KR102269098B1 - INTRUSION DETECTION DEVICE THAT DETECTS INTRUSIONS THROUGH MULTIPLE LiDAR SENSORS INSTALLED IN A SECURE AREA AND OPERATING METHOD THEREOF - Google Patents

Abstract

Disclosed are an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area, and an operating method thereof. The present invention provides an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area and an operation method thereof, so that the user recognizes that the object, which is an intrusion detection target, exists, and a warning message for notifying the intrusion state can be displayed to help maintain security.

Description

An intrusion detection device that detects an intrusion through a plurality of lidar sensors installed in a security area and an operation method thereof

The present invention relates to an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area, and an operating method thereof.

LiDAR detects changes in the time, intensity, frequency, etc. of the time, intensity, and frequency of the light being reflected from the surrounding target after emitting a laser beam, and measuring the distance to the object so that you can know the surroundings. technology and its devices.

These lidars can measure not only the distance to the target, but also the moving speed, direction, and temperature, so they can be used in a variety of fields, such as weather observation, precise terrain observation, landing guidance of aircraft, recognition of the surroundings of autonomous vehicles, and analysis of surrounding atmospheric substances. can be utilized.

Meanwhile, people are paying attention to checking and reinforcing security as crimes caused by intrusion into homes become an issue and cases where important technology inside the company is leaked frequently occur.

Conventionally, the lidar sensor is mainly used to assist the driver by detecting the traffic environment around the driving vehicle. If such a lidar sensor is used to detect an intrusion from the outside within the security area, the object that is the target of intrusion detection It will be able to detect intrusions more precisely and efficiently detect intrusions by utilizing the advantages of the lidar sensor that can collect 3D image information including distance information.

Specifically, it can be used to prevent crimes caused by intrusion into homes or to prevent the leakage of important technologies inside the company by intruders, and it can be used for the purpose of monitoring external intruders by installing it in a security area such as an industrial site. It can contribute to strengthening.

Therefore, it is necessary to study a technique for detecting an intrusion through a plurality of lidar sensors installed in a security area.

The present invention provides an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area and an operation method thereof, so that the user recognizes that the object, which is an intrusion detection target, exists, and a warning message for notifying the intrusion state We want to support you to maintain security by displaying

An intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention is through n (n is a natural number of 2 or more) LiDAR sensors installed at different points in the security area. By radiating a laser beam in a preset direction, a separation distance measuring unit that measures the separation distance between the n lidar sensors and an object that is an intrusion detection target, the separation distance measured by each of the n lidar sensors in one column A matrix generator for generating a 1 x n first matrix by allocating as components constituting , 1 x n by calculating the Hadamard product between the 1 x n first matrix and a predetermined 1 x n weight matrix. A feature vector generator for generating a weighting matrix and generating an n-dimensional feature vector including values constituting the 1 x n weighting matrix as each component, wherein the n-dimensional feature vector and the object exist A vector similarity calculator that calculates a vector similarity between a preset n-dimensional reference vector for indicating a state, compares the vector similarity with a predetermined threshold value, and when it is confirmed that the vector similarity exceeds the threshold value, the object is determined to exist, and when it is confirmed that the vector similarity is less than or equal to the threshold value, a determination unit that determines that the object does not exist, and a determination unit that determines that the object exists by the determination unit, notifies an intrusion state and a warning message display unit for displaying a warning message for the screen.

In addition, the operation method of the intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in the security zone according to an embodiment of the present invention is a laser in a preset direction through n lidar sensors installed at different points in the security zone. Measuring the separation distance between the n lidar sensors and the object that is the intrusion detection target by radiating a light beam, assigning the separation distance measured by each of the n lidar sensors as a component constituting one column 1 generating a first matrix of xn, generating a weighting matrix of 1 xn by calculating a Hadamard product between the first matrix of 1 xn and a weighting matrix of predetermined 1 xn, and generating the weighting matrix of 1 xn generating an n-dimensional characteristic vector including constituent values as each component, calculating a vector similarity between the n-dimensional characteristic vector and a preset n-dimensional reference vector for indicating that an object exists comparing the vector similarity with a predetermined threshold value, and if it is determined that the vector similarity exceeds the threshold value, it is determined that the object exists, and if it is confirmed that the vector similarity is less than or equal to the threshold value, and determining that the object does not exist, and when it is determined that the object exists by the determining step, displaying a warning message for informing that the object is in an intrusion state on the screen.

The present invention provides an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area and an operation method thereof, so that the user recognizes that the object, which is an intrusion detection target, exists, and a warning message for notifying the intrusion state can be displayed to help maintain security.

1 is a diagram illustrating the structure of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention.
2 is a flowchart illustrating an operating method of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. These descriptions are not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, like reference numerals are used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, refer to those of ordinary skill in the art to which the present invention belongs. It has the same meaning as is commonly understood by those who have it.

In this document, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, in various embodiments of the present invention, each of the components, functional blocks or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic. A circuit, an integrated circuit, an ASIC (Application Specific Integrated Circuit), etc. may be implemented with various well-known devices or mechanical elements, and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks in the accompanying block diagram or steps in the flowchart are computer program instructions that are loaded in a processor or memory of equipment capable of data processing, such as a general-purpose computer, a special-purpose computer, a portable notebook computer, and a network computer, and perform specified functions. can be interpreted as meaning Since these computer program instructions may be stored in a memory provided in a computer device or in a memory readable by a computer, the functions described in the blocks of the block diagrams or the steps of the flowcharts are produced as articles of manufacture containing instruction means for performing the same. could be In addition, each block or each step may represent a module, segment, or portion of code comprising one or more executable instructions for executing the specified logical function(s). It should also be noted that, in some alternative embodiments, it is also possible for the functions recited in blocks or steps to be executed out of the prescribed order. For example, two blocks or steps shown one after another may be performed substantially simultaneously or in the reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram illustrating the structure of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention.

Referring to FIG. 1 , the intrusion detection device 110 for detecting intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention includes a separation distance measurement unit 111 , a matrix generation unit 112 , It includes a feature vector generating unit 113 , a vector similarity calculating unit 114 , a determining unit 115 , and a warning message display unit 116 .

The separation distance measurement unit 111 emits a laser beam in a preset direction through n (n is a natural number of 2 or more) LiDAR sensors installed at different points in the security area, and intrudes with the n LiDAR sensors. Measure the separation distance between the objects to be detected.

Here, the lidar refers to a technique for measuring the distance to the target by using a laser beam of a very short wavelength, and the separation distance measuring unit 111 emits a laser beam in a preset direction through the lidar sensor, and then invades The separation distance between the lidar sensor and the object may be measured by measuring the return time of the laser beam reflected back to the object to be detected. In addition, as the number of lidar sensors increases, an object can be detected more precisely.

Specifically, if there is an object that is an intrusion detection target, the return time of the laser beam reflected back to the object is relatively short, so the distance between the lidar sensor and the object will be measured short. If the object does not exist, the laser beam will go into the air. Since this will be emitted, the return time to return will be long, and the distance between the lidar sensor and the object will be measured long.

The matrix generator 112 generates a 1 x n first matrix by allocating the separation distance measured by each of the n lidar sensors as components constituting one column.

For example, if it is assumed that n is '3' and the separation distances measured by the three lidar sensors are '20', '10', and '30', respectively, the matrix generator 112 is '20', By allocating '10' and '30' as components constituting one column, '[20 10 30]', which is a 1 x 3 matrix, can be created.

The feature vector generator 113 generates a 1 x n weight calculation matrix by calculating a Hadamard product between the 1 x n first matrix and a predetermined 1 x n weight matrix, and the 1 x n weights. An n-dimensional feature vector including values constituting an operation matrix as each component is generated.

Here, the Hadamard product means an operation of multiplying each component in a matrix or vector of the same size. When there are two matrices '[abc]' and '[xyz]', the Hadamard product between the two matrices is calculated. A matrix can be expressed as '[ax by cz]'.

In this case, according to an embodiment of the present invention, n weight components included in the weight matrix may have values greater than 0 and less than 1, and the total sum of the n weight components may be 1.

For example, according to the example described above, 'n=3', the 1 x n first matrix is '[20 10 30]', and the 1 x n weight matrix is '[0.4 0.2 0.4]' in advance by the developer. Let's assume it's fixed. Then, the feature vector generator 113 calculates the Hadamard product between '[20 10 30]', which is a matrix of 1 x 3, and '[0.4 0.2 0.4]', which is a weight matrix of 1 x 3, so that the weight of 1 x 3 is '[8 2 12]', which is an operation matrix, can be generated, and '8', '2', and '12', which are values constituting the 1 x 3 weight operation matrix, '[8 2 12]', are each (8, 2, 12), which is a three-dimensional feature vector including components

The vector similarity calculating unit 114 calculates a vector similarity between the n-dimensional characteristic vector and a preset n-dimensional reference vector for indicating that an object exists.

In this case, according to an embodiment of the present invention, the calculation of the vector similarity between the n-dimensional feature vector and the n-dimensional reference vector may be performed according to Equation 1 below.

Here, M denotes the vector similarity between two vectors, C denotes the cosine similarity between the two vectors, D denotes the Euclidean distance between the two vectors, and the cosine similarity C between the two vectors is According to Equation 2, the Euclidean distance D between the two vectors may be calculated according to Equation 3 below.

where C is the cosine similarity between vectors A and B, A _i is the i-th component of the vector A, B _i is the i-th component of the vector B, and the cosine similarity C has a value between -1 and 1 The larger the value, the more similar vectors are.

In Equation 3, D denotes a Euclidean distance, and pi and qi denote i-th components included in the two vectors. As the Euclidean distance between two vectors is small, the two vectors can be regarded as similar vectors, and as the Euclidean distance between two vectors increases, the two vectors can be regarded as dissimilar vectors.

Accordingly, as the vector similarity between the n-dimensional characteristic vector and the n-dimensional reference vector increases, the n-dimensional characteristic vector can be regarded as a vector similar to the n-dimensional reference vector. The feature vector may be regarded as a vector similar to the n-dimensional reference vector.

For example, when 'n = 3' and a preset three-dimensional reference vector for indicating that the object is in a state of being present is (d1, d2, d3), the vector similarity calculating unit 114 is the The vector similarity between (8, 2, 12), which is a three-dimensional feature vector, and (d1, d2, d3), which is the three-dimensional reference vector, can be calculated according to Equation 1 above.

Thereafter, the determination unit 115 compares the vector similarity with a predetermined threshold value, and when it is determined that the vector similarity exceeds the threshold value, it is determined that the object exists, and the vector similarity is the threshold value. If it is confirmed as follows, it is determined that the object does not exist.

When it is determined by the determination unit 115 that the object exists, the warning message display unit 116 displays a warning message for informing that the object is in an intrusion state on the screen.

At this time, according to an embodiment of the present invention, the warning message display unit 116 classifies the dangerous state according to the degree of proximity of the object and displays the warning message differently, the warning level table maintaining unit 117 and the warning level checking unit 118 and a warning message display processing unit 119 may be included.

The warning grade table maintaining unit 117 includes a plurality of different warning grades and a range value in which an upper limit value and a lower limit value for a predetermined different vector similarity corresponding to each of the plurality of warning grades are specified. Save and maintain a warning level table.

For example, information may be recorded in the warning level table as shown in Table 1 below.

Multiple warning levels Range Values for Vector Similarity caution 1 to 1.3 boundary 1.3 to 1.7 danger 1.7 ~

When it is determined by the determination unit 115 that the object exists, the warning level check unit 118 is a first warning recorded in correspondence with the value of the vector similarity range to which the vector similarity belongs from the warning level table. Check the grade.

In this way, when the first warning level is confirmed, the warning message display processing unit 119 displays a warning message for informing that the intrusion state is according to the first warning level on the screen.

For example, if the vector similarity calculated by the vector similarity calculating unit 114 is '1.6', the warning level checking unit 118 includes the vector similarity of '1.6' from the warning level table as shown in Table 1 above. You can check the warning level of 'boundary' recorded corresponding to the range value of '1.3 ~ 1.7'.

When the warning grade of 'alert' is confirmed by the warning grade check unit 118, the warning message display processing unit 119 may display a warning message on the screen to inform that it is an intrusion state according to the warning grade of 'alert'. .

That is, the intrusion detection apparatus 110 according to the present invention generates warning messages according to different warning levels according to the vector similarity between the n-dimensional characteristic vector and the n-dimensional reference vector for indicating that an object exists. By displaying on the screen, it is possible to support the user to recognize how close the current object is.

In addition, according to an embodiment of the present invention, the intrusion detection apparatus 110 may further include a location information storage unit 120, a sensor check unit 121 and an image display unit 122.

The location information storage unit 120 may store location information of the n lidar sensors within the security area and location information on a plurality of cameras pre-installed in the security area.

The sensor check unit 121 compares the n-dimensional characteristic vector and the n-dimensional reference vector with components existing at positions corresponding to each other, and the magnitude of the components constituting the n-dimensional characteristic vector is determined to be the same as the n-dimensional characteristic vector. A first component that is equal to or smaller than the size of a component existing at a corresponding position in the n-dimensional reference vector is extracted, and the first lidar sensor corresponding to the first component is identified.

When the first lidar sensor is confirmed, the image display unit 122 is located within a preset distance from the position of the first lidar sensor with reference to the position information storage unit among the plurality of cameras installed in advance in the security area. It connects to the first camera confirmed to be the first camera, receives real-time image information from the first camera, and displays a real-time image according to the image information on the screen.

For example, as described above, when it is assumed that 'n=3', the three-dimensional characteristic vector is (8, 2, 12), and the three-dimensional reference vector is (d1, d2, d3), sensor confirmation The unit 121 may compare '8' and 'd1', '2' and 'd2', and '12' and 'd3' in order to compare the components present at positions corresponding to each other, respectively. At this time, the sensor identification unit 121 determines that the size of the components 'd1', 'd2', and 'd3' among '8', '2', and '12' is the same as or smaller than the size of the components at positions corresponding to each other. Component 1' can be extracted, and 'Lidar Sensor 1' corresponding to 'Component 1' can be identified.

When the 'lidar sensor 1' is confirmed by the sensor confirmation unit 121 in this way, the image display unit 122 refers to the location information storage unit 120 among the plurality of cameras installed in the security area in advance. Access to 'camera 1', which is confirmed to be located within a preset distance from the position of 'rider sensor 1', receives real-time image information from 'camera 1', and displays a real-time image according to the image information on the screen can do.

That is, the intrusion detection apparatus 110 according to the present invention compares the n-dimensional characteristic vector and the n-dimensional reference vector among components, and when it is determined that the object is in a dangerous state due to the existence of the object, By displaying a real-time image on the screen, it is possible to support the quick response of the user to the intrusion of the object.

2 is a flowchart illustrating an operating method of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention.

In step S210, a laser beam is radiated in a preset direction through n lidar sensors installed at different points in the security area, thereby measuring the separation distance between the n lidar sensors and an object that is an intrusion detection target.

In step S220, a first matrix of 1 x n is generated by allocating the separation distance measured by each of the n lidar sensors as components constituting one column.

In step S230, a 1 x n weight calculation matrix is generated by calculating the Hadamard product between the 1 x n first matrix and a predetermined 1 x n weight matrix, and values constituting the 1 x n weight calculation matrix are calculated for each Generates an n-dimensional feature vector including components.

In step S240, the vector similarity between the n-dimensional characteristic vector and a preset n-dimensional reference vector for indicating that the object exists is calculated.

In step S250, the vector similarity is compared with a predetermined threshold value, and when it is confirmed that the vector similarity exceeds the threshold value, it is determined that the object exists, and it is confirmed that the vector similarity is less than or equal to the threshold value If so, it is determined that the object does not exist.

In step S260, if it is determined that the object exists by step S250, a warning message for informing that the object is in an intrusion state is displayed on the screen.

In this case, according to an embodiment of the present invention, n weight components included in the weight matrix may have values greater than 0 and less than 1, and the total sum of the n weight components may be 1.

In addition, according to an embodiment of the present invention, the calculation of the vector similarity between the n-dimensional feature vector and the n-dimensional reference vector may be performed according to Equation 1 above.

In addition, according to an embodiment of the present invention, in step S260, a plurality of different warning grades and an upper limit value and a lower limit value for different predetermined vector similarity values corresponding to each of the plurality of warning grades are set. Storing and maintaining a warning grade table in which a designated range value is recorded, if it is determined that an object exists by step S250, from the warning grade table to the value of the vector similarity range to which the vector similarity belongs Checking the correspondingly recorded first warning level, and when the first warning level is confirmed, the step of displaying a warning message for notifying the intrusion state according to the first warning level on the screen.

In addition, according to an embodiment of the present invention, the operating method of the intrusion detection device includes location information of the n lidar sensors within the security area and location information on a plurality of cameras pre-installed in the security area. maintaining a location information storage unit in which is stored, by comparing the n-dimensional characteristic vector and the n-dimensional reference vector with components existing at positions corresponding to each other, respectively, components constituting the n-dimensional characteristic vector extracting a first component whose size is equal to or smaller than the size of a component existing at a corresponding position in the n-dimensional reference vector, and identifying a first lidar sensor corresponding to the first component, and the second 1 When the lidar sensor is confirmed, the first camera that is confirmed to be located within a preset distance from the position of the first lidar sensor with reference to the location information storage unit among the plurality of cameras installed in advance in the security area is connected The method may further include receiving real-time image information from the first camera and displaying a real-time image according to the image information on a screen.

Above, the operating method of the intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in the security area according to an embodiment of the present invention has been described with reference to FIG. 2 . Here, the operation method of the intrusion detection device for detecting intrusion through a plurality of lidar sensors installed in the security area according to an embodiment of the present invention detects an intrusion through a plurality of lidar sensors installed in the security area described with reference to FIG. Since it may correspond to the configuration of the operation of the intrusion detection device 110, a more detailed description thereof will be omitted.

The operating method of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through combination with a computer.

In addition, the operating method of the intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in the security area according to an embodiment of the present invention is implemented in the form of a computer program command for execution through combination with a computer, computer readable may be recorded on the medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and carry out program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions 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.

As described above, the present invention has been described with specific matters such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , various modifications and variations are possible from these descriptions by those of ordinary skill in the art to which the present invention pertains.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and not only the claims to be described later, but also all those with equivalent or equivalent modifications to the claims will be said to belong to the scope of the spirit of the present invention. .

110: an intrusion detection device that detects an intrusion through a plurality of lidar sensors installed in the security area
111: separation distance measuring unit 112: matrix generating unit
113: feature vector generating unit 114: vector similarity calculating unit
115: determination unit 116: warning message display unit
117: warning level table holding unit 118: warning level confirmation unit
119: warning message display processing unit 120: location information storage unit
121: sensor confirmation unit 122: image display unit

Claims (12)

The location information of n (n is a natural number greater than or equal to 2) LiDAR sensors installed at different points in the security zone within the security zone and location information about a plurality of cameras pre-installed in the security zone are stored. a location information storage unit 120;
a separation distance measuring unit 111 for measuring a separation distance between the n lidar sensors and an object to be intrusion detection by emitting a laser beam in a preset direction through the n lidar sensors;
a matrix generator 112 for generating a 1 x n first matrix by allocating the separation distance measured by each of the n lidar sensors as components constituting one column;
A 1 x n weighting matrix is generated by calculating a Hadamard product between the 1 x n first matrix and a predetermined 1 x n weight matrix, and values constituting the 1 x n weighting matrix are calculated for each a feature vector generating unit 113 that generates an n-dimensional feature vector included as a component;
a vector similarity calculating unit 114 for calculating a vector similarity between the n-dimensional characteristic vector and a preset n-dimensional reference vector for indicating that an object exists;
By comparing the vector similarity with a predetermined threshold, if it is determined that the vector similarity exceeds the threshold, it is determined that the object exists. If it is determined that the vector similarity is less than or equal to the threshold, the object exists. a determination unit 115 that determines that it is not being performed;
a warning message display unit 116 for displaying a warning message for informing that the object is in an intrusion state on the screen when it is determined by the determination unit 115 that the object exists;
The n-dimensional characteristic vector and the n-dimensional reference vector are compared with each other, and components present at corresponding positions are compared, and the magnitude of the components constituting the n-dimensional characteristic vector is determined in the n-dimensional reference vector. a sensor confirmation unit 121 for extracting a first component equal to or smaller than the size of the component present at the corresponding position, and confirming the first lidar sensor corresponding to the first component; and
When the first lidar sensor is confirmed, it is confirmed that it is located within a preset distance from the position of the first lidar sensor with reference to the location information storage unit 120 among the plurality of cameras installed in advance in the security area An image display unit 122 that connects to a first camera to receive real-time image information from the first camera, and displays a real-time image according to the image information on a screen
including,
The warning message display unit 116 is
A warning for storing and maintaining a warning level table in which a plurality of predetermined different warning grades and a range value in which an upper limit value and a lower limit value for a predetermined different vector similarity corresponding to each of the plurality of warning grades are recorded are recorded rating table holding unit 117;
When it is determined by the determination unit 115 that the object exists, a warning level check for checking a first warning level recorded in correspondence to a range value of the vector similarity to which the vector similarity belongs from the warning level table part 118; and
When the first warning level is confirmed, a warning message display processing unit 119 for displaying a warning message for informing that the intrusion state is in accordance with the first warning level on the screen
An intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area comprising a. According to claim 1,
An intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area where the n weight components included in the weight matrix are configured with values greater than 0 and less than 1, and the sum of the n weight components is 1. According to claim 1,
An intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area, wherein the calculation of the vector similarity between the n-dimensional characteristic vector and the n-dimensional reference vector is performed according to Equation 1 below.
[Equation 1]

Here, M is the vector similarity between two vectors, C is the cosine similarity between the two vectors, and D is the Euclidean distance between the two vectors. delete delete The location information of n (n is a natural number greater than or equal to 2) LiDAR sensors installed at different points in the security zone within the security zone and location information about a plurality of cameras pre-installed in the security zone are stored. maintaining a location information storage unit;
measuring a separation distance between the n lidar sensors and an object that is an intrusion detection target by radiating a laser beam in a preset direction through the n lidar sensors;
generating a 1 x n first matrix by allocating the separation distance measured by each of the n lidar sensors as components constituting one column;
A 1 x n weighting matrix is generated by calculating a Hadamard product between the 1 x n first matrix and a predetermined 1 x n weighting matrix, and values constituting the 1 x n weighting matrix are calculated for each generating an n-dimensional feature vector including as a component;
calculating a vector similarity between the n-dimensional characteristic vector and a preset n-dimensional reference vector for indicating that an object exists;
By comparing the vector similarity with a predetermined threshold, if it is determined that the vector similarity exceeds the threshold, it is determined that the object exists. If it is determined that the vector similarity is less than or equal to the threshold, the object exists. determining that it is not;
When it is determined that the object exists by the determining step, displaying a warning message for informing that the intrusion state is on the screen;
The n-dimensional characteristic vector and the n-dimensional reference vector are compared with each other, and components present at corresponding positions are compared, and the magnitude of the components constituting the n-dimensional characteristic vector is determined in the n-dimensional reference vector. extracting a first component equal to or smaller than the size of the component present at the corresponding position, and identifying a first lidar sensor corresponding to the first component; and
When the first lidar sensor is confirmed, the first camera that is confirmed to be located within a preset distance from the position of the first lidar sensor with reference to the location information storage unit among the plurality of cameras installed in advance in the security area receiving real-time image information from the first camera by accessing the , and displaying a real-time image according to the image information on a screen.
including,
The step of displaying the warning message on the screen is
Storing and maintaining a warning grade table in which a plurality of different predetermined warning grades and a range value in which an upper limit value and a lower limit value for a predetermined different vector similarity corresponding to each of the plurality of warning grades are recorded are recorded; ;
when it is determined that the object exists by the judging step, checking a first warning grade recorded in correspondence with a range value of the vector similarity to which the vector similarity belongs from the warning grade table; and
If the first warning level is confirmed, displaying a warning message on the screen to inform that the intrusion state according to the first warning level
An operating method of an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area comprising a. 7. The method of claim 6,
The n weight components included in the weight matrix are composed of values greater than 0 and less than 1, and the total sum of the n weight components is 1 of an intrusion detection device that detects an intrusion through a plurality of lidar sensors installed in a security area. how it works. 7. The method of claim 6,
Calculation of the vector similarity between the n-dimensional characteristic vector and the n-dimensional reference vector is performed according to Equation 1 below. A method of operating an intrusion detection device for detecting an intrusion through a plurality of lidar sensors installed in a security area.
[Equation 1]

Here, M is the vector similarity between two vectors, C is the cosine similarity between the two vectors, and D is the Euclidean distance between the two vectors. delete delete A computer-readable recording medium recording a computer program for executing the method of any one of claims 6 to 8 through combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 6 to 8 through combination with a computer.

Images