components of computing device 22 , including processor 24 and computer readable storage medium 26 .

Computing device 22 may also include one or more input/output interfaces 32 and one or more network communication interfaces 36 that provide interfaces for one or more input/output devices 34 . The input/output interface 32 and the network communication interface 36 are coupled to the communication bus 28 . The input/output device 34 may be coupled to other components of the computing device 22 via an input/output interface 32 . Exemplary input/output device 34 may include a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touchscreen), a voice or sound input device, various types of sensor devices, and/or imaging devices. input devices, and/or output devices such as display devices, printers, speakers and/or network cards. The exemplary input/output device 34 may be included in the computing device 22 as a component constituting the computing device 22 , and may be connected to the computing device 22 as a separate device distinct from the computing device 22 . may be

Although representative embodiments of the present invention have been described in detail above, those of ordinary skill in the art will understand that various modifications are possible without departing from the scope of the present invention with respect to the above-described embodiments. . Therefore, the scope of the present invention should not be limited to the described embodiments and should be defined by the claims described below as well as the claims and equivalents.

100: detection device
110: filming unit
120: transmission unit
200: smart device
300: analysis server
310: communication module
320: storage module
330: boundary detection module
331: first machine learning module
332: second machine learning module
340: image conversion module
341: preprocessing module
342: image resizing module
343: area display module
350: image superposition module
360: video analysis module

Claims (20)

one or more processors, and
A method performed in a computing device having a memory storing one or more programs to be executed by the one or more processors, the method comprising:
Receiving a CCD image and a thermal image of the hidden location from the detection device;
extracting an object boundary from the CCD image;
displaying an outline on the thermal image;
generating an overlapping image by matching a boundary of an object of the CCD image with an outline displayed on the thermal image and superimposing the CCD image and the thermal image; and
and determining, by a hidden camera, a hidden area in the generated superimposed image.
The method according to claim 1,
The step of extracting the boundary of the object from the CCD image,
recognizing an object in the CCD image through a first machine learning module; and,
and detecting a boundary of the object in a CCD image in which the object is recognized through a second machine learning module.
The method according to claim 1,
The step of displaying an outline on the thermal image includes:
correcting emissivity information of the thermal image;
performing an automatic level adjustment process on the corrected thermal image;
resizing the pre-processed movie image to a preset size; and
Detecting and displaying an outline in the resized thermal image.
4. The method according to claim 3,
The step of correcting the emissivity information of the thermal image,
Normalizing the brightness distribution by normalizing the emissivity of different materials in the thermal image to 1.0, the method.
4. The method according to claim 3,
The step of performing the automatic level adjustment process,
calculating a density level of each pixel with respect to the corrected thermal image, and resetting a color to the corresponding pixel according to the calculated density level.
4. The method according to claim 3,
The step of detecting and displaying the outline includes:
A method of calculating a brightness level of each pixel by grayscale processing the resized thermal image, and extracting pixels corresponding to discontinuities of the brightness level.
The method according to claim 1,
The step of generating the superimposed image includes:
and adjusting the transparency of the CCD image to overlap the CCD image.
The method according to claim 1,
The step of determining the area where the hidden camera is hidden includes:
extracting a region having the highest temperature within the boundary of the object of the generated overlapping image;
determining the extracted area as a hidden area by a hidden camera; and,
and providing an overlapping image indicating the hidden region to a user.
9. The method of claim 8,
The step of providing to the user is
Receiving image selection information from a smart device; and
According to the image selection information, the method comprising the step of providing the CCD image or the superimposed image displaying the hidden area to the smart device.
one or more processors, and
A computing device having a memory for storing one or more programs executed by the one or more processors, the computing device comprising:
a communication module for receiving a CCD image and a thermal image of the hidden location from the detection device;
a boundary detection module for extracting an object boundary from the CCD image;
an image conversion module for displaying an outline on the thermal image;
an image overlapping module that matches a boundary of an object of the CCD image with an outline displayed on the thermal image, and generates an overlapping image by overlapping the CCD image and the thermal image; and
Computing device comprising an image analysis module for determining a hidden area of the hidden camera in the generated superimposed image.
11. The method of claim 10,
The boundary detection module,
a first machine learning module for recognizing an object in the CCD image; and,
Computing device comprising a second machine learning module for detecting the boundary of the object in the CCD image in which the object is recognized.
11. The method of claim 10,
The image conversion module,
a preprocessing module for correcting emissivity information of the thermal image and performing automatic level adjustment on the corrected thermal image;
an image resizing module for resizing the pre-processed movie image to a preset size; and
Computing device comprising a region display module for detecting and displaying an outline from the resized thermal image.
13. The method of claim 12,
The preprocessing module normalizes the brightness distribution by normalizing the emissivity of different materials in the thermal image to 1.0, the computing device.
13. The method of claim 12,
The pre-processing module calculates a density level of each pixel for the corrected thermal image, and resets a color to the corresponding pixel according to the calculated density level.
13. The method of claim 12,
The area display module calculates a brightness level of each pixel by grayscale processing the resized thermal image, and extracts a pixel corresponding to a discontinuity of the brightness level.
11. The method of claim 10,
The image overlapping module, the CCD image and the overlap by adjusting the transparency of the CCD image, the computing device.
11. The method of claim 10,
The image analysis module extracts the region with the highest temperature within the boundary of the object of the generated overlapping image, determines the extracted region as the region where the hidden camera is hidden, and displays the overlapped image displaying the hidden region. A computing device provided to a user.
18. The method of claim 17,
The communication module receives the image selection information from the smart device, and provides the CCD image or the superimposed image displaying the hidden area to the smart device according to the image selection information.
a detection device including a photographing unit for photographing a hidden place to obtain a CCD image and a thermal image; and
receiving the CCD image and the thermal image from the detection device, extracting a boundary of an object from the CCD image, and displaying a contour on the thermal image, the boundary of the object of the CCD image and the contour displayed on the thermal image and an analysis server for matching and superimposing the CCD image and the thermal image to generate an overlapping image, and determining an area in which a hidden camera is hidden from the generated overlapping image.
20. The method of claim 19,
The hidden camera detection system,
The hidden camera detection system further comprising a smart device for receiving and displaying the thermal image displaying the hidden area.

Images