KR101518314B1 - Method and apparatus for video surveillance by using surveillance apparatus of unmanned aerial vehicle - Google Patents

Abstract

A video surveillance method and apparatus are disclosed. The intruder monitoring method includes a step of determining a position calculation formula based on the image information captured by the ground monitoring device, a step of calculating an intruder's location information and an intruder's characteristic information when an intruder is detected in the ground monitoring device, And transmitting the information of the intruder to the unmanned aerial surveillance apparatus.

Description

TECHNICAL FIELD [0001] The present invention relates to a video surveillance method and apparatus using an unmanned aerial surveillance apparatus,

The present invention relates to a monitoring method, and more particularly, to a video monitoring method and apparatus.

Object recognition and tracking techniques are widely applied in many fields such as image synthesis, motion capture, security surveillance, and Human Computer Interaction (HCI). Especially, as the requirements for security and surveillance in real life have been increasing recently, object recognition and tracking technology in video surveillance system has become increasingly important.

Until recently, many algorithms for object recognition and tracking have been developed. Many algorithms for object recognition and tracking include, for example, adaptive background generation and background difference techniques, area based object tracking, and shape information based object extraction techniques. However, there is still a problem in the stability of the moving object detection technique of the existing image processing system. There are also problems with power consumption, accuracy, and processing speed according to the detection process.

In object recognition, object recognition is a series of processes for locating a target object on an input image. In performing the object recognition in the image, the size, direction, position, pose, and the like of the object may appear differently in the individual images even if they are the same object. Also, there may be cases where a plurality of objects are contained in one image, or a target object is covered by another object and only a part of the object is visible. A robust object recognition method under all these conditions is a difficult problem. In the meantime, many researches on object recognition technique have been carried out in image, and various approaches are actively sought now.

The technique of recognizing objects in such images can be utilized in various technical fields. For example, the technology of recognizing objects in images can be used for security in various places such as military facilities, airports, parking lots, subways, highways, discount stores, gas stations, construction sites, kindergartens, hospital transportation systems, ATMs and convenience stores. Currently, the market for video security is steadily increasing. Also, a technique of recognizing an object in an image may be used in a technique of editing an image. In order to be used in these various fields, there is a need for a technique for increasing the accuracy for recognizing an object in an image.

A first object of the present invention is to provide a video surveillance method.

A second object of the present invention is to provide a video surveillance apparatus.

According to an aspect of the present invention, there is provided an intruder monitoring method comprising: determining a position calculation formula based on image information photographed by a terrestrial monitoring device; detecting an intruder from the terrestrial surveillance device; The location information of the intruder and the feature information of the intruder, and transmitting the location information of the intruder and the feature information of the intruder to the unmanned aerial surveillance apparatus. The position calculation formula H is determined by the following equation,

≪ Equation &

Y is a global positioning system (GPS) coordinate, A is an image coordinate, the image coordinates are coordinate information calculated from an image picked up by the terrestrial monitoring apparatus, H is a relationship between the image coordinates and the GPS coordinates Lt; / RTI > The position calculation formula is an equation for calculating position information of the intruder by interpolating the position of the intruder on the basis of the reference point, and the reference point is obtained by dividing the image information based on the X coordinate and the Y coordinate Can be calculated points. The feature information of the intruder may be information that is calculated based on movement of the intruder's joint determined based on the template model, or may be information that is calculated based on the intruder's outline information. Wherein the intruder monitoring method comprises: moving to an intruder position based on position information of the intruder received by the unmanned aerial vehicle monitoring apparatus; imaging an image at a position where the unmanned aerial vehicle monitoring apparatus moves; The method comprising the steps of: calculating object feature information on a moving object in an image captured by a device; determining, based on an intruder determination formula that compares feature information of the moving object with feature information of the moving object, And determining an object as the intruder. The intruder determination formula is performed based on the following equation,

≪ Equation &

Vi is object feature information on an object moving in an image captured by the UAV, F is feature information of an intruder calculated by a ground monitoring device, i is a parameter determined based on the number of moving objects , And m may be a determined intruder among the moving objects. The unmanned aerial vehicle monitoring apparatus may further include transmitting the image information of the intruder to the ground monitoring apparatus.

According to another aspect of the present invention, there is provided an intruder monitoring apparatus including a ground monitoring apparatus, wherein the ground monitoring apparatus includes a first processor, The position calculation formula is determined based on the information, and when the intruder is detected, the position information of the intruder and the feature information of the intruder are calculated, and the position information of the intruder and the feature information of the intruder are transmitted to the unmanned aerial surveillance device . ≪ / RTI > The position calculation formula H is determined by the following equation,

≪ Equation &

Y is a global positioning system (GPS) coordinate, A is an image coordinate, the image coordinates are coordinate information calculated from an image picked up by the terrestrial monitoring apparatus, H is a relationship between the image coordinates and the GPS coordinates Lt; / RTI > The position calculation formula is an equation for calculating position information of the intruder by interpolating the position of the intruder on the basis of the reference point, and the reference point is obtained by dividing the image information based on the X coordinate and the Y coordinate Can be calculated points. The feature information of the intruder may be information that is calculated based on movement of the intruder's joint determined based on the template model, or may be information that is calculated based on the intruder's outline information. Wherein the intruder monitoring apparatus includes an unmanned aerial surveillance apparatus, the unmanned aerial vehicle monitoring apparatus includes a second processor, the second processor moves to a location of the intruder based on the received location information of the intruder, The method comprising the steps of: capturing an image at a position, calculating object feature information on an object moving in the captured image, and comparing the feature information of the moving object with feature information of the intruder, As the intruder. The intruder determination formula is performed based on the following equation,

≪ Equation &

Vi is object feature information on an object moving in an image captured by the UAV, F is feature information of an intruder calculated by a ground monitoring device, i is a parameter determined based on the number of moving objects , And m may be a determined intruder among the moving objects. The second processor may be configured to transmit image information of the intruder to the ground monitoring device.

As described above, by using the video surveillance method and apparatus according to the embodiment of the present invention, the intruder can be accurately and continuously tracked even when the camera is out of the rectangular area or the angle of view of the installed camera.

1 is a conceptual diagram illustrating a monitoring object tracking method according to an embodiment of the present invention.
2 is a conceptual diagram illustrating a position calculation formula according to an embodiment of the present invention.
3 is a conceptual diagram illustrating a position calculation formula according to an embodiment of the present invention.
4 is a conceptual diagram illustrating a method of calculating intruder feature information according to an embodiment of the present invention.
5 is a flowchart illustrating a method of searching for an intruder according to an embodiment of the present invention.
6 is a conceptual diagram illustrating a networking method of the ground monitoring device and the UAV according to the embodiment of the present invention.
7 is a conceptual diagram illustrating a video surveillance system according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Hereinafter, the same reference numerals will be used for the same constituent elements in the drawings, and redundant explanations for the same constituent elements will be omitted.

In existing surveillance system using camera, a monitoring agent is needed to detect the object to be monitored in the image captured through the surveillance camera. However, the monitoring staff may be less focused on monitoring as the monitoring time continues. As the monitoring time increases, the probability of missed monitored objects increases. In addition, when the object to be monitored is located in a rectangular area of the camera implementing the video surveillance system, or when the angle of view of the surveillance camera is removed, the object can not be traced.

Hereinafter, in the embodiment of the present invention, there is a need for a method for automatically tracking a monitored object and tracking the monitored object even when the detected object exists in a rectangular area of the camera or outside the angle of view of the camera.

1 is a conceptual diagram illustrating a monitoring object tracking method according to an embodiment of the present invention.

Referring to FIG. 1, an image monitoring apparatus for performing a monitoring object tracking method according to an exemplary embodiment of the present invention may include a ground monitoring apparatus 100 and an unmanned aerial vehicle monitoring apparatus 150. The ground surveillance apparatus 100 may include a ground surveillance camera, and the air surveillance apparatus 150 may include an air surveillance camera.

The terrestrial monitoring apparatus 100 may determine a position calculation formula for calculating positional information of an object included in the image based on the image captured using the terrestrial surveillance camera. According to an embodiment of the present invention, when it is determined that the intruder 120 appears on an image photographed by the ground surveillance camera, the ground surveillance apparatus 100 calculates the position of the intruder 120 Information can be calculated. The ground monitoring apparatus 100 can transmit the position information of the intruder 120 calculated by the unmanned aerial vehicle monitoring apparatus 150 and the unmanned aerial vehicle monitoring apparatus 150 moves to the location of the intruder 120, . ≪ / RTI > For example, the ground monitoring apparatus 100 transmits the GPS coordinates of the intruder calculated based on the location calculation formula to the unmanned aerial surveillance apparatus 150, so that the unmanned aerial surveillance apparatus 150 moves to the location of the intruder 120 . ≪ / RTI >

For example, the GPS coordinates of the intruder 120 may be obtained by the ground surveillance apparatus 100 calculating a coordinate transformation matrix based on an image and converting the image coordinates into GPS (global positioning system) coordinates based on the calculated coordinate transformation matrix Can be calculated.

GPS coordinates are one example of location information for moving the unmanned aerial vehicle monitoring device 150 to the location of the intruder 120, and other location information may be used for movement of the UAV 150.

In addition, according to the embodiment of the present invention, the terrestrial monitoring apparatus 100 can transmit the intruder's location information to the unmanned aerial surveillance apparatus 150 without changing the image information and the image captured by the intruder. The unmanned aerial vehicle monitoring apparatus 150 calculates the position of the chip particle 120 based on the position information of the intruder 120 included in the received image information and image information of the chip particle 120, It can also be moved. That is, the information about the position of the unmanned aerial vehicle monitoring device 150 may be calculated by the unmanned aerial vehicle monitoring device 150, not by the ground monitoring device 100.

In addition, when it is determined that the intruder 120 is present in the ground sensing apparatus 100, the ground monitoring apparatus 100 can calculate the characteristic information of the intruder 120. For example, the terrestrial monitoring apparatus 100 may calculate the feature information of the intruder 120 by calculating the contour information of the intruder 120, calculating feature points of the intruder 120, Can be calculated.

The location information of the intruder 120 and the feature information of the intruder 120 may be transmitted to the UAV 150. The unmanned aerial surveillance apparatus 150 can move to the location of the intruder 120 based on the coordinates of the intruder 120. The unmanned aerial vehicle monitoring apparatus 150 can calculate the characteristics of the moving object when the moving object exists in the moved position. The unmanned aerial vehicle monitoring apparatus 150 can determine whether the intruder 120 is an object among the moving objects based on the characteristic of the object directly calculated and the characteristic information of the intruder 120 received from the ground monitoring apparatus 100 have.

In another embodiment, the UAV 150 may not directly determine the object corresponding to the intruder 120, but may transmit the image information captured through the UAV 150 to the video surveillance apparatus 100 The video surveillance apparatus 100 may determine an object corresponding to the intruder and transmit the determined information to the unmanned aerial surveillance apparatus 150 again.

2 is a conceptual diagram illustrating a position calculation formula according to an embodiment of the present invention.

In Fig. 2, a method for calculating a position calculating formula for converting from image coordinates to GPS coordinates will be described.

Referring to FIG. 2, the feature point 200 is determined from the photographed image. The feature point 200 in the image may be a reference point for calculating GPS coordinates in the image. For example, the X-axis and Y-axis may be set at predetermined intervals in the photographed image, and a point where they meet can be set as the feature point 200. [ The position of the intruder 250 existing at another position of the image based on the feature point 200 can be calculated. For example, the location information of the intruder 250 can be calculated through the interpolation formula based on the four minutiae points 200. That is, the GPS position of the point corresponding to the position of the chip particle 250 can be calculated by performing interpolation based on the four feature points 200.

3 is a conceptual diagram illustrating a position calculation formula according to an embodiment of the present invention.

In Fig. 3, a method for calculating a position calculation formula for converting from image coordinates to GPS coordinates will be described.

* The position calculation formula may be a formula for calculating the positional information of the image and the GPS coordinate information of the point where the intruder to be monitored in the image can appear and calculating the relation between the two information. That is, the location information and the GPS coordinate information in the image of the feature point 300 may be calculated and the position calculation formula may be a formula for determining the relationship between the position information in the image of the feature point 300 and the GPS coordinate information. For example, the position calculation formula may be a matrix satisfying the following equation (1).

&Quot; (1) "

Here, Y may be a GPS coordinate of a minutia, A may be an image coordinate of a minutia, and H may be a position calculation formula.

Based on the calculated H, the terrestrial surveillance system can calculate the GPS position based on the position in the captured image when the intruder is present. For example, when an intruder is located at the location X 350 in the image, the GPS coordinates of the intruder can be calculated by substituting the image coordinate A of the location X 350 in the image into Equation 1 above.

The method of determining the position calculation formula disclosed in Figs. 2 and 3 can be used as one example of various methods other than those disclosed in Figs. 2 and 3 to calculate the position of the intruder.

4 is a conceptual diagram illustrating a method of calculating intruder feature information according to an embodiment of the present invention.

Referring to FIG. 4, the intruder's feature information can be calculated based on the template model of the human body. For example, based on the template model of the human body, the intruder can calculate the feature information of the intruder based on the joint position change information generated when the intruder moves.

The human template model may be a model with a large number of joints (400) and a degree of freedom (DOF) model to reflect the complex pose of a person. The position of the joint included in the template model can be changed based on the change in the position of the joint 400 occurring when the intruder moves. The feature information of the intruder can be calculated based on the joint position information of the changed template model.

The feature information of the intruder can be transmitted from the ground monitoring device to the unmanned aerial surveillance device as described above, and can be used to search for an intruder in a location where the unmanned aerial surveillance device has moved. Equation (2) below is an expression for searching intruder information in the UAV.

&Quot; (2) "

Here, Vi is the feature information of moving objects in the image acquired from the unmanned aerial surveillance system, and F may be the feature information of the intruder calculated by the ground monitoring device. In the unmanned aerial surveillance system, an object having Vi with the smallest difference can be determined as an intruder based on Equation (2), and an intruder can be searched.

5 is a flowchart illustrating a method of searching for an intruder according to an embodiment of the present invention.

Referring to FIG. 5, the ground surveillance apparatus determines a position calculation formula from photographed image information (step S500).

The position calculation formula may be, for example, an equation for performing a conversion between the image information and the position information. The position calculation formula may be a predetermined matrix, and the GPS coordinates may be calculated by multiplying the feature point by the position calculation matrix in the captured image. Alternatively, the position calculation formula can be calculated by interpolating the position of the intruder based on the reference point as a kind of interpolation function.

If the intruder is detected by the ground surveillance apparatus, the intruder's location information and intruder's feature information are calculated (step S510).

If an intruder is detected in the ground monitoring device, the ground sensing device can calculate the intruder's location information and the intruder's characteristic information. The location information of the intruder may be information based on the location and information of the intruder in the current image and the knowledge of the location calculation. The intruder's feature information can be calculated in various ways. For example, the attacker's feature information can be calculated using the template model or using the outline information.

The location information of the intruder and the feature information of the intruder are transmitted from the ground monitoring apparatus to the unmanned aerial surveillance apparatus (step S520).

Various methods can be used to transmit intruder's location information and intruder's characteristic information from the ground monitoring device to the unmanned aerial surveillance device. For example, if a service based on a mobile communication network such as 3G or LTE is available between a ground monitoring device and an unmanned aerial surveillance device, networking is performed based on the mobile communication network between the ground monitoring device and the unmanned aerial vehicle monitoring device .

6 is a conceptual diagram illustrating a networking method of the ground monitoring device and the UAV according to the embodiment of the present invention.

Referring to FIG. 6, the intruder's location information and the intruder's characteristic information generated in the terrestrial monitoring apparatus 600 may be transmitted to the unmanned aerial surveillance apparatus through the wireless LAN network. The video surveillance apparatus may be formed based on a network between a plurality of APs. For example, the ground monitoring apparatus 600 transmits the generated intruder's location information and intruder's characteristic information to the unmanned aerial observation device 660 through the first AP 620, And transmits it to the second AP 640 which covers it, and transmits it to the unmanned aerial vehicle monitoring device 660.

The unmanned aerial vehicle monitoring apparatus 660 can detect an intruder based on the received location information of the intruder and the feature information of the intruder. Information on the image of the intruder captured by the unmanned aerial vehicle monitoring apparatus 660 may be transmitted to the ground monitoring apparatus 600 through a mobile communication network such as 3G, LTE or LTE-A. For example, the unmanned aerial vehicle monitoring apparatus 660 transmits the image information of the intruder through the peripheral base station 680, and the base station 680 can transmit the received image information to the ground monitoring apparatus 600 again. The networking between the unmanned aerial vehicle monitoring apparatus 660 and the ground monitoring apparatus 660 can be implemented on a variety of networks as an example.

The unmanned aerial vehicle monitoring apparatus moves to the calculated position based on the intruder's location information (step S530).

The unmanned aerial surveillance system can be moved to the location information of the intruder transmitted by the ground monitoring device.

After the unmanned aerial vehicle monitoring apparatus moves to the calculated position based on the location information of the intruder, the information of the moving object is searched (step S540).

The information of the moving object can be determined in the UAV. It is possible to capture an image with a camera provided in the unmanned aerial vehicle and acquire information on a moving object in the captured image.

The unmanned aerial vehicle monitoring system determines whether an object corresponding to an intruder among moving objects is an object and tracks the determined object (step S550).

An object corresponding to an intruder among moving objects in an unmanned aerial surveillance system is an object corresponding to an intruder by comparing the feature information of the moving object based on the feature information received from the ground monitoring device by the unmanned aerial vehicle It can be judged.

7 is a conceptual diagram illustrating a video surveillance system according to an embodiment of the present invention.

Referring to FIG. 7, the video surveillance apparatus may include an unmanned aerial surveillance system 750 and a terrestrial surveillance system 700.

The terrestrial monitoring apparatus 700 may include an image pickup section 705, a positional information calculating section 710, an intruder's characteristic information calculating section 715, a communication section 720, and a processor 725.

The image pickup unit 705 can take a surveillance image through a camera installed on the ground.

The position information calculation unit 710 can calculate the relationship between the position information of the image and the GPS position information in the supervised image.

The position information calculation unit 710 determines a formula for position calculation from the photographed image information. The position calculation formula may be, for example, an equation for performing a conversion between the image information and the position information. The position calculation formula may be a predetermined matrix, and the GPS coordinates may be calculated by multiplying the feature point by the position calculation matrix in the captured image. Alternatively, the position calculation formula can be calculated by interpolating the position of the intruder based on the reference point as a kind of interpolation function.

The intruder's feature information calculating unit 715 can calculate the feature information on the intruder captured in the image. The feature information for the intruder may be information for identifying the intruder. For example, it may be a set of information on the feature points of the intruder calculated based on the template model, or may be information on the outline of the intruder calculated based on the outline of the intruder.

The communication unit 720 may be implemented to transmit the generated intruder's location information and intruder's characteristic information to the UAV. If the image information captured by the unmanned aerial vehicle monitoring apparatus 750 is transmitted, the communication unit 720 may be implemented to receive image information captured by the unmanned aerial vehicle monitoring apparatus 750.

The processor 725 may be implemented to control operations of the image pickup unit 705, the positional information calculation unit 710, the intruder's feature information calculation unit 715, and the communication unit 720.

The unmanned aerial vehicle monitoring apparatus 750 may include an image pickup unit 755, an intruder determination unit 760, a communication unit 765, and a processor 770. The unmanned aerial vehicle monitoring apparatus 750 can be implemented based on an unattended camera installed on an unmanned airplane.

The image capturing unit 755 can capture a surveillance image through a camera installed in the unmanned aerial observation device 750.

The intruder determination unit 760 can determine whether an intruder is an object in the object included in the image photographed by the image pickup unit 755. [ The intruder determination unit 760 can determine the intruder by comparing the feature information of the object obtained by the UAV 750 with the feature information of the intruder.

The communication unit 765 can receive the location information of the intruder and the feature information of the intruder from the terrestrial aviation monitoring apparatus 700. [ The unmanned aerial vehicle sensing apparatus 750 can move to the location of the intruder based on the received location information of the intruder. In addition, the unmanned aerial vehicle monitoring apparatus 750 acquires feature information of the intruder, and the intruder determining unit 760 can perform intruder monitoring based on the acquired information. If the ground surveillance apparatus 700 requires image information captured by the unmanned aerial surveillance apparatus 750, the communication section 765 can transmit the captured image information to the ground surveillance apparatus 700.

The processor 770 may be implemented to control operations of the image pickup unit 755, the intruder determination unit 760, and the communication unit 765. [

It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined in the appended claims. It will be possible.

Claims (14)

In the intruder monitoring method,
Determining a position calculation formula based on image information photographed by the ground monitoring device;
Calculating a location information of the intruder and the feature information of the intruder when the intruder is detected in the terrestrial monitoring apparatus; And
And transmitting the location information of the intruder and the feature information of the intruder to the UAV,
The position calculation formula (H) is determined by the following equation,
≪ Equation &

Y is a global positioning system (GPS) coordinate, A is an image coordinate,
Wherein the image coordinates are coordinate information calculated from an image captured by the terrestrial monitoring device,
And H is a position calculation matrix indicating a relationship between the image coordinates and the GPS coordinates. delete The method of claim 1, wherein the position calculation formula
Wherein the position information of the intruder is calculated by interpolating a position of the intruder on the basis of a reference point,
Wherein the reference point is a point calculated by dividing the image information based on an X coordinate and a Y coordinate. The method according to claim 1,
Wherein the information is calculated based on movement of the intruder's joint determined based on a template model or information calculated based on contour information of the intruder. The method according to claim 1,
Moving to a location of the intruder based on position information of the intruder received by the unmanned aerial vehicle monitoring device;
Capturing an image at a position where the unmanned aerial vehicle monitoring apparatus moves;
Calculating object feature information on a moving object in the image captured by the unmanned aerial vehicle monitoring apparatus;
Further comprising determining the one of the moving objects as the intruder based on an intruder determination formula for comparing the characteristic information of the moving object with the characteristic information of the intruder. The method according to claim 5,
Is performed based on the following equation,
≪ Equation &

Vi is object feature information on an object moving in an image captured by the UAV, F is feature information of an intruder calculated by a ground monitoring device, i is a parameter determined based on the number of moving objects And m is a determined intruder among the moving objects. 6. The method of claim 5,
Wherein the unmanned aerial surveillance apparatus further comprises transmitting image information of the intruder to the ground monitoring apparatus. An intruder monitoring apparatus, wherein the intruder monitoring apparatus includes a ground monitoring apparatus, the ground monitoring apparatus includes a first processor,
Wherein the first processor determines a position calculation formula based on the photographed image information, calculates the position information of the intruder and the feature information of the intruder when the intruder is detected, and calculates the position information of the intruder based on the position information of the intruder, Information to the unmanned aerial surveillance device,
The position calculation formula H is determined by the following equation,
≪ Equation &

Y is a global positioning system (GPS) coordinate, A is an image coordinate,
Wherein the image coordinates are coordinate information calculated from an image captured by the terrestrial monitoring device,
And H is a position calculation matrix indicating a relationship between the image coordinates and the GPS coordinates . delete 9. The method according to claim 8, wherein the position calculation formula
Wherein the position information of the intruder is calculated by interpolating a position of the intruder on the basis of a reference point,
Wherein the reference point is a point calculated by dividing the image information based on an X coordinate and a Y coordinate. The method according to claim 8,
Wherein the information is calculated based on movement of the intruder's joint determined based on a template model or information calculated based on contour information of the intruder. 9. The system of claim 8, wherein the intruder monitoring device comprises an unmanned aerial surveillance device, the unmanned aerial surveillance device includes a second processor,
The second processor moves to the intruder's location based on the received location information of the intruder, captures an image at the moved location, calculates object feature information on the moving object in the captured image, And determining one of the moving objects as the intruder based on the intruder determination formula comparing feature information of the intruder with feature information of the intruder. 13. The method of claim 12,
Is performed based on the following equation,
≪ Equation &

Vi is object feature information on an object moving in an image captured by the UAV, F is feature information of an intruder calculated by a ground monitoring device, i is a parameter determined based on the number of moving objects And m is a determined intruder among the moving objects. 13. The apparatus of claim 12,
And transmits the image information obtained by imaging the intruder to the ground monitoring device.

Images