KR101910033B1 - Method tracking and monitoring object - Google Patents

Abstract

According to an embodiment of the present invention, a method of tracing and monitoring an object comprises the steps of: storing interested objects pre-selected from images in which a specific event has occurred among images transmitted through a plurality of cameras; detecting a target object from the images photographed in real time through the camera; extracting a second object factor for each region that is a feature of the interested objects when extracting a first object factor for each region that is a feature of any one of the interested object; counting the second object factors to select the second object factor with the highest number as a risk factor, deriving similarity for each region of the risk factors and the first object factors by using a predetermined similarity table, and deriving an applied weight for each region when the first object factor and the risk factor are determined to be the same as each other; calculating a risk of the target object by summing, by each region, the multiplication of the similarity and the weight; and operating the camera to track the target object according to a predetermined scenario corresponding to the calculated risk. The present invention is able to track only a target object such as an intruder or an enemy by operating a camera according to a preset scenario corresponding to a risk.

Description

{METHOD TRACKING AND MONITORING OBJECT}

More particularly, the present invention relates to a method of tracking and monitoring an object, and more particularly, to a method and apparatus for calculating a risk of a target object to be detected in real time and operating a camera according to a predetermined scenario according to the risk, And how to track objects.

Traditionally, military facilities such as aerodromes, ammunition, communication facilities, GOPs, command centers, etc. are installed in main facilities of military or military facilities in order to prepare for enemy invasion and infiltration, However, due to the recent development of information and communication technology, the surveillance camera system has been introduced as an alternative means of military boundaries.

In addition, facilities that require a security boundary, such as a substation, should be monitored for access by persons other than those licensed and monitored for external intruders. To this end, a surveillance camera system is being built around major security facilities.

Such a surveillance camera system enables an unattended surveillance of a scene by monitoring an image captured by a plurality of cameras installed in a boundary target area by a supervisor of a central surveillance control station.

However, since the existing surveillance camera system recognizes and judges the situation on the basis of the scene image coming from the camera installed in the boundary area, the surveillance manager at the central surveillance control station judges the situation according to the proficiency of the surveillance manager of the central surveillance station There may be errors in recognition and judgment.

In other words, such a surveillance camera system can not achieve homogeneity in monitoring and boundary quality of major security facilities or military garrisons, making systematic and rational response difficult in situations.

In addition, the existing surveillance camera system can prevent the enemy army from moving to the main facility by intruding or infiltrating the border area of the army, for example, iron fence or fence, There is a problem that the direction of the enemy army can not be traced.

Accordingly, in the present invention, when the surveillance manager at the central surveillance control station does not monitor, when the enemy forces intrudes into or penetrates into the border area of the military, it can be automatically tracked and photographed, And a system and method for including the same.

An object of the present invention is to provide an image processing apparatus and method capable of calculating a risk level for a target object to be detected in real time and tracking the target object only for the intruder or enemy target object by operating a camera according to a predetermined scenario according to the risk The object of the present invention is to provide a method for tracking and monitoring an object.

It is another object of the present invention to provide a surveillance system and a surveillance system capable of detecting a risk of a target object based on similarities between target factors and risk factors of a target object located in a surveillance zone, The object of the present invention is to effectively distinguish and identify an intruding intruder or enemy target object and to drive the cameras to track the intruder or enemy target object.

The problems to be solved by the present invention are not limited to the above-mentioned task (s), and another task (s) not mentioned is to be clearly understood to those skilled in the art to which the present invention belongs It can be understood.

According to another aspect of the present invention, there is provided a method for tracking and monitoring an object, the method comprising: Detecting one of the target objects from the images photographed in real time through the cameras, extracting a first object factor for each feature of the target object, Calculating a second target factor for each region by counting the second target factor, selecting a second target factor that is the highest for each region as a risk factor, and using the preset similarity table, And the degree of similarity of each of the first subject factors and the first subject factors, and when the first subject factor and the risk factors are determined to be equal to each other Calculating a risk of the target object by summing the product of the similarity and the weight by the site, and calculating the risk of the target object by operating the camera to track the target object according to the predetermined scenario according to the calculated risk. The method comprising the steps of:

According to an example of the present invention, the calculating step may be performed through an equation (1) for the risk of the target object,

(1) 이고, 이때, n은 상기 부위의 개수, k는 상기 부위별 기설정된 상수, A는 상기 제1 대상인자와 상기 위험인자와의 공통점에 따른 유사도, B는 상기 부위별 인자들이 동일할 때 적용되는 가중치인 것을 특징으로 한다. The calculation equation

(1) where n is the number of sites, k is a predetermined constant for each site, A is the similarity between the first object factor and the risk factor, B is the site-specific factor Is a weight that is applied when

According to another aspect of the present invention, there is provided a method for estimating a position of a target object, the method comprising: a first estimation step of estimating a position of the target object based on preset coordinate information for each of regions divided from an image captured in real- And a second estimating step of estimating a moving speed and a direction angle of the target object moving for a predetermined time from a first position to a second position of the target object to be estimated.

According to an example of the present invention, the second estimating step may include a step of estimating a movement path along the direction angle by operating one of the plurality of cameras disposed within a predetermined distance along the movement path And updating the scenario.

According to an example of the present invention, the second estimating step may include: a control signal for tracking the target object based on a position of an imaging region of the camera, a first position of the target object, And the scenario is updated to operate the one of the cameras according to the transmission time and the delay time.

A method for tracking and monitoring an object related to at least one embodiment of the present invention configured as described above includes the steps of calculating a risk level for a target object detected in real time and operating the camera according to a predetermined scenario according to the risk level, It has the effect of allowing only intruders or enemy target objects to be tracked.

In addition, since the risk of the target object is determined based on the degree of similarity between the target factors and the risk factors of the target object located in the surveillance zone, it is possible to prevent the intruder or the enemy It is possible to effectively distinguish and identify the target object.

1 is an object tracking and monitoring system according to an embodiment of the present invention.
2 is a configuration diagram of an object tracking and monitoring server according to an embodiment of the present invention.
3 is an operation process of the object tracking monitoring server according to one embodiment.
4 is an object tracking and monitoring system according to another embodiment of the present invention.

Hereinafter, a method of tracking and monitoring objects related to the present invention will be described in more detail with reference to the drawings. The suffix "module" and " part "for the components used in the following description are given or mixed in consideration of ease of specification, and do not have their own meaning or role. In the present specification, the same or similar reference numerals are given to different embodiments in the same or similar configurations. As used herein, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise.

It is to be understood that the drawings herein illustrate conceptual aspects of exemplary circuits embodying the principles of the invention. That is, it should be understood that the functions shown in the figures may be substantially represented on a computer-readable medium and performed by various processes performed by the computer or processor, whether or not the computer or processor is explicitly shown.

And, each function can be provided not only with dedicated hardware, but also with the use of hardware capable of executing software in connection with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared.

In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is an object tracking and monitoring system according to an embodiment of the present invention.

Referring to FIG. 1, the object tracking and monitoring system 1000 may include a plurality of cameras 10-1 to 10-N and an object tracking and monitoring server 100.

Here, the cameras 10-1 to 10-N are composed of two types of cameras, namely, a fixed camera and a PTZ camera. In addition, the cameras 10-1 to 10-N include a video display, a pan / tilt / zoom function And may include any and all of the equipment for. More specifically, the fixed type camera displays various types of images such as a general camera, a dome camera, an infrared camera, a laser camera, a thermal camera, and the like, and has a general angle of view (about 80 degrees) And the PTZ camera has a pan / tilt / zoom function, and a driving device for the PTZ camera can be provided.

The cameras 10-1 to 10-N may be installed in a static place such as a warehouse, or may be spaced apart from each other by a predetermined distance in a monitoring area such as a dynamic place such as a person's walking path.

Next, the object tracking and monitoring server 100 can receive images photographed from the cameras 10-1 to 10-N via the network 50. [

More specifically, the object tracking and monitoring server 100 is a wired communication system including at least one of a power line communication (PLC), a USB communication, an Ethernet, a serial communication, and an optical / Interface, a wireless LAN (WLAN), a Digital Living Network Alliance (DLNA), a Wireless Broadband (Wibro), a WiMAX, a High Speed Downlink Packet Access (HSDPA) (IEEE 802.16), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), and Wireless Broadband Mobile Broadband Service (WMBS) (Bluetooth), Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC) A short distance communication interface including at least one of Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, and Wi-Fi Direct Images taken from the cameras 10-1 to 10-N through the network 50 can be received.

In addition, the object tracking and monitoring server 100 includes a port for connecting a device equipped with a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, O port, an earphone port, and the like, and can be connected to an output device such as a display, an external storage device, a mouse, and a keyboard.

Hereinafter, the object tracking monitoring server 100 will be described in more detail with reference to FIG. 2 and FIG.

FIG. 2 is a configuration diagram of an object tracking and monitoring server according to an embodiment of the present invention, and FIG. 3 is an operation process of an object tracking and monitoring server according to an embodiment.

1 to 3, the object tracking and monitoring server 100 may include a storage unit 110, a detection unit 120, an extraction unit 130, a calculation unit 140, and an operation unit 150 .

First, the storage unit 110 stores the objects of interest (hereinafter, referred to as " objects of interest ") selected from the images in which the specific events have occurred among the images transmitted through the cameras 10-1 to 10- (S100).

Here, the specific event means an unauthorized intrusion or infiltration from the outside into a predetermined surveillance zone such as an aerodrome, ammunition, communication facility, GOP, command control station, etc., and the object of interest is an enemy , An intruder, and the like.

4, the object tracking and monitoring server 100 relays the images received through the cameras 10-1 to 10-N to the storage DB 200, It is possible to receive interest objects selected from the images in which the specific event occurred from the stored images.

Here, the storage DB 200 is a storage medium for storing images, which are transmitted from the object tracking monitoring server 100, in the form of a database (DB) according to predetermined events, such as Oracle, Infomix, Oriented database management system (OODBMS) such as a relational database management system (RDBMS) such as Sybase, DB2, or Gemston, Orion, O2, etc. And has the appropriate fields to achieve its function.

More specifically, the storage DB 200 classifies the images relayed from the object tracking monitoring server 100 according to a specific event, extracts interest objects selected from the classified images, and transmits the classified objects to the object tracking monitoring server 100 And a DVR (Digital Video Recorder) and an NVR (Network Video Recorder) that include a control module and a communication module to transmit data.

Also, the storage DB 200 can acquire and collect GIS (Geographic Information System) information of a space in which the cameras 10-1 to 10-N arranged in the monitoring area are arranged apart from each other.

That is, the storage DB 200 generally includes a geographic information system (not shown) that integrates geographical data occupying a spatial position and attribute data related thereto Store, update, process, analyze, and output the GIS information of the space in which the cameras 10-1 to 10-N arranged in the monitoring area are spaced apart from each other.

Referring to FIGS. 1 and 2 again, the detection unit 120 may detect any one target object from images captured in real time through the cameras 10-1 through 10-N (S110).

Here, the target object may be an object included in the images before being classified as a specific event or before being selected as the object of interest.

At this time, the detection unit 120 detects the target object from the images photographed through the cameras 10-1 to 10-N using the Haar-Like Feature scheme, or detects the HOG (Histogram of Oriented Gradient), CS -LBP (Center-Symmetric Local Binary Pattern) and Gabor Filter Response, and the like.

Next, the extracting unit 130 may extract the first target factors of each site, which is a characteristic of any one of the target objects, from any one of the target objects detected by the detecting unit 120 (S120).

Here, the first object factors of each region are classified into specific areas such as a hat or a helmet, a suitcase bag or a climbing bag on the middle, And the second object factors to be described in the present invention may be used in the same sense as the above description.

More specifically, the extracting unit 130 divides the image region of the target object detected by the detecting unit 120 according to sites, compares the divided image region and predetermined collection factors by site, Can be extracted as the first object factor of the first.

Here, the predetermined collection factors are collectors of upper parts such as cap hats, helmets, climbing caps, collectors on the middle, including accessories such as suitcases, Such as a factor, a gun, a knife, for example, a hand or waist collection factor.

At this time, when extracting the first object factors for each part, the extracting unit 130 extracts a second object factor for each part, which is a characteristic of the objects of interest received from the storage DB 200 or stored in the storage unit 110, (S130).

More specifically, the extracting unit 130 divides the image region of the object of interest previously stored in the storage unit 110 into regions, compares the divided image regions with predetermined collection factors on a site basis, It can be extracted as a second target factor of the site.

Tables 1 to 4 below show examples in which second target factors stored in advance in the storage unit 110 are extracted for each region.

Areas of interest Second Target Factor Counted counts Upper part helmet 30 times Cap hat 8 times Climbing cap Episode 2 Fur hat 4 times none 6 times

Areas of interest Second Target Factor Counted counts Central part

Accessories (bag, water bottle, etc.) 20 times Climbing goods Episode 2 none 28

Areas of interest Second Target Factor Counted counts Lower part Turf 38 times sports shoes 8 times Hiking Episode 2 none Episode 2

Areas of interest Second Target Factor Counted counts Specific site

gun 40 times knife 5 times none 5 times

The extracting unit 130 counts the second target factors extracted from the storage unit 110 according to the sites and calculates the second highest target factor as a risk factor such as a risk factor of the upper region, The risk factors for central, subcancer, and gun can be selected as risk factors for specific sites (S140).

According to the embodiment, the storage DB 200 or the storage unit 110 may store statistics about interesting objects including second target factors for each specific event, for example, an unauthorized intrusion or infiltration into a predetermined monitoring area Information, for example, the examples described in Tables 1 to 4 are manually inputted and stored in advance. At this time, the extracting unit 130 can select a risk factor based on the statistical information.

At this time, the calculating unit 140 may calculate the degree of similarity between the selected risk factors and the first object factors according to the common points between the first object factors and the second object, using the predetermined similarity table (S150).

More specifically, the calculating unit 140 calculates the risk factors selected by the extracting unit 130 using the similarity table shown in Tables 5 to 8 below and the risk factors selected by the extracting unit 130, It is possible to derive the degree of similarity between sites.

The following Tables 5 to 8 are examples of predetermined similarity tables.

Risk factors for upper respiratory tract The first target factor Similarity (2.5 ~ 0) helmet helmet 2.5 Cap hat 1.0 Climbing cap 0.1 Fur hat 0.2 none 0.5

Risk factors in the middle The first target factor Similarity (2.5 ~ 0) Equipment accessories

Accessories (bag, water bottle, etc.) 2.5 Climbing goods 0.1 none 1.5

Risk factors for lower part The first target factor Similarity (2.5 ~ 0) Turf Turf 2.5 sports shoes 0.5 Hiking 0.1 none 0.1

Risk factors for specific areas The first target factor Similarity (2.5 ~ 0) gun
gun 2.5 knife 0.5 none 0.5

At this time, the calculating unit 140 may derive the weights applied when the first object factor and the risk factor are determined to be equal to each other (S160).

Table 9 below shows an example of weights applied when the first object factor and the risk factor are the same for each site.

Identical sites of the primary and risk factors weight Upper part 4 Central part 2 Lower part 6 Specific site 20

More specifically, the calculating unit 140 may calculate the risk of the target object by summing the products of the weights applied when the first object factor and the risk factor are determined to be equal to each other, .

Here, the risk level of the target object can be calculated through the following equation (1).

(1) 이고, 이때, n은 상기 부위의 개수, k는 상기 부위별 기설정된 상수, a는 상기 제1 대상인자와 상기 위험인자의 공통점에 따른 유사도, b는 상기 부위별 인자들이 동일할 때 적용되는 가중치일 수 있다. Here,

(1) where n is the number of sites, k is a predetermined constant for each site, a is the similarity between the first object factor and the risk factor, b is the site-specific factor It may be an applied weight.

For example, if the first object of the target object is a cap on an upper part, a part on a central part, a part on a lower part, and a specific part, The risk of the target object is 1.0 + 1.5 + 0.1 + (2.5 * 20) because the similarities are 1.0, 1.5, 0.1 and 2.5, = 52.6.

Thereafter, the operation unit 150 may operate the cameras 10-1 to 10-N to track the target object according to the predetermined scenarios according to the calculated risk (S180).

Here, the predetermined scenario may include an area in which the cameras are activated, a driving timing of the cameras located in the activated area, and an alarm signal to the outside through the network 50 from the position of the target object to track the target object Whether the object is to be transmitted or not, and may be a series of operations for responding to penetration or movement of the object according to the magnitude of the risk.

That is, the object tracking monitoring server 100 monitors various monitoring peripherals (not shown) such as a warning light, a telephone, a speaker, and an alarm generator in addition to the cameras 10-1 to 10-N according to a predetermined scenario according to the above- Can be operated.

According to an embodiment, the object tracking monitoring server 100 performs a first estimation step of estimating the position of the target object based on preset coordinate information for each of the divided regions from the image when the risk is equal to or greater than a predetermined value And a second estimating step of estimating a moving speed and a direction angle of the object moved from the estimated first position to the second position for a predetermined period of time.

For example, the object tracking monitoring server 100 determines that the coordinate information (X, Y, Z) of the target object located in the region of the image is (10, 15, 21) B * 15) of the target object by mapping the mapping values (a, b, c) of the camera (e.g., 10-1) and the coordinate information (X, Y, Z) (a * 10, b * 16, c * 22) through interlocking with a geographic information system (not shown) (A * 20, b * 16, c * 22) on the basis of the true north of the current position of the moving object on the basis of the already known Pythagorean theorem (M / s) of the target object based on the distance m and the predetermined time s.

The estimating unit 160 may estimate the moving path of the target object according to the direction angle.

According to the embodiment, when the movement path according to the direction angle is estimated through the estimation unit, the operation unit 150 may be provided with a camera (not shown) disposed within a predetermined distance along the movement path among the cameras 10-1 to 10- The scenario can be updated to operate one camera (e.g., 10-1 to 10-5).

At this time, the operation unit 150 displays a control signal for tracking the target object based on the position of one of the cameras (e.g., 10-1 to 10-5), the first position of the target object, The transmission time and the delay time can be determined, and the scenario can be updated to operate one of the cameras (e.g., 10-1 to 10-5) according to the transmission time and the delay time.

According to another embodiment of the present invention, the object tracking and monitoring system 1000-1 may further include a protection device 300. [

The protection device 300 according to the embodiment may be configured such that the risk of the target object is equal to or greater than a predetermined value and trespassing is detected around the specific facility in the monitoring area, -5) is positioned within a predetermined distance from the area detected as the trespassing, it is possible to warn the intruder of the target object.

More specifically, the protection device 300 may include a sensing unit 310, a requesting unit 330, and a corresponding unit 350.

First, the sensing unit 310 is installed in a vicinity of a specific facility such as a military station or a petroleum warehouse in the monitoring area, and interlocks with the object tracking monitoring server 100 to check whether the risk of the target object is above a predetermined value When the risk of the target object is equal to or greater than a predetermined value, it is possible to detect intrusion of the target object around the specific facility.

For example, the sensing unit 310 may include a vibration sensor (not shown) for sensing a vibration of a boundary around a specific facility, an open / close sensor (not shown) for detecting opening and closing of a door, And an infrared sensor (not shown) that detects the surroundings of the boundary through the antenna.

Next, the request unit 330 can request the object tracking monitoring server 100 of the position and the photographed image of any one of the cameras (for example, 10-1 to 10-5) operated through the operation unit 150 have.

Thereafter, the correspondence unit 350 extracts the target object and the boundary network from the image captured through any one of the cameras (for example, 10-1 to 10-5) operated by the object tracking monitoring server 100 (For example, 10-1 to 10-5) is located within a predetermined distance from the detected area, a warning sound is warned to warn against intrusion of the target object into the corresponding area And transmits a warning message to the mobile terminal 353 of the person in charge of the area or displays a warning message on the monitor 355 provided in the communication room.

The method of tracking and monitoring the object described above can be applied to a case where the configuration and method of the embodiments described above are not limitedly applied. Instead, the embodiments may be modified such that all or some of the embodiments are selectively .

10-1 to 10-N: Cameras
50: Network
100: Object tracking monitoring server
110:
120:
130:
140:
150:
160:
200: Storage DB
300: Protection device
310:
330:
350:
1000: Object tracking and monitoring system

Claims (5)

Storing interest objects selected from images in which a specific event has occurred among images previously transmitted through a plurality of cameras;
Detecting a target object from images photographed in real time through the camera;
Extracting a second object factor for each region that is a feature of the ROI when extracting a first object factor for each region that is a feature of the ROI;
Counting the second object factor, selecting a second object factor that is highest in each region as a risk factor, deriving the similarity between the risk factor and the first object factor using a predetermined similarity table, Deriving a weight for each site applied when the first subject factor and the risk factor are determined to be equal to each other;
Calculating a risk of the target object by summing the product of the similarity and the weight by site; And
And operating the camera to track the target object according to a predetermined scenario according to the calculated risk,
Wherein the calculating step comprises:
(1) for the risk of the target object,
The calculation equation

(1)
Here, n is the number of the sites, k is a predetermined constant for each site, a is the similarity between the first object factor and the risk factor, b is a weight value applied when the site-specific factors are the same, The method comprising the steps of:
delete The method according to claim 1,
A first estimating step of estimating a position of the target object based on preset coordinate information for each of the areas divided from the image photographed from the camera in real time when the risk is equal to or greater than a predetermined value;
Further comprising a second estimating step of estimating a moving speed and a direction angle of the target object moving for a predetermined time from a first position to a second position of the target object to be estimated.
4. The method of claim 3, wherein the second estimating step comprises:
And updating the scenario so as to operate one of the plurality of cameras disposed within a predetermined distance along the movement path when the movement path according to the direction angle is estimated. How to monitor.
5. The method of claim 4, wherein the second estimating step comprises:
Determining a transmission time and a delay time of a control signal for tracking the target object based on a position of an imaging region of the camera, a first position of the target object, and a moving speed; And
And updating the scenario to operate the one of the cameras according to the transmission time and the delay time.

Images