KR101687296B1 - Object tracking system for hybrid pattern analysis based on sounds and behavior patterns cognition, and method thereof - Google Patents

Abstract

The present invention relates to an object tracking system and an object tracking method capable of analyzing a hybrid pattern based on sound and behavior pattern recognition. The object tracking method includes: a first step of a single pronunciation of a frequency in a preset range; a second step of determining whether or not a sound event occurs; a third step of transmitting voice event occurrence information; a fourth step of receiving single pronunciation frequency information; a fifth step of receiving image event information; a sixth step of generating information related to a target area or a target object; a seventh step of transmitting the information related to the target area or the target object; an eighth step of generating event photographing information and retransferring the same to a control device; and a ninth step of outputting a message corresponding to an event analysis value.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an object tracking system and an object tracking method capable of analyzing a hybrid pattern based on acoustic and behavior pattern recognition,

The present invention relates to an object tracking system and an object tracking method capable of analyzing a hybrid pattern based on acoustic and behavior pattern recognition, and more particularly, to an object tracking system and an object tracking method capable of analyzing an object corresponding to 2 to 5 seconds In this paper, we propose a method to select a tracking object based on the acoustic frequency of a speech and to perform a filtering with a behavioral pattern by a fixed camera in order to verify it. The present invention relates to an object tracking system and an object tracking method capable of performing hybrid pattern analysis based on acoustic and behavior pattern recognition for enabling high-precision tracking.

In recent years, in order to prevent the occurrence of crime, surveillance cameras are frequently installed in the outskirts or in unseasonable places, and a surveillance camera is installed for the purpose of catching an accident even in a place where frequent traffic accidents are frequent have.

When installing such a surveillance camera, it is important to know how much information can be obtained in comparison with the installation cost and whether to solve the square area.

Accordingly, there is a demand for precision analysis technology for automatically recognizing the emergency situation and notifying the control center in the related technical field.

Korean Patent Registration No. 10-1291728 "CCTV POLE SYSTEM CAPABLE OF MOVING CAMERA UP AND DOWN ", which is capable of raising and lowering a camera, The present invention relates to a CCTV pawl system which can be easily installed on the upper part or can be ascended and descended by a camera which can be downsized and efficiently checked and repaired. , There is a limit to the effective recognition and tracking of objects.

Korean Patent Registration No. 10-1581795, " MANUFACTURING METHOD OF LED STREET LIGHT WITH CCTV CAMERA ", which incorporates a CCTV camera, is used to illuminate a road on which a vehicle is traveling (Closed Circuit Television) camera installed in a street light or an LED (Light Emitting Diode) lighting used to illuminate a predetermined object including a security light for illuminating a road on which pedestrians are walking, and a predetermined subject can be photographed The present invention is directed to an LED street lamp having a built-in CCTV camera. However, the object of the present invention is to acquire an image of a clear object, and there is a limit to effectively recognize and track the object.

Korean Patent Laid-Open Publication No. 10-2016-0070922 corresponding to the prior art 3 "Subway cabin surveillance CCTV system and subway cabin information transmission method using the same (Surveillance CCTV system for subway cabin information using the same ") relates to a subway room monitoring CCTV system and a subway room information transmission method using the same, which enable high-resolution information to be continuously transmitted so that the situation in a subway room can be checked in real time in history, There is a limitation that it can not be used as a wide range CCTV system on the road.

Korean Patent Registration No. 10-1507978 " VERSATILE CLOSED CIRCUIT TELEVISION SECURITY SYSTEM "corresponding to Conventional Technology 4 relates to a multipurpose CCTV crime prevention system and is disposed inside a toilet, An emergency button for transmitting a radio signal corresponding to a push command; A wireless emergency bell receiver disposed within the toilet, the wireless emergency bell receiver receiving the wireless signal from the emergency button; A signal processor for receiving a radio signal from the radio emergency bell receiver and transmitting a radio signal in an emergency; A radio transmission unit for transmitting the radio signal in the emergency state under the control of the signal processing unit; A radio receiver for receiving the transmitted emergency radio signal; And a CCTV security pole including the CCTV camera installed when the radio receiver is installed and the radio receiver receives the radio signal in the emergency. Thus, the CCTV security pole can be used as a surveillance method using indoor CCTV, There are limitations that can not be done.

Korean Patent Registration No. 10-1291728 entitled " CCTV POLE SYSTEM CAPABLE OF MOVING CAMERA UP AND DOWN " Korean Patent Registration No. 10-1581795 entitled " MANUFACTURING METHOD OF LED STREET LIGHT WITH CCTV CAMERA " Korean Patent Laid-Open Publication No. 10-2016-0070922 entitled " Surveillance CCTV System for Subway Cabin & Surveillance Method Using Subway Cabin Information Using the Same " Korean Patent Registration No. 10-1507978 entitled " VERSATILE CLOSED CIRCUIT TELEVISION SECURITY SYSTEM "

In order to solve the above problems, the present invention primarily selects a tracking object that is raised in an emergency situation based on the acoustic frequency of a phoneme corresponding to 2 to 5 seconds, which can be expressed in one sentence, An object tracking system capable of performing hybrid pattern analysis based on acoustic and behavior pattern recognition in order to enable precise tracking by significantly increasing the probability of selection of an object to be traced in an emergency by performing filtering based on a behavior pattern by a fixed camera Object tracking method.

However, the objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

According to another aspect of the present invention, there is provided an object tracking method capable of analyzing a hybrid pattern based on acoustic and behavior pattern recognition, Stage 1; A second step of determining whether or not an acoustic event is generated by analyzing whether the acoustic frequency recognition device determines that the terminal sound is equal to or greater than a preset threshold value dB; A third step of, when the acoustic event occurs, generating a voice event occurrence information by the acoustic frequency recognition device and transmitting the voice event occurrence information to the control device; A fourth step of receiving the monophonic sound frequency information from the sound frequency recognition device which senses the received monophonic sound for the purpose of analyzing whether the emergency situation occurs or not in order to start the analysis of the emergency situation; A fifth step of receiving the video event information from the fixed photographing device located in the same area as the acoustic frequency recognition device in which the control device senses the phoneme; A sixth step of analyzing an emergency situation of a subject through the voice event occurrence information and the video event information and generating information about a target area or a target object to be photographed by the rotary camera in an emergency situation; A seventh step of transmitting the information about the target area or the target object determined by the control device to a rotating camera located in the same area as the sound frequency recognizing device that senses the sound; An eighth step of causing the rotary camera to shoot an object area or a target object determined by the control device to generate event photographing information and return the event photographing information to the control device; And a control step of generating an event analysis value by using the event photographing information received by the control device and outputting a message corresponding to the event analysis value to the flat speaker. The fifth step of receiving the shortened sound frequency information from the acoustic frequency recognition device which senses the received short sound for analyzing whether the control device is in an emergency situation; A step 5-2 of analyzing the received monophonic sound frequency information to determine whether the monophonic sound corresponds to a sound frequency requested for assistance; When the monaural sound corresponds to the sound frequency requested for assistance, the control device performs the first image event detection. After calculating the direction of the received monaural sound frequency signal, Based event detection event image) from the image captured by the control unit. On the other hand, when the terminal sound does not correspond to the assist request sound frequency, the controller analyzes the received sound end frequency information (Step 5 - 3) of judging whether or not the singular pronunciation corresponds to the acoustic frequency (whistle sound frequency) generated by the help requesting tool; And when the analysis result corresponds to the sound frequency (whistle sound frequency) generated by the help requesting tool, the control device performs the second image event detection (event extraction of the event based on the subject and the help request tool) , Calculates the direction of the received end sound emission frequency signal, and performs a second image event detection from the image captured by the fixed camera disposed in the area matching the direction. On the contrary, if the end sound does not correspond to the whistle sound frequency (5) performing the third video event detection (two subject-based emergency occurrence event video event extraction) by the control device; And the sixth step includes analyzing an emergency situation of the subject when the control device senses at least one of the first to third video events and the monaural assisted sound frequency in the fifth step The control device determines an image pickup target area or object of the rotary camera as an acoustic frequency signal direction (i.e., a direction in which the acoustic frequency signal is sensed) When generating the analysis value, the event analysis value includes' help event analysis value 'matching with the first video event,' help request tool (whistle) event analysis value matching with the second video event ', and' , 'Violent event event analysis value', and 'normal event analysis value' matching with other normal events, and the normal event analysis value is classified into ' (A situation where a moving object moves around the main entrance of the access control area and there is a possibility that the moving object may be stolen when the moving object is wandering for a certain period of time or stopped for a predetermined time while facing the main entrance door) .
In this case, the ninth step may include determining whether the event analysis value generated by the controller is a plurality of event analysis values; (9-2) selecting a highest priority event analysis value according to a priority among a plurality of event analysis values when a plurality of moving objects are identified in a target area in which the control device is determined to be photographed; A step 9-3 of the controller extracting a message corresponding to an event analysis value corresponding to the selected event analysis value; The controller transmits the sound information corresponding to the extracted message to the flat speaker; And (9-5) the speaker outputs the acoustic information as a voice or an alarm sound by transmitting the acoustic information. , And the priority order is set through a sequence of 'help event analysis value', 'help request tool (whistle) event analysis value', violence event analysis value ', and' normal event analysis value ' .
In addition, a fixed camera, a rotary camera, a speaker, an acoustic frequency recognition device, and a beacon wireless signal transmission / reception unit are set and installed in the vicinity of the confirmed monitored area, and the control device is separately installed in an external control center The control unit of the control center is set to receive a beacon radio signal from a mobile terminal that has executed the safe-ear application in each mobile terminal, and controls the beacon radio signal transmitting and receiving unit in each surrounding area of the confirmed monitored area And transmits the position of the transmission ear to the mobile terminal of the predetermined destination after receiving it through the network.

delete

delete

delete

The object tracking system and the object tracking method capable of analyzing hybrid patterns based on acoustic and behavior pattern recognition according to an embodiment of the present invention are based on the acoustic frequency for a single sound corresponding to 2 to 5 seconds which can be expressed in one sentence In order to verify the effectiveness of the tracking system, it is necessary to perform the filtering with the behavior pattern by the fixed camera to greatly improve the selection probability of the tracking object placed in the emergency situation and to perform precise tracking. do.

FIG. 1 is a diagram illustrating an object tracking system capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to an embodiment of the present invention.
FIG. 2 and FIG. 3 are flowcharts illustrating an acoustic recognition-based method among object tracking methods capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to an embodiment of the present invention.
FIG. 4 is a flowchart illustrating an acoustic recognition-based method among object tracking methods capable of analyzing hybrid patterns based on acoustic and behavior pattern recognition according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating an object tracking system capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to another embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a detailed description of preferred embodiments of the present invention will be given with reference to the accompanying drawings. In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

In the present specification, when any one element 'transmits' data or signals to another element, the element can transmit the data or signal directly to the other element, and through at least one other element Data or signal can be transmitted to another component.

FIG. 1 is a diagram illustrating an object tracking system capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to an embodiment of the present invention. Referring to FIG. 1, an object tracking system capable of analyzing a hybrid pattern based on acoustic and behavior pattern recognition tracks object regions or object objects captured using acquired image information, and analyzes patterns of object regions or object objects to analyze And outputs a voice or an alarm sound corresponding to the resultant value.

The object tracking system capable of analyzing the hybrid pattern based on the acoustic and behavior pattern recognition according to the present embodiment outputs different voice or alarm depending on the result value, thereby enabling the emergency situation to be recognized when the emergency occurs, If a crime situation occurs, it should be aware of the crime situation in the vicinity so that it can cope with the emergency quickly or prevent the crime from being committed in advance.

For this, an object tracking system capable of analyzing hybrid patterns based on sound and behavior pattern recognition according to the present embodiment includes fixed camera assemblies 100G (100-1 to 100-N, where N is a natural number of 2 or more), rotating camera assemblies 200G 200-1 to 200-N), a control device 300, a directional flat plate type speaker assembly 400G (400-1 to 400-N), a speech recognition frequency device assembly 500G (500-1 to 500- And beacon radio signal transmission / reception subassemblies 600G (600-1 to 600-N).

Each fixed camera 100 constituting the fixed camera assembly 100G is provided to photograph a predetermined area and detect whether or not a specific event occurs.

For this purpose, the fixed camera 100 is positioned where the predetermined area can be widely photographed.

Specifically, if the object tracking system according to the present embodiment is used in an access control area, the fixed camera 100 can capture a door that can enter and exit the access control area and windows positioned around the door .

The fixed camera 100 generates the first to third video events and the normal event generation information when the first to third video events and the normal events, which are specific video events, are detected while the preset area is photographed, ).

Here, the first video event indicates a case in which a help request is detected in a specific area such as "a subject jumps," " a subject swings a hand, " An event can be defined as "a subject holding or holding a whistle" in a specific area, "a subject whistling or whistling a whistle", "a subject swinging a hand whistling or whistling", " Quot ;, " having ", " having ", and the like are detected through the whistle. The third video event indicates that two objects are entangled in a specific area, , "When at least one of two subjects falls over when two subjects are tangled or are positioned at a predetermined gap in the eyes, Quot; indicates that the probability of an emergency situation is high except for the first video event and the second video event. Finally, the normal event indicates a case where at least a moving subject is detected in a specific area. That is, the fixed camera 100 performs a function of detecting whether a moving object exists in a specific area.

To this end, the fixed camera 100 may include a sensing sensor, not shown in the figure, that can sense a moving object or recognize a sound.

The first to third video events and normal event generation information generated by the fixed camera 100 include at least one of identification information unique to the fixed camera 100, time information, sound information, and image information.

The unique identification information may be any type of information preset in the fixed type camera 100, such as the serial number of the fixed type camera 100 and the coordinate information of the area taken by the fixed type camera 100.

In addition, the fixed camera 100 may be provided as a plurality of units as shown and may transmit / receive information to / from the control device 300. [

Meanwhile, the rotary camera 200 is used to track the determined object area or the determined object, and the rotary camera 200 rotates or zooms in or out in order to enlarge or reduce the object area or object, out.

The rotary camera 200 receives the object area or the determined object information determined according to the event generation information generated in the fixed camera 100 from the controller 300. [

When the acoustic frequency recognition apparatus 500 transmits sound event occurrence information to the control apparatus 300 and transmits the first to third video event and normal event occurrence information from the fixed camera 100 to the control apparatus 300, The controller 300 comprehensively determines the area to be photographed by the rotary camera 200 or the object to be photographed by using the acoustic event generation information, the first to third image events, and the normal event generation information, The controller 300 transmits information on the determined object area or the determined object to the rotary camera 200. The controller 300 will be described later in detail.

In addition, the rotary type camera 200 photographs the determined object area or the determined object to generate event shooting information, and transmits the photographed event shooting information to the control device 300.

To this end, the rotary camera 200 includes a 'fixed camera 100' that generates first to third video events and normal event generation information, and a 'sound frequency recognition device 500) 'so that the determined object region or the determined object is photographed.

For example, in the case where an object tracking system capable of analyzing a hybrid pattern based on sound and behavior pattern recognition according to the present embodiment is used in the access control area as described above, event occurrence information (sound event occurrence information, If the determined object received from the control device 300 according to the first to third normal event occurrence information is a person located near the door formed in the access control area, the rotating type camera 200 recognizes the person, And event shooting information is generated by photographing a person by moving the lens.

The rotary type camera 200 may be provided in a plurality of ways as shown in the same manner as the fixed type camera 100 and the acoustic frequency recognition device 500, and may transmit and receive information to / from the control device 300.

If the rotating type camera 200 receiving the object information determined from the control device 300 for the first time can not recognize the person any more, the control device 300 controls the first rotating camera 200 around the first rotating camera 200 Additional tracking of the object may be possible via another rotary camera 200 positioned in the direction of movement of the object.

The control device 300 controls the fixed camera 100, the rotary camera 200 and the flat speaker 400 and the acoustic frequency recognition device 500 and analyzes sound and video events when an event is generated, And a voice or an alarm sound is automatically transmitted according to the result value.

The controller 300 is installed in the vicinity of the fixed camera 100, the rotating camera 200, the flat speaker 400, and the acoustic frequency recognizer 500, or is provided as a separate server. A plurality of fixed type cameras 100-1 to 100-N, rotating type cameras 200-1 to 200-N, flat type speakers 400-1 to 400-N, And transmits and receives information to and from the frequency identification devices 500-1 to 500-N.

The control device 300 includes a communication unit 310, a moving object recognition unit 320, a pattern analysis unit 330, a message DB unit 340, and a control unit 350.

The communication unit 310 is provided for transmitting and receiving information to and from the fixed type camera 100, the rotating type camera 200 and the flat type speaker 400 and the acoustic frequency recognition device 500, And transmits the determined object area or object information, which is determined through the moving object recognizing unit 320, to the rotating camera 200. The moving object recognizing unit 320 receives the event information from the moving object recognizing unit 320,

The communication unit 310 receives the event shooting information generated by tracking the object area or the determined object determined by the rotary camera 200 and transmits the event shooting information to the control unit 350 and stores the sound information stored in the message DB unit 340 And transmits it to the flat-panel speaker 400.

Meanwhile, the moving object recognizing unit 320 determines a target area or a target object to be photographed by the rotary camera 200 through the event occurrence information received through the communication unit 310, and determines a target object determined in the event generation information And is provided for generating movement coordinates of the determined target object.

Specifically, when a 'sound' is detected at the main entrance / exit of the access control area, the moving object recognizing unit 320 determines the main entrance and the object to be photographed, detects the object causing the movement, And when the movement of the determined object is continuously detected, the movement direction and the movement coordinates of the determined object are determined so that the determined object can be tracked.

Then, the moving object recognizing unit 320 causes the moving object and the object information to be determined, and the moving direction and the moving coordinate of the object to be transmitted to the rotating type camera 200 through the communication unit 310.

Meanwhile, the pattern analyzer 330 is provided to generate event analysis values by analyzing a situation or a behavior pattern of the target area or the target object through the event shooting information received through the rotating camera 200. [

The pattern analysis unit 330 stores event analysis values in which the event analysis values according to the situation or action pattern of the target area or the target object are stored in advance or generated, and the event analysis values are set with predetermined priorities and stored .

Here, the priority order is set according to the emergency situation, and the emergency situation may be set based on at least one of natural disaster, dangerous goods, violence, emergency of the target object, and theft.

Natural disasters are information related to floods, tidal waves, heavy rains, etc., and dangerous goods are information related to weapons including explosives, guns, etc., and violence may mean a collision between a single object or a plurality of objects. Of course, this is only an example, and the emergency situation according to the present embodiment may be further subdivided and classified.

The emergency situation in this embodiment may be set to a single category, but a plurality of categories may be set in combination. For example, if analysis values related to dangerous goods and analytical values related to violence were analyzed at the same time, and analysis values related to violence and analysis values related to theft were analyzed at the same time, the combination of dangerous goods and violence was more likely to be an emergency situation than a combination of violence and theft It is set high.

The pattern analyzer 330 may further include a precision pattern analyzer to more accurately determine the situation. When the pattern analyzer 330 further includes the precision pattern analyzer, the pattern analyzer 330 may calculate the analysis value generated by the pattern analyzer 330 And the analysis values may be classified according to further subdivided categories.

The message DB unit 340 stores sound information to be output from the flat panel speaker 400 according to a message and a message corresponding to the event analysis value generated by the pattern analysis unit 330.

The sound information stored in the message DB unit 340 is information that can be outputted as a sound of a person or an alarm such as a siren through the flat speaker 400 and is stored in correspondence with the message.

Meanwhile, the control unit 350 controls the communication unit 310, the moving object recognizing unit 320, the pattern analyzing unit 330, and the message DB unit 340 so that the control device 300 controls the fixed camera 100, The speaker 200, the flat-plate speaker 400, and the acoustic-frequency recognition device 500. [

Specifically, the control unit 350 receives the first to third event generation information and the normal event generation information from the fixed camera 100 and receives the sound event generation information from the sound frequency recognition apparatus 500 through the communication unit 310 The moving object recognizing unit 320 determines a target area or a target object to be photographed by the rotary camera 200 through the received first to third event occurrence information and acoustic event occurrence information, And generates the moving coordinates of the determined target object.

The control unit 350 controls the communication unit 310 to transmit the movement coordinates generated in the object region or the object determined by the moving object recognition unit 320 and the moving coordinate to the rotation type camera 200 through the communication unit 310, And transmits the event photographing information to the pattern analyzing unit 330. The pattern analyzing unit 330 receives the event photographing information from the rotating type camera 200,

The control unit 350 extracts a message corresponding to the event analysis value generated by the pattern analysis unit 330 from the message DB unit 340 and outputs sound information to be output according to the extracted message to the reputation Type speaker 400 as shown in FIG.

Meanwhile, the flat speaker 400 is provided for outputting sound information according to the event analysis value as a human voice or an alarm sound, and receives sound information from the controller 300. [

In the illustrated example, it is assumed that the flat speaker 400 is a separate component. However, the flat speaker 400 may be included in the controller 300, Or may be provided in the fixed type camera 100 or the rotary type camera 200. [

FIG. 2 and FIG. 3 are flowcharts illustrating an acoustic recognition-based method among object tracking methods capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to an embodiment of the present invention. Referring to FIG. 2, one of the acoustic frequency recognition apparatuses 500-1 to 500-N senses the pronunciation of a predetermined range of frequencies (S11).

After step S11, the acoustic frequency recognition apparatus 500 determines whether an acoustic event is generated by analyzing whether the terminal sound of step S21 is equal to or greater than a predetermined threshold value dB (S12).

If it is determined in step S12 that the sound event has occurred, the sound frequency recognition apparatus 500 generates the sound event occurrence information (S13) and transmits the sound event occurrence information to the control apparatus 300 (S14).

After step S14, the control device 300 determines whether the acoustic frequency recognition device 500 senses the ending sound received in step S14 ) Of the sounding frequency information.

After step S15, the control device 300 analyzes the short-term phonetic frequency information received in step S15 to determine whether the monophonic sound corresponds to the help-requested sound frequency (step S16). Here, the sound frequency of the help request is stored in advance by storing all the information capable of frequency output by a combination of characters constituting a sentence by a sentence by a voice of a person such as 'help me' 300 performs recognition within a predetermined range of error range from the frequency output range of each character of a previously stored sentence and analyzes whether or not the sentence matched with the help request acoustic frequency is recognized by the combination of the recognized characters will be.

If it is determined in step S16 that the monophonic sound corresponds to the assist request sound frequency, the process proceeds to step S16a. On the other hand, if the monophonic sound does not correspond to the assist request sound frequency, the process proceeds to step S13, The controller 300 analyzes the short-term sound frequency information received in step S15 and determines whether the short sound corresponds to the whistle sound frequency (S17).

More specifically, in step S16a, the control device 300 performs the first image event detection. After calculating the direction of the single-phonetic frequency signal received in step S15, From the image photographed by the camera 100, whether or not there is an image in which a subject is running, an image in which a subject shakes his or her hand, an image in which a subject falls, etc. corresponding to a first image event (S16a).

If it is determined in step S16 that the monophonic sound is the assist request sound frequency (first judgment), and if it is determined in step S16a that the first image event is detected (second judgment) Finally, the control device 300 analyzes the state of the subject as an emergency situation, and then determines the region to be photographed or the target object of the rotary camera 400 as the direction of the acoustic frequency signal (that is, the direction in which the acoustic frequency signal is sensed) (S19).

Then, the control device 300 transmits information on the determined object area or object to the rotary camera 200 (S20).

The rotary type camera 200 causes the control device 300 to photograph the object area or the object determined (S21). In this case, the rotatable camera 200 can enlarge or reduce the target area or the target object, and can photograph the target object along the movement path of the target object when the target object moves.

When the distance between the rotary camera 200 and the object is distant as the object moves, the other rotary camera 200 in the movement path of the object may track the object.

Then, the rotary camera 200 photographs the target area or the target object to generate event shooting information (S22). If the determined object is a person located near the door formed in the entrance control area, the rotary camera 200 recognizes the person and moves the lens according to the movement of the person to generate the event shooting information by shooting the person. At this time, the event shooting information may include image information and movement coordinates for indicating a movement path when the object moves.

Then, the rotary camera 200 transmits the generated event shooting information to the control device 300 (S23).

Accordingly, the control device 300 generates an event analysis value using the received event photographing information (S23a). The event analysis value is a result value for detecting a state of an event using the event shooting information in the pattern analysis unit 330 of the controller 300 and outputting a message corresponding thereto.

On the other hand, if it is determined that the monaural pronunciation is not the assist requesting acoustic frequency, the control unit 300 analyzes the monophonic sound frequency information received in step S15 to determine whether the monaural sound corresponds to the whistle sound frequency (S17).

Here, the whistler sound frequency is preliminarily stored in advance as all possible information on the frequency output of the whistle distributed on the market, so that the controller 300 performs recognition within a predetermined range of error range from the previously stored whistle frequency output range, The number of cases of the output intensity of the whistle frequency is combined to analyze whether it corresponds to the whistle acoustic frequency.

If it is determined in step S17 that the monophonic sound corresponds to the whistle sound frequency, the process proceeds to step S18a. On the contrary, if the monophonic sound does not correspond to the whistle sound frequency, the process proceeds to step S18.

More specifically, in step S18a, the controller 300 performs the second image event detection. After calculating the direction of the single-ended sound frequency signal received in step S15, Quot ;, " an image in which a subject whistles or whistles a whistle, "" an image in which a subject whistles or ran whistles," which corresponds to a second video event from an image photographed from the camera 100, Quot ;, "an image in which a subject whistles or whistles the whistle," or the like.

If it is determined in step S17 that the monophonic sound is the whistle sound frequency (first judgment), and if it is determined in step S18a that the second video event is detected (second judgment) Finally, after analyzing the control device 300 as an emergency situation of the subject, the control device 300 controls the operation of the rotary camera 200 in the direction of the acoustic frequency signal (i.e., the direction in which the acoustic frequency signal is sensed) (S19). The processes of step S20 to step S23a are as described above.

Next, the flow returns to step S16, and if the analysis result of step S16 is that the monophonic sound is not the assist requesting sound frequency (first judgment), and the analysis result of the following step S17 is not the whistle sound frequency The control device 300 determines whether the third video event is detected through the video of the subject photographed by the fixed camera 100 in step S18. In step S18, in the determination of the third video event, the controller 300 calculates the direction of the phoneme frequency signal received in step S15, Quot; image in which two subjects are entangled ", "image in which two subjects are positioned at a predetermined interval "," An image of at least one of two subjects in a state of being in a state of being sad, or an image of waving their hand "or the like.

As a result of the determination in step S18, when the control device 300 detects the third video event, it analyzes the subject as an emergency situation and then sets the region to be photographed by the rotating camera 200 as the acoustic frequency signal direction The direction in which the acoustic frequency signal is sensed) (S19). The processes of step S20 to step S23a are as described above.

Then, the rotary camera 200 transmits the generated event shooting information to the control device 300 (S23).

Meanwhile, when the event analysis value is generated using the event shooting information received by the controller 300 in step S23a, the event analysis value includes 'help event analysis value' matching the first video event, A whistle event analysis value matching with the third video event, a 'violent event event analysis value' matching with the third video event, and a 'normal event analysis value' matching with the normal event in FIG. As a concrete example of the normal event, when the moving object moves around the main entrance door of the access control area and the moving object is stopped for a predetermined time or for a predetermined time while facing the main entrance door, the control device 300 This can be judged as a possibility of theft. Then, the control device 300 generates the theft analysis value using the subdivided normal event analysis value.

Referring to FIG. 3, after step S23a, the control device 300 determines whether there are a plurality of event analysis values generated in step S23a (S24). Specifically, when a plurality of moving objects are identified in the target area in which shooting has been determined, the controller 300 detects each moving object and determines the behavior of the moving object. For example, if there are two moving objects, the behavior of the first moving object and the second moving object are respectively determined.

As a result of the judgment in the step S24, if there are a plurality of items, the process goes to the step S25, and if not, the process goes to the step S26.

That is, in step S25, the control device 300 selects the highest priority event analysis value according to the priority (S25). More specifically, if there are a plurality of event analysis values (S24-Yes), the control device 300 selects the highest priority event analysis value according to the priority among the plurality of event analysis values.

The control device 300 may be configured such that priority information is included in the event analysis value when generating or storing event analysis values, or may be categorized by priority and stored in the corresponding category.

Here, the priority order may be set through a sequence of 'help event analysis value', 'whistle event analysis value', 'violent event event analysis value', and 'normal event analysis value'. In another embodiment, Or an order between the different event analysis values and the subdivided normal event analysis values. In addition, the priority order can be set according to the emergency situation among the subdivided normal event analysis values, and the emergency situation can be set based on at least one of natural disaster, dangerous goods, violence, emergency of the target object, .

Specifically, when the dangerous goods is set to have a higher priority than theft, for example, it is determined that the first moving object wanders at the entrance of the main entrance door for a certain period of time and the event analysis value is classified as theft. And the event analysis value is classified as a dangerous object, the second moving object classified as a dangerous object having a higher priority is selected.

After step S25, the control device 300 extracts a message corresponding to the event value corresponding to the selected event analysis value (S26). If the event analysis value is a dangerous object, the control device 300 extracts a message related to the dangerous object among the messages stored in the message DB 340. To this end, the message may be stored for each category corresponding to the emergency situation.

On the other hand, when the number of event analysis values is not plural (S24-NO), the control device 300 extracts the corresponding message because the generated analysis value itself is the selected analysis value without need to select the event analysis value (S26) .

After step S26, the control device 300 transmits the sound information corresponding to the message extracted in step S26 to the directional flat speaker 400 (S27).

After step S27, the flat speaker 400 transmits the sound information and outputs the sound information as a sound or an alarm sound (S28). If a message matching the normal event analysis value associated with the dangerous object is extracted and the acoustic information corresponding to the message is a fire alarm sound, the flat speaker 400 sounds a fire alarm sound.

On the other hand, after step S28, the control device 300 determines whether another acoustic-frequency-generating device 500 has received another acoustic-event generating information (S29).

As a result of the determination in step S29, the control device 300 receives other sound event occurrence information The process proceeds to step S30. On the contrary, if no other acoustic event occurrence information is received, the object tracking method process is completed which can perform hybrid pattern analysis based on acoustic and behavior pattern recognition.

That is, when receiving another sound event occurrence information from another acoustic frequency recognition device 500 in accordance with step S30 (S29-YES), the control device 300 generates another sound event from another rotation type camera 200 Information is received. In this process, the controller 300 determines an object area or a target object to be photographed (step S15 to step S19) and transmits it to the other rotatable camera 200, The steps of generating and transmitting the event shooting information (steps S21 to S23) are the same as those described above or can be sufficiently inferred, and detailed description will be omitted.

On the other hand, if no other acoustic event occurrence information is received from another acoustic frequency recognition device 500 (S29-N), the process returns to the first step or ends.

After step S30, the control device 300 generates another event analysis value (S31).

After step S31, the control device 300 determines whether the priority level of the event analysis value output from the flat speaker 400 is higher than that of the event analysis value output in step S27 or S28 in step S32.

If it is determined in step S32 that the priority of the event analysis value other than the event analysis value corresponding to the voice or alarm sound being output from the flat speaker 400 is high (S32-Yes) A message corresponding to the event analysis value is extracted (S33).

After step S33, the control device 300 requests the flat speaker 400 to stop outputting a sound or an alarm sound (S34).

After step S4, the control device 300 transmits the acoustic information corresponding to the extracted other message to the flat speaker 400 (S35).

After step S35, the flat speaker 400 outputs another voice or alarm sound (S36).

On the other hand, if the priority of the event analysis value other than the event analysis value corresponding to the voice or alarm sound output from the flat speaker 400 is low (S190-Y), the controller 300 determines that the flat panel speaker 400 So that the transmission of the voice or alarm sound being output is maintained.

At this time, the time to output the sound or the alarm sound from the flat-type speaker 400 may be preset and stored in the controller 300, and the sound or alarm sound output from the flat- , It can be stopped when the set time has elapsed automatically.

FIG. 4 is a flowchart illustrating an acoustic recognition-based method among object tracking methods capable of analyzing hybrid patterns based on acoustic and behavior pattern recognition according to an embodiment of the present invention. The flow according to the method of Fig. 4 can be performed independently in addition to the step S18a, NO in Fig. 3, the step S16a, NO in Fig. 3, the step S18, NO in Fig.

Here, the step S16a, NO in FIG. 3 is a step S16a, in which, if it is determined that the pronunciation of the monophone is the assist request sound frequency (first judgment) in step S16 and the first video event is not detected (Second judgment) ", the process proceeds to step S100 of FIG. 4 by the following process.

3, step S18, NO), the case where the sound is not the assist sound frequency and the whistle sound frequency (first judgment), and the third image event is not detected The process proceeds to step S100 of FIG.

Here, in the third video event, the control device 300 performs the detection. In the determination of the third video event, the controller 300 calculates the direction of the shortest sound emission frequency signal received in step S15 &Quot; an image in which two subjects are entangled " corresponding to a third image event from an image photographed from the fixed camera 100 arranged in an area matching with the direction, " Quot ;, " image ", "image of at least one of two subjects falling or shaking hands"

3, the step S18a is NO. If the result of the judgment in the step S17 is that the monophonic sound is the whistle sound frequency (the first judgment), and if it is judged in the step S18a that the second video event is detected , The process proceeds to step S100 of FIG.

More specifically, step S100 will be described.

First, the control device 300 detects a normal event from one of the plurality of fixed cameras 100 (S110). Here, the normal event indicates a case where at least a moving subject is detected within a specific area. That is, the fixed camera 100 performs a function of detecting whether a moving object exists in a specific area.

After step S110, the control device 300 determines whether the value is a single-ended dB (decibel) ≥1 dB (decibel) value (S120). That is, the control device 300 receives (or receives) the sound data through the acoustic frequency recognition device 500 disposed in the area where the fixed camera 100 sensing the normal event is matched in step S110 among the plurality of acoustic frequency recognition devices 500 (DB), which is the magnitude of the sound frequency signal of the single-ended sound, and then determines whether or not it is larger than a preset first decibel (dB) value.

Here, the first dB value represents the dB value of the acoustic frequency signal which is larger than the noise normally generated in the surroundings. That is, it can be recognized that the occurrence of an acoustic frequency signal having a frequency higher than the first dB value occurs as usual. Accordingly, when the acoustic frequency signal of the first dB value or more is recognized, the controller 300 controls the rotary camera 200 to photograph the area where the acoustic frequency signal is generated.

Such a case will mainly be used as a method for judging the crime or accident scene occurring in the blind spot of the fixed type camera 100 as an acoustic frequency signal.

On the other hand, if it is determined in step S120 that the monophonic sounding dB is equal to or greater than the first sounding sounding amount value, the controller 300 determines whether the sounding sounding level is the second sounding sounding level.

If it is determined in step S130 that the terminal sound dB is equal to or greater than the second dB value, the control device 300 proceeds to step S170 to determine the object area of the rotating camera in the step sound direction, If it is less than the second dB value, the process proceeds to step S140, where the target area is determined according to the predetermined priority.

That is, if it is determined in step S130 that the terminal sound dB is equal to or greater than the second dB value, the controller 300 sets the imaging object area of the rotary camera 200 to the sound frequency signal direction Direction).

More specifically, when the strength of the sound frequency signal of the single sound is equal to or greater than the second dB value, the controller 300 calculates the direction of the sound frequency signal using the recognized sound frequency signal information, To the target area. Thereafter, the controller 300 causes the rotary camera 200 to photograph the direction in which the acoustic frequency signal is sensed, thereby controlling the photographing of the cause of the acoustic frequency signal. That is, even when the fixed camera 100 generates a normal event, the direction of the acoustic frequency signal can be directly determined as the target area by ignoring the event.

Here, the second dB value corresponds to the intensity of the treble (e.g., screaming acoustic frequency signal) or impact sound (e.g., total acoustic frequency signal, bomb sound frequency signal, etc.) . That is, the second dB value is larger than the first dB value. Therefore, when the control device 300 recognizes the acoustic frequency signal of the second dB value or more, the control unit 300 controls the rotating type camera 200 to preferentially photograph the area where the acoustic frequency signal is sensed because it is in a dangerous situation.

As a result of the determination in step S130, if the single-sounding dB corresponding to the sound frequency signal intensity is smaller than the second dB value, the controller 300 controls the rotary camera 200 to photograph the object (S140).

This priority may include whether or not the direction of the acoustic frequency signal is included in a specific area where the normal event is generated. If the direction of the acoustic frequency signal is included in the specific area in which the event is generated, The camera 200 can determine the direction in which it is to be photographed. In addition, if the direction of the sound frequency signal is not included in the specific area in which the event is generated, the direction to be photographed may be determined according to various priorities set by the user.

That is, when a plurality of normal events are detected in the fixed camera 100, the control device 300 transmits a specific area, which is captured by the camera in which one event having the highest priority is detected, 200 may be controlled so as to photograph in detail.

For example, the control device 300 determines whether or not the sound frequency signal dB value A in the range between the first and second dB values is greater than the first and second dB values, a motion frequency signal dB value B is greater than a sound frequency signal dB value B, and a motion event a is an arm frequency b Is a fast-moving event, and the motion event b can be set as a fast-moving event. The reason is that when the sound frequency signal is bigger than when the sound frequency signal is small, and when the arm moves faster than when the leg is moving quickly, there is a high possibility of a crime or an accident.

On the other hand, if it is determined in step S120 that the stepped sound dB is less than the first dB value, the controller 300 proceeds to step S150 and determines the target area of the rotary camera 200 as the normal event area S150).

If it is determined in step S110 that the normal event is not detected, the control device 300 proceeds to step S160 to determine whether or not the sound level is dB_dec1 dB (step S160) If the sounding dB is smaller than the first dB value, the flow returns to step S11 in FIG. 2. Conversely, if the sounding dB is greater than or equal to the first dB value, the object area of the rotating camera is determined in the sounding direction (step S170) .

Also, if it is determined in step S130 that the terminal sound dB is equal to or greater than the second dB value, the controller 300 proceeds to step S170 and determines the object area of the rotary camera in the step sound direction in step S170.

If the strength of the recognized sound frequency signal is between the first dB value and the second dB value (step S130, NO), the control device 300 controls the rotary camera 200 In more detail, the controller 300 combines or compares the audio frequency signal information, the first to third event information, and the normal event information, and determines an object to be photographed according to the priority.

To this end, the control device 300 calculates the direction of the acoustic frequency signal using the monophonic sound frequency signal information, and determines whether or not the normal event is sensed in an area photographed by at least one fixed camera 100 . When a normal event is detected in a specific area captured by the fixed camera 100, the control device 300 determines whether the direction of the calculated sound frequency signal is included in a specific area captured by the fixed camera 100 in which the event is sensed Or not.

If the direction of the calculated acoustic frequency signal is included in a specific region captured by the fixed camera 100 where the event is generated, the controller 300 determines whether the direction of the calculated acoustic frequency signal corresponds to the direction of the calculated acoustic frequency signal And controls to shoot the corresponding specific area.

On the other hand, when the direction of the calculated sound frequency signal is not included in the specific region captured by the fixed camera 100 in which the event is detected, the control device 300 determines whether or not the specific region .

In this case, the control device 300 may control the rotating type camera 200 to compare the priority order of the normal event information with the priority order of the sound frequency signal information to photograph the direction corresponding to the higher priority order have.

For this purpose, the control device 300 may assign priorities to various levels of events, or assign different priorities to various levels of sound frequency signal information by intensity. When a plurality of events are detected in the plurality of fixed cameras 100, the control device 300 may be configured to rotate the specific area captured by the camera, which detects one normal event having the highest priority among the plurality of normal events, It is possible to control the camera 200 to photograph in detail.

On the other hand, when the normal event is not detected in the specific area captured by the fixed camera 100, the control device 300 calculates the direction of the sound frequency signal using the recognized sound frequency signal information, As a target area.

When the sound frequency signal is not recognized in the acoustic frequency recognition device 500 and an event is detected in the fixed type camera 100, the control device 300 determines the specific region being photographed in the fixed type camera 100 in which the event is detected And controls the lens direction of the rotating type camera 200 so as to photograph the determined target area.

The object tracking system capable of analyzing the hybrid pattern based on acoustic and behavior pattern recognition based on this configuration recognizes not only the event detection information but also the acoustic frequency signal information of the fixed camera 100, .

FIG. 5 is a diagram illustrating an object tracking system capable of hybrid pattern analysis based on acoustic and behavior pattern recognition according to another embodiment of the present invention. 5, the stationary camera 100, the rotary camera 200, the flat speaker 400, the acoustic frequency recognition device 500, and the beacon wireless signal transceiver 600 are set up, The control device 300 may be installed separately in the external control center 3 and the control device 300 may be installed in the external control center 3 In this case, the external control center 3 or the control device 300 can manage or control all of the plurality of sets individually.

This prevents duplication of unnecessary resources and enables continuous and total management of crimes and accidents caused by the collective management and movement of the sites.

Meanwhile, the network 2 is a communication network which is a high-speed period network of a large communication network capable of a large-capacity, long-distance voice and data service, and may be a next generation wired and wireless network for providing Internet or high-speed multimedia service. When the network 2 is a mobile communication network, it may be a synchronous mobile communication network or an asynchronous mobile communication network. As an embodiment of the asynchronous mobile communication network, a WCDMA (Wideband Code Division Multiple Access) communication network is exemplified. In this case, although not shown in the drawings, the network 2 may include a Radio Network Controller (RNC). Meanwhile, although the WCDMA network is exemplified, it may be a next generation communication network such as a 3G LTE network or a 4G network, or an IP network based on other IP. The network 2 is connected to the control center 3 and is connected to the stationary camera 100 of the sites 1-1, 1-2, ..., 1-m around the monitored area, The first to m-th mobile terminals 4-1 to 4-m, m are natural numbers of 2 or more), and the beacon signal transmitting / And transmits signals and data between the external systems.

The controller 300 of the control center 3 enlarges the image of the position where the emergency situation has occurred through the portable camera 200 and sends warning broadcast through the directional flat speaker 400 to the area This can reduce the complaints of nearby residents.

The control device 300 of the control center 3 is set so as to receive a beacon radio signal from the mobile terminal that has executed the safety-restricting application among the mobile terminals 1-1 to 1-m, The beacon radio signal transmitting and receiving unit 600 of each of the peripheral sites 1-1, 1-2, ..., 1-m of the area is received via the network 2, To the mobile terminal.

When the emergency terminal is input to the mobile terminal that has executed the safe e-mail application among the mobile terminals 4-1 to 4-m, the control device 300 of the control center 3 transmits a beacon signal And outputs the beacon signal to the beacon radio signal transmitting and receiving unit 600. The beacon radio signal transmitting and receiving unit 600 extracts the identification number of the beacon radio signal transmitting and receiving unit 600, Perform emergency reporting to the nearest crime prevention center.

The present invention can also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device and the like, and also implemented in the form of a carrier wave (for example, transmission over the Internet) .

The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner. And functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers skilled in the art to which the present invention pertains.

As described above, preferred embodiments of the present invention have been disclosed in the present specification and drawings, and although specific terms have been used, they have been used only in a general sense to easily describe the technical contents of the present invention and to facilitate understanding of the invention , And are not intended to limit the scope of the present invention. It is to be understood by those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

1-1 to 1-m: field
2: Network
3: Control center
4-1 to 4-m: first to mth mobile terminals
100: Fixed type camera
100G (100-1 to 100-N): fixed camera aggregate
200: Rotating camera
200G (200-1 to 200-N): a rotatable camera assembly
300: Control device
310:
320: Moving object recognition unit
330: pattern analysis unit
340: Message DB section
350:
400: directional flat speaker
400G (400-1 to 400-N): directional flat panel speaker assembly
500: Speech recognition frequency device
500G (500-1 to 500-N): Speech recognition frequency device aggregate
600: Beacon radio signal transmitting /
600G (600-1 to 600-N): beacon radio signal transmitting / receiving subunit

Claims (5)

A first step in which one acoustic frequency recognition device senses a step sound of a predetermined range of frequencies;
A second step of determining whether or not an acoustic event is generated by analyzing whether the acoustic frequency recognition device determines that the terminal sound is equal to or greater than a preset threshold value dB;
A third step of, when the acoustic event occurs, generating a voice event occurrence information by the acoustic frequency recognition device and transmitting the voice event occurrence information to the control device;
A fourth step of receiving the monophonic sound frequency information from the sound frequency recognition device which senses the received monophonic sound for the purpose of analyzing whether the emergency situation occurs or not in order to start the analysis of the emergency situation;
A fifth step of receiving the video event information from the fixed photographing device located in the same area as the acoustic frequency recognition device in which the control device senses the phoneme;
A sixth step of analyzing an emergency situation of a subject through the voice event occurrence information and the video event information and generating information about a target area or a target object to be photographed by the rotary camera in an emergency situation;
A seventh step of transmitting the information about the target area or the target object determined by the control device to a rotating camera located in the same area as the sound frequency recognizing device that senses the sound;
An eighth step of causing the rotary camera to shoot an object area or a target object determined by the control device to generate event photographing information and return the event photographing information to the control device; And
Generating an event analysis value by using the event shooting information received by the control device, and outputting a message matching the event analysis value to the flat speaker; / RTI >
The fifth step includes a step 5-1) of analyzing the received monophonic sound frequency information by the controller to determine whether the monophonic sound corresponds to the sound frequency of the help request;
When the monaural sound corresponds to the sound frequency requested for assistance, the control device performs the first image event detection. After calculating the direction of the received monaural sound frequency signal, Based event detection event image) from the image captured by the control unit. On the other hand, when the terminal sound does not correspond to the assist request sound frequency, the controller analyzes the received sound end frequency information (5-2) judging whether or not the monophonic sound corresponds to an acoustic frequency (whistle sound frequency) generated by the help requesting tool; And
If the monaural sound corresponds to the acoustic frequency (whistle sound frequency) generated by the help requesting tool, the control device performs the second image event detection (event extraction of the emergency event image based on the subject and the help request tool) The second image event detection is performed from the image captured by the fixed camera disposed in the area matched with the direction after calculating the direction of the received end sound emission frequency signal. On the contrary, if the sound emission does not correspond to the whistle sound frequency, A fifth step of the controller performing the third video event detection (two subject-based emergency situation occurrence video event extraction); / RTI >
In the sixth step,
Wherein when the control device senses at least one of the first to third video events and the sound source is a monaural assisted sound frequency in the fifth step, the controller analyzes the emergency scene of the subject, Or determines the target object as the direction of the acoustic frequency signal (i.e., the direction in which the acoustic frequency signal is sensed)
In the ninth step,
When the control device generates the event analysis value using the event shooting information, the event analysis value includes a 'help event analysis value' matching the first video event, a 'help request tool (whistle) event matching the second video event Analytic value ', a' violent event event analysis value 'matching with the third video event, and a' normal event analysis value 'matching with other normal events, and the normal event analysis value is classified into' (A situation where the moving object moves around the main entrance of the access control area and there is a possibility that the moving object may be stolen when the moving object is wandering for a certain period of time or stopped for a predetermined time while facing the main entrance) A method of object tracking capable of hybrid pattern analysis based on acoustic and behavior pattern recognition.
The method of claim 1,
(9-1) determining whether the event analysis value generated by the controller is plural or not;
(9-2) selecting a highest priority event analysis value according to a priority among a plurality of event analysis values when a plurality of moving objects are identified in a target area in which the control device is determined to be photographed;
A step 9-3 of the controller extracting a message corresponding to the selected event analysis value;
The controller transmits the sound information corresponding to the extracted message to the flat speaker; And
(9-5) the speaker receiving the sound information and outputting the sound information as a sound or an alarm sound; Further comprising:
Wherein the priority is set through a sequence of 'help event analysis value', 'help request tool (whistle) event analysis value', violence event analysis value ', and' normal event analysis value ' An object tracking method capable of hybrid pattern analysis based on behavior pattern recognition.
The method according to claim 1,
When a fixed camera, a rotary camera, a speaker, an acoustic frequency recognition device, and a beacon wireless signal transmission / reception unit are set and installed at a site in the vicinity of a confirmed monitored area, and the control device is installed separately in an external control center,
The controller of the control center is set so as to receive a beacon radio signal from a mobile terminal that has executed a safe-ear application of each mobile terminal, and controls the beacon radio signal transmitting / receiving unit in each of the surrounding areas of the monitored area, And then transmitting a transmission ear position to a mobile terminal of a predetermined destination. The object tracking method according to claim 1,
delete delete

Images