JP2011243054A - Crime prevention device and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a crime prevention device and program capable of preventing occurrence of a crime more effectively.SOLUTION: The crime prevention device 20 detects a location of a person who is present in the object area at prescribed time intervals on the basis of image information obtained by imaging an inside of a monitoring object building 90 with a camera 42, and on the other hand, specifies whether or not the detected person is an unspecified person other than a predetermined guard and guarded person, to detect a behavior state of a person specified as an unspecified person on the basis of the detected location of the unspecified person, derive a degree of suspiciousness of the unspecified person on the basis of the detected behavior state, calculate a crime risk value showing a level of crime risk to the guarded person by the unspecified person based on the derived degree of suspiciousness, and execute predetermined processing for preventing a crime, using the calculated crime risk value.

Description

  The present invention relates to a crime prevention device and a program.

  Conventionally, for the purpose of providing a crime prevention device capable of preventing crime more efficiently, Patent Document 1 by the present applicant obtains image information of the target area in real time by photographing the target area. Based on the acquired image information, while detecting the position of the person existing in the target area at a predetermined time interval, the detected person is identified as a defender, a defender, and an indeterminate person, Based on the position of the detected person and the specific result, a first distance that is a distance between the defender and the defender, and a second distance that is a distance between the indefinite person and the defender. Based on the ratio of the derived first distance and second distance, a crime risk value indicating the crime risk level by the indefinite person for the defender is calculated, and the crime risk value is used. To prevent crime Crime prevention device for executing predetermined processing Te have been disclosed.

JP 2009-140264 A

  However, in the technique disclosed in Patent Document 1, the indefinite person does not necessarily commit a crime against the defender. Since the crime risk value is calculated and applied in the same way for unidentified persons, it is not always possible to obtain the crime risk value accurately, and it is not always possible to effectively prevent the occurrence of crime, There was a problem.

  The present invention has been made to solve the above problems, and an object of the present invention is to provide a crime prevention apparatus and program that can more effectively prevent the occurrence of crime.

  In order to achieve the above object, the crime prevention apparatus according to claim 1 is based on imaging means for acquiring image information of the target area by imaging the target area, and image information acquired by the imaging means. Detecting means for detecting a position of a person existing in the target area at predetermined time intervals, and whether or not the person detected by the detecting means is a predetermined defender and an indefinite person excluding a defender. A specifying means for specifying, a detecting means for detecting a behavioral state of the indeterminate person based on a position detected by the detecting means of the person specified as the indeterminate person by the specifying means, and detected by the detecting means Deriving means for deriving the suspicious degree of the unidentified person based on the behavioral state, and a crime by the unidentified person against the defender based on the suspicious degree derived by the deriving means A calculation means for calculating a crime risk value indicating the height of the screen, and an execution means for executing a process predetermined to prevent crime using the crime risk value calculated by the calculation means. ing.

  According to the crime prevention apparatus according to claim 1, the image information of the target area is obtained by photographing the target area by the photographing unit, and based on the image information obtained by the photographing unit by the detecting unit, While the position of the person existing in the target area is detected at predetermined time intervals, whether or not the person detected by the detecting means by the specifying means is a predetermined defender or an indefinite person excluding the defender Is identified.

  Here, in the present invention, the behavior state of the indeterminate is detected by the detection means based on the position detected by the detection means of the person identified as the indeterminate by the specifying means, and the derivation means The suspicious degree of the unidentified person is derived based on the behavior state detected by the detecting means, and the crime risk by the unidentified person against the defender based on the suspicious degree derived by the calculating means by the calculating means. The crime risk value indicating the height of the is calculated.

  In the present invention, the execution unit executes a predetermined process for preventing crime using the crime risk value calculated by the calculation unit.

  Thus, according to the crime prevention apparatus according to claim 1, on the basis of the image information acquired by photographing the target area, the position of the person existing in the target area is detected at predetermined time intervals, Identify whether or not the detected person is an indefinite person excluding a predetermined defender and defender, and based on the detected position of the person identified as the indefinite person, the behavior state of the indefinite person And detecting a suspicious degree of the undetermined person based on the detected behavior state, and calculating a crime risk value indicating a crime risk level by the undetermined person for the defender based on the derived suspicious degree. Since the predetermined crime processing is performed using the calculated crime risk value to prevent crime, compared to the case where the suspicious degree of the unidentified person according to the behavioral state of the unidentified person is not used. Crime more effectively It is possible to prevent the occurrence.

  In the present invention, as in the invention described in claim 2, the behavior state of the person detected based on the position of the person existing in the target region and the suspicious degree corresponding to the behavior state are associated with each other. Storage means stored in advance, and the derivation means reads out the suspicious degree corresponding to the behavior state detected by the detection means from the storage means, thereby deriving the suspicious degree of the unidentified person. Good. Thereby, generation | occurrence | production of a crime can be prevented more simply. The storage means includes a RAM (Random Access Memory), an EEPROM (Electrically Erasable and Programmable Read Only Memory), a semiconductor storage element such as a flash EEPROM (Flash EEPROM), a portable recording medium such as a flexible disk, a hard disk, etc. Or an external storage device provided in a server computer connected to a network.

  Further, according to the present invention, as in the invention according to claim 3, the indefinite person enters the admission permitted area in which only the defender and the defensive person are allowed to enter in advance. A first behavioral state indicating whether or not the second behavioral state indicating whether or not the unsettled person has stayed in the target area for a predetermined time or more, and the unsettled person is the defender or It may include at least one of third action states indicating whether or not the defender is acting together.

  Further, according to the present invention, as in the invention described in claim 4, the specifying means determines whether the person detected by the detecting means is the defender, the defender, or the indefinite person. A first distance which is a distance between the defender and the defender, and the indefinite person and the defender based on the position of the person detected by the detection means and the identification result by the identification means A distance deriving unit for deriving a second distance which is a distance of the first distance, and the computing unit is derived by the ratio of the first distance and the second distance derived by the distance deriving unit and by the deriving unit. The crime risk value may be calculated based on the suspicious degree. As a result, the defender can be effectively used, and as a result, crime can be prevented more efficiently.

  In particular, according to the fourth aspect of the present invention, the amount of change between the first distance derived by the distance deriving unit at the present time and the first distance derived by the distance deriving unit at the time before the predetermined time is calculated. And predicting the distance between the defender and the defender after the predetermined time based on the second distance derived by the distance deriving means at the present time and deriving by the distance deriving means before the predetermined time A distance predicting unit that predicts a distance between the indeterminate person and the defender after the predetermined time based on the amount of change from the second distance, and the computing unit is predicted by the distance predicting unit. Further, the crime risk value may be calculated based on a distance between the defender and the defender, a ratio of the distance between the indeterminate person and the defender, and a suspicious degree derived by the deriving means. . Thereby, as a result of being able to predict the crime risk value after the predetermined time, the occurrence of crime can be prevented more immediately.

  Further, the invention according to claim 4 is the same as the invention according to claim 5, wherein the first arrival time, which is the time for the defender to reach the defender based on the first distance, is set. And an arrival time deriving unit for deriving a second arrival time which is a time for the indeterminate person to reach the defender based on the second distance, and the calculation unit includes the arrival time. The crime risk value may be calculated based on a ratio between the first arrival time and the second arrival time derived by the deriving unit and the suspicious degree derived by the deriving unit. Thereby, the occurrence of crime can be prevented with higher accuracy.

  In particular, the invention according to claim 5 is characterized in that the first arrival time derived by the arrival time deriving means at the present time and the first arrival time derived by the arrival time deriving means at the time before the predetermined time, And predicting the time when the defender reaches the defender after the predetermined time based on the change amount of the second time and the second arrival time derived by the arrival time deriving means at the present time It further comprises arrival time predicting means for predicting the time when the indeterminate person reaches the defender after the predetermined time based on the amount of change from the second arrival time derived by the arrival time deriving means at the time. A ratio between a time when the defender arrives at the defender predicted by the arrival time predicting means and a time when the indefinite person arrives at the defender; It may be calculated the crime risk value based on the suspiciousness degree derived by. Thereby, as a result of being able to predict the crime risk value after the predetermined time, the occurrence of crime can be prevented more immediately.

  The invention according to claim 4 or 5 further includes a traveling direction deriving unit for deriving the traveling direction of the defender and the traveling direction of the indeterminate person, and the computing unit includes the traveling direction deriving unit. The crime risk value may be calculated so that the value increases as the traveling direction of the indeterminate is closer to the traveling direction of the defensive person derived by the above. Thereby, the occurrence of crime can be prevented with higher accuracy.

  In addition, the present invention identifies defender identification information which is information for identifying the defender given in advance to the defender, and identifies the defender given in advance to the defender Identification information storage means for preliminarily storing defender identification information, which is information for performing, and obtaining any identification information of the defender identification information and the defender identification information from the person detected by the detection means And when the identification information acquired by the acquisition unit matches the defender identification information stored in the identification information storage unit, the acquisition unit of the identification information is acquired. When the person is identified as a defender and the identification information acquired by the acquisition means matches the defender identification information stored in the identification information storage means, the identification information Retrieve the human is identified as an object to be defensive person may be identified as another person is indefinite person. Thereby, a defender, a defender, and an indefinite person can be specified more reliably, and as a result, the occurrence of a crime can be prevented with higher accuracy.

  Further, according to the present invention, as the predetermined process, the execution means stores at least one of the crime risk value and the suspicious degree, and displays at least one of the crime risk value and the suspicious degree. , A process of issuing a warning when at least one of the crime risk value and the suspicious degree is equal to or greater than a predetermined threshold, and a process of notifying the defender closest to the target defender that the crime risk is high In addition, at least one process of notifying the defender closest to the unidentified person whose suspicious degree is equal to or greater than the predetermined threshold that there is an unidentified person with a high suspicious degree nearby may be executed. . Thereby, the effect according to the applied process can be acquired.

  On the other hand, in order to achieve the above object, the program according to claim 6, based on the image information acquired by the imaging unit that acquires the image information of the target area by imaging the target area, Detecting means for detecting the position of a person existing in the target area at predetermined time intervals, and specifying whether the person detected by the detecting means is a predetermined defender and an indeterminate person excluding the defender Based on the position detected by the detecting means of the person identified as the indeterminate person by the specifying means, the detecting means for detecting the action state of the indeterminate person, and the action state detected by the detecting means The derivation means for deriving the suspicious degree of the unidentified person based on the suspicious person, and the suspicious person derived from the suspicious degree derived by the derivation means by the unidentified person A calculation means for calculating a crime risk value indicating the height of the crime risk, and an execution means for executing a predetermined process for preventing crime using the crime risk value calculated by the calculation means, It is for functioning.

  Therefore, according to the program described in claim 6, since the computer can be caused to act in the same manner as in the invention described in claim 1, as in the invention described in claim 1, the crime can be generated more effectively. Can be prevented.

  According to the present invention, based on image information acquired by photographing a target area, the position of a person existing in the target area is detected at predetermined time intervals, while the detected person is determined in advance. Identifies whether the person is an indeterminate person except the defender and the defender, detects the indeterminate person's behavioral state based on the detected position of the person identified as the indeterminate person, and based on the detected behavioral state The suspicious degree of the undetermined person is derived, a crime risk value indicating the crime risk level by the undetermined person for the defender is calculated based on the derived suspicious degree, and the crime risk value is calculated using the calculated crime risk value. Since the predetermined process is executed to prevent the occurrence of crime, the occurrence of crime is more effectively prevented compared to the case where the suspicious degree of the indeterminate person according to the behavior state of the indefinite person is not used. Can, and Cormorants effect can be obtained.

It is a block diagram which shows the whole structure of the crime prevention system which concerns on embodiment. It is a top view which shows the structure of the building which the crime prevention system which concerns on embodiment makes into the monitoring object. It is a side view which shows the layout of the building which the crime prevention system which concerns on embodiment makes into the monitoring object, and the arrangement position of the various equipment which a crime prevention system has. It is a block diagram which shows the principal part structure of the electric system of the crime prevention apparatus which concerns on embodiment. It is a schematic diagram which shows the main memory content of the secondary memory | storage part with which the crime prevention apparatus which concerns on embodiment was equipped. It is a schematic diagram which shows the structure of the identification information database which concerns on embodiment. It is a schematic diagram which shows the structure of the attribute information database which concerns on embodiment. It is a schematic diagram which shows the structure of the positional infomation database which concerns on embodiment. It is a schematic diagram which shows the structure of the 1st suspiciousness database which concerns on embodiment. It is a schematic diagram which shows the structure of the 2nd suspiciousness database which concerns on embodiment. It is a schematic diagram which shows the structure of the crime risk value database which concerns on embodiment. It is a flowchart which shows the flow of a process of the processing program according to the visitor layer which concerns on embodiment. It is the schematic which shows an example of the display state of the initial screen which concerns on embodiment. It is a flowchart which shows the flow of a process of the crime prevention process program which concerns on 1st Embodiment. It is a schematic diagram with which it uses for description of the process by the crime prevention process program which concerns on 1st Embodiment. It is a flowchart which shows the flow of a process of the crime prevention process program which concerns on 2nd Embodiment. It is a schematic diagram with which it uses for description of the process by the crime prevention process program which concerns on 2nd Embodiment.

  DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the drawings. Here, a case will be described in which the present invention is applied to a crime prevention system in which an office building is a monitoring target building (hereinafter referred to as a “monitoring target building”).

[First Embodiment]
First, the configuration of a crime prevention system 10 to which the present invention is applied will be described with reference to FIGS.

  As shown in FIGS. 1 to 3, the crime prevention system 10 according to this embodiment includes a crime prevention device 20 that plays a central role in the system 10. In the crime prevention system 10 according to the present embodiment, the crime prevention device 20 is installed in the server room 85 in which the server device 85A of the monitoring target building 90 is installed. Or a building other than the monitoring target building 90 or the like.

  On the other hand, the crime prevention system 10 according to the present embodiment includes an operation panel 30 including a display unit 30A, an operation unit 30B, and an alarm unit 30C, and a video camera (hereinafter referred to as “camera”) capable of capturing a moving image. 40), a card reader 50 that reads information stored in an ID (Identification) card 52 described later, and a locking / unlocking unit 60 that locks and unlocks the door 80B described later.

  As shown in FIGS. 2 and 3, the monitored building 90 according to the present embodiment needs to pass through the hall 80 when entering the inside of the monitored building 90.

  The hall 80 includes a door 80 </ b> A that communicates with the hall 80 from the outside, and a door 80 </ b> B that communicates with the interior of the monitoring target building 90 from the hall 80. Here, the door 80A can be opened and closed without any particular restriction, while the locking / unlocking portion 60 described above is provided in the vicinity of the door 80B, and the locking and unlocking thereof are unlocked. This is performed by the lock unit 60.

  By the way, in the crime prevention system 10 according to the present embodiment, a person who can enter the monitored building 90 indefinitely belongs to a predetermined permitter (here, a company occupying the monitored building 90). Only those who are permitted to be given to the authorized person, and are registered in advance in a secondary storage unit 20D (see also FIG. 4) of the crime prevention apparatus 20 described later. An ID card 52 in which identification information is stored is distributed.

  The card reader 50 described above is provided in the vicinity of the door 80B of the hall 80. When the permitter goes out of the monitored building 90, the permitter can carry the hall by carrying the ID card 52. When entering the inside of the monitoring target building 90 from 80, the crime prevention device 20 obtains identification information from the ID card 52 carried by the permitter via the card reader 50 and authenticates (Authentication). I am doing so.

  In the present embodiment, the ID card 52 is a non-contact type ID that allows the card reader 50 to read the identification information by holding it over a predetermined information reading unit (not shown) of the card reader 50. Although the card is applied, the present invention is not limited to this, and another ID card such as a contact type ID card may be applied.

  On the other hand, as shown in FIGS. 2 and 3, the operation panel 30 described above is provided in the vicinity of the door 80B of the hall 80, and the camera 40 described above is provided on the ceiling surface of the hole 80 and in the vicinity of the door 80B. Is provided.

  In addition to the above-described authentication using the ID card 52, the permitter inputs the identification information stored in the ID card 52 distributed to him / her through the operation unit 30B of the operation panel 30, thereby preventing the crime. Authentication by 20 can also be received.

  Further, the camera 40 can shoot substantially the entire area of the hall 80. In the crime prevention system 10 according to the present embodiment, the shooting range of the camera 40 is such that at least a person 70 entering the monitored building 90 holds the ID card 52 over the information reading unit of the card reader 50. The installation position and the installation angle of the camera 40 are set in advance so as to include an area that is positioned when the authentication procedure is performed by inputting identification information via the operation unit 30B of the operation panel 30. .

  As shown in FIG. 1, an operation panel 30 is electrically connected to the crime prevention apparatus 20, and the crime prevention apparatus 20 displays various information on the display unit 30A of the operation panel 30, and displays the operation unit 30B. It is possible to grasp the details of the operation performed and to output an alarm by the alarm unit 30C.

  The crime prevention apparatus 20 is also electrically connected to the camera 40, and the crime prevention apparatus 20 can input image information obtained by photographing with the camera 40. In the crime prevention system 10 according to the present embodiment, the camera 40 is always operated, and image information indicating a moving image obtained by shooting from the camera 40 is always input to the crime prevention device 20. .

  Further, the card reader 50 is also electrically connected to the crime prevention device 20, and the crime prevention device 20 can input the identification information read by the card reader 50. Furthermore, the crime prevention device 20 is also electrically connected to the locking / unlocking unit 60, and the crime prevention device 20 can remotely control the locking and unlocking of the door 80B via the locking / unlocking unit 60.

  On the other hand, as shown in FIG. 2, the monitoring target building 90 according to the present embodiment includes meeting rooms 82A to 82D, reception rooms 83A to 83C, general offices 84A to 84C, server room 85, safe room 86, and president's room. Each of the 87 rooms, the staircases 88A to 88B, and the corridors 89A to 89F are partitioned by walls.

  In these partitioned areas, video cameras (hereinafter referred to as “cameras”) 42 capable of capturing moving images are provided on the respective ceiling surfaces, and each camera 42 is provided. The vicinity of the arrangement position in the partitioned area can be photographed.

  The crime prevention apparatus 20 according to the present embodiment is provided with an automatic tracking function for automatically tracking a person existing inside the monitoring target building 90 based on image information obtained by photographing with the camera 42. Each camera 42 has an installation position and a position of each camera 42 so that the vicinity of the end of the shooting range of the adjacent cameras 42 overlap each other, and each camera 42 can shoot a substantially entire area inside the monitoring target building 90. The installation angle is preset.

  As shown in FIG. 1, each camera 42 is also electrically connected to the crime prevention apparatus 20, and the crime prevention apparatus 20 inputs image information obtained by photographing by each camera 42 for each camera 42. be able to. Note that, in the crime prevention system 10 according to the present embodiment, the camera 42 is always operated similarly to the camera 40, and the crime prevention apparatus 20 shows a moving image obtained by shooting from the camera 42. Image information is always input.

  The crime prevention apparatus 20 according to the present embodiment recognizes whether or not a person exists in the image indicated by the image information based on the image information input from the camera 40 and the camera 42. It has a human position detection function for deriving presence position information indicating a presence position when it exists.

  In the crime prevention apparatus 20 according to the present embodiment, the recognition as to whether or not the person exists is recognized by the image indicated by the image information input from the camera 40 and the camera 42 in a substantially circular shape and a person. The area of the size determined in advance within the plane area of the head of the head is black, brown, white, gold, etc. When there is a region that occupies more than half of the area, it is performed by recognizing that the region exists as a human region, and this is not limited to this. It is good also as a form performed by applying a technique. Further, in the crime prevention apparatus 20 according to the present embodiment, the position information indicating the position of the person is configured so that the planar shapes of all the areas to be photographed by the camera 40 and the camera 42 are the same size. A square is divided into a matrix, and is derived as coordinate information of an XY coordinate system with a predetermined square position as an origin (0, 0).

  In the crime prevention apparatus 20 according to the present embodiment, the above-described automatic tracking function is performed based on the image information input from the camera 40 and the camera 42, and the person region specified by the person position detection function based on the image information. This is realized by using a so-called feature point tracking algorithm that extracts and tracks a predetermined feature point from.

  Note that the feature point tracking algorithm is described in many documents such as Japanese Patent Application Laid-Open No. 2009-20800, and is well known in the art, so detailed description thereof is omitted here.

  Furthermore, an interphone 44 (not shown in FIG. 2; see FIG. 1) is provided in each room of the monitored building 90, and all the interphones 44 are electrically connected to the crime prevention apparatus 20.

  Each room of the monitoring target building 90 is given a room number for identifying the room for each room in advance. The visiting visitor inputs the room number corresponding to the visited room via the operation unit 30B of the operation panel 30, so that the operation panel 30, the crime prevention apparatus 20, and the interphone 44 provided at the visited place You can talk to people in the room you are visiting.

  Each interphone 44 is provided with an unlocking button (not shown) that is pressed when unlocking the door 80B, and the interphone 44 is operated when the unlocking button is pressed. Unlock instruction information for instructing unlocking of the door 80B is transmitted to the crime prevention apparatus 20. And the crime prevention apparatus 20 will control the locking / unlocking part 60 so that the door 80B may be unlocked, when unlocking instruction information is received from any intercom 44.

  In crime prevention system 10 according to the present embodiment, door 80B is opened when unlocked by locking / unlocking portion 60, and after a predetermined period (5 seconds in the present embodiment) has elapsed. When there is no person within a predetermined distance of the door 80B (in this embodiment, the plane distance from the door 80B is within 1 m), the door 80B is closed and locked, while there is a person. The door 80B is closed and locked when the person no longer exists within the predetermined distance of the door 80B.

  Next, with reference to FIG. 4, the structure of the main part of the electrical system of the crime prevention apparatus 20 having a particularly important role in the present system will be described.

  As shown in the figure, the crime prevention apparatus 20 according to the present embodiment includes a CPU (central processing unit) 20A that controls the operation of the crime prevention apparatus 20 as a whole and a work area when the CPU 20A executes various processing programs. A RAM 20B used, a ROM 20C in which various control programs, various parameters, and the like are stored in advance, a secondary storage unit (here, a hard disk device) 20D as a storage means used for storing various information, and various information A keyboard 20E used for inputting, a display 20F used for displaying various kinds of information, and an input / output I / F (interface) 20G for exchanging various signals between external devices and the like are provided. These parts are electrically connected to each other by a system bus BUS.

  Accordingly, the CPU 20A accesses the RAM 20B, ROM 20C, and secondary storage unit 20D, acquires various input information via the keyboard 20E, displays various information on the display 20F, and external devices via the input / output I / F 20G. Various signals can be exchanged between the two. The operation panel 30, the camera 40, the camera 42, the intercom 44, the card reader 50, and the locking / unlocking unit 60 are electrically connected to the crime prevention apparatus 20 via the input / output I / F 20G.

  On the other hand, FIG. 5 schematically shows the main storage contents of the secondary storage unit 20D provided in the crime prevention apparatus 20.

  As shown in the figure, the secondary storage unit 20D is provided with a database area DB for storing various databases and a program area PG for storing various applications and programs.

  The database area DB includes an identification information database DB1, an attribute information database DB2, a position information database DB3, a first suspicious degree database DB4, a second suspicious degree database DB5, and a crime risk value database DB6. Hereinafter, the configuration of each database will be described in detail.

  In the crime prevention system 10 according to the present embodiment, a person who wants to protect the authorized person from crime (hereinafter referred to as “guardian”) and a person (hereinafter referred to as “crime prevention”) for preventing crimes against the defender. , "Defender").

  The identification information database DB1 is for storing information for specifying whether the permitter is a defender or a defender. As an example, as shown in FIG. Information and each type of information are configured to be stored for each of the permitters targeted in the crime prevention apparatus 20.

  The type is information indicating whether the person who has the ID card 52 in which the corresponding identification information is stored is a defender or a defender. In the example shown in FIG. 6, for example, the person who has the ID card 52 storing the identification information “10001” is the “defender” and the ID card storing the identification information “20003”. The person who possesses 52 indicates that it is a 'guardian'.

  On the other hand, as shown in FIG. 7 as an example, the attribute information database DB2 is configured such that the identification information and attributes are stored for each permitter.

  The attribute is information indicating the characteristics of the authorized person who has the ID card 52 storing the corresponding identification information. In the attribute information database DB2 according to the present embodiment, as shown in FIG. , Gender, height, and status information. In the example shown in FIG. 7, for example, the permitter possessing the ID card 52 storing the identification information “10001” is a 65-year-old male president who is 170 cm tall, “10002” The person who possesses the ID card 52 storing the identification information is a 20-year-old female general employee with a height of 155 cm, and possesses the ID card 52 storing the identification information of “20001”. Is shown to be a 24-year-old male guard with a height of 183 cm.

  On the other hand, as shown in FIG. 8 as an example, the position information database DB3 is configured such that information on camera ID, pixel position, and position coordinates is stored for each of the camera 40 and the camera 42. Yes.

  The camera ID is given in advance as different information (information combining alphabets and numbers in the present embodiment) for each camera in order to identify the camera 40 and the camera 42.

  In the crime prevention system 10 according to the present embodiment, the camera 40 and the camera 42 are fixed in a predetermined range by fixing the installation position, the shooting direction, and the enlargement ratio. In this state, the pixel position by the solid-state imaging device incorporated in the camera 40 and the camera 42 and the corresponding position coordinate in the XY coordinate system are stored in association with each other, and based on this information, the camera 40 and the position of a person existing in the image of the imaging target area indicated by the image information obtained from the camera 42 is specified.

  The pixel position and the position coordinate in the position information database DB3 correspond to the pixel position by the solid-state imaging device and the position coordinate in the XY coordinate system, and the camera 40 and the camera 42 are referred to by referring to these information. Thus, the position of a person existing in the image photographed can be specified as the position in the XY coordinate system.

  In the position information database DB3 according to the present embodiment, as shown in FIG. 8, a pair of diagonal coordinates of a rectangular pixel area (imaging area) in the solid-state imaging device is used as the pixel position. The position of the person in the XY coordinate system is specified by applying the value and referring to the position coordinates corresponding to the pixel area in which the person's area existing most in the captured image is included. As described above, in the present embodiment, information having a predetermined range is applied as the pixel position. However, the present invention is not limited to this, and for example, one point of the pixel region in the solid-state imaging device is used as the pixel position. And the position coordinates corresponding to the pixel position closest to the predetermined position (for example, the center of gravity of the whole body, the center position of the head, etc.) of the person in the captured image is set as the XY of the person. Needless to say, it is possible to adopt a form specified as a position in the coordinate system.

On the other hand, the first suspiciousness degree database DB4, as shown in FIG. 9 as an example, admission during the action state, identifier, and the information of the first suspiciousness degree P _a is configured to be stored.

  The behavioral state at the time of entering the building is information indicating the behavioral state at the time of entry of the visitor 70 to the inside of the monitored building 90, and as shown in the figure, the crime prevention system 10 according to the present embodiment. Then, the normal authentication based on the above-mentioned presentation of the ID card 52 or the input of identification information is performed to unlock the door 80B (hereinafter referred to as “automatic authentication state”), and a person in the visited room is called. A state where the door 80B is unlocked (hereinafter referred to as “manual authentication state”), and a state where the person who has been authenticated by any of the above is snuggled up to enter the house (hereinafter referred to as “cooperation state”). The three types of states are applied.

Further, the above identifier is information for identifying each of the action state (automatic authentication state, a manual authentication state, tailgating state), the first suspiciousness degree P _a in advance to the corresponding action state is information indicating a granted suspicious degree was, the crime prevention system 10 according to this embodiment, as the value of the first suspiciousness degree P _a is large, the degree of the person who performed the corresponding action state suspicious high Represents that.

In the example shown in FIG. 9, for example, the identifier given in advance to the automatic authentication state is “Y”, and the suspicious case is when the behavior state when the visitor enters the monitored building 90 is the automatic authentication state. indicates that degree P _a is "0", a pre-assigned identifier to the tailgating state 'N', behavioral state during admission of visitors to the monitored building 90 in tailgating state suspiciousness degree P _a in case of a show that is "1".

On the other hand, the second suspiciousness degree database DB5, as shown in FIG. 10 as an example, the tracking during the action state, and the information of the second suspiciousness degree P _t is configured to be stored.

  The behavior state at the time of tracking is information indicating the behavior state of a visitor who has entered the inside of the monitored building 90. As shown in the figure, in the crime prevention system 10 according to the present embodiment, A state in which a person with an identifier of “T” exists outside the permitted partition area (hereinafter referred to as “non-permitted area presence state”), and a time over which a person with the identifier of “T” is permitted The state where the person stays in the hall (hereinafter referred to as “non-permitted time stay state”), the person whose identifier is “N” does not act with the person whose identifier is “Y” (hereinafter, “ "Unauthenticated state") and four other states are applied.

  In the crime prevention system 10 according to the present embodiment, a partitioned area where only the authorized person may enter is determined in advance, and information indicating the partitioned area (hereinafter referred to as “entrance restricted area information”). It is stored in advance in a predetermined area of the secondary storage unit 20D. Further, in the crime prevention system 10 according to the present embodiment, information (hereinafter referred to as “the indefinite person”) other than the permitter (hereinafter referred to as “the indeterminate”) may indicate the time during which the visitor may stay. The stayable time information is stored in advance in a predetermined area of the secondary storage unit 20D. Then, in crime prevention system 10 according to the present embodiment, it is determined whether or not an indeterminate person whose identifier is set to “T” is in a non-permitted area presence state using the entrance restriction area information. Using the possible time information, it is determined whether or not an undefined person whose identifier is set to “T” is in a staying state for a non-permitted time.

On the other hand, the second suspicious degree _Pt is information indicating the degree of suspiciousness given in advance to the corresponding action state at the time of tracking. In the crime prevention system 10 according to the present embodiment, the second suspicious degree Pt. The larger the value of P _t, the higher the degree of suspiciousness of the person who performed the corresponding action state.

In the example shown in FIG. 10, disallowed regions present state, the prohibition time stay state, and the second suspiciousness degree P _t granted to three states of unauthenticated state are both '1' shown, second suspiciousness degree P _t granted to other state indicates that it is a '0'.

On the other hand, as shown in FIG. 11 as an example, the crime risk value database DB6 is configured so that crime risk values indicating the level of crime risk by each indefinite person for each defender are stored in chronological order. Has been. In the figure, t represents the current time, t-δt represents the time δt seconds before the present, and t + δt represents the time δt seconds after the present. Further, S ₁ , S ₂ ,... Represent different indeterminate persons, and V ₁ , V ₂ ,.

  Next, the operation of the crime prevention system 10 according to the present embodiment will be described.

  First, with reference to FIG. 12, the operation of the crime prevention system 10 when a visitor enters the monitoring target building 90 will be described. Note that FIG. 12 is a flowchart showing the flow of processing of the stratification program executed by the CPU 20A of the crime prevention apparatus 20 when it is detected that a person is present in the image information input from the camera 40. The program is stored in advance in the program area PG of the secondary storage unit 20D. Here, a case will be described in which the identification information database DB1, the position information database DB3, and the first suspiciousness database DB4 are constructed in advance in order to avoid complications.

  In step 100 in the figure, all information in the identification information database DB1 and the first suspiciousness database DB4 is read out, and information on the camera 40 is read out from the position information database DB3. In the next step 102, a predetermined initial screen is displayed. The display unit 30A of the operation panel 30 is controlled to display

  FIG. 13 shows an example of an initial screen displayed on the display unit 30A by the processing in step 102. As shown in the figure, on the initial screen according to the present embodiment, presentation of the ID card 52 (hereinafter referred to as “first action state”) and input of identification information (hereinafter referred to as “second action state”). ), And a message prompting execution of one of the three types of behavioral states of calling the person to be visited (hereinafter referred to as “third behavioral state”). In response to this, a visitor (hereinafter referred to as a “regular behavior execution visitor”) performs one of the three types of behavior states.

  Therefore, in the next step 104, it is detected as follows which of the three types of action states has been performed by the regular action execution entrant.

  That is, when the identification information stored in the ID card 52 is read by the card reader 50, it is determined that the first action state has been performed by the regular action execution visitor, and the operation part 30B of the operation panel 30 is used. When the identification information is input, it is determined that the second action state has been performed by the regular action execution visitor, and any room number is input via the operation unit 30B of the operation panel 30. It is determined that the third action state has been performed by the regular action execution admission person.

  In the next step 106, it is determined whether or not the behavior state detected by the processing in step 104 is the first behavior state or the second behavior state, that is, the automatic authentication state. The process proceeds to execute a predetermined automatic authentication process.

  In the crime prevention apparatus 20 according to the present embodiment, the automatic authentication process is executed as follows.

  That is, when the action state detected by the process of step 104 is the first action state, the identification information input via the card reader 50 is read from the identification information database DB1 by the process of step 100. It is determined whether or not the identification information exists, and only when it exists, the locking / unlocking unit 60 is controlled so as to unlock the door 80B assuming that the regular action execution admission person is the permitter.

  On the other hand, when the action state detected by the process of step 104 is the second action state, the identification number input via the operation unit 30B of the operation panel 30 is obtained by the process of step 100. It is determined whether or not it exists in the identification information read from the identification information database DB1, and only when it exists, unlocking is performed so that the regular action execution visitor is regarded as the above-mentioned permitter and unlocks the door 80B. The unit 60 is controlled.

  When the door 80B is unlocked by the above-described automatic authentication process, the door 80B is temporarily opened and then locked as described above. During the period, the vehicle passes through the position where the door 80B is disposed and enters the inside of the monitoring target building 90.

In the next step 110, the identification information read by the card reader 50 or the type corresponding to the identification information input via the operation unit 30B of the operation panel 30 is read from the identification information database DB1 by the process of step 100 above. acquires from the information, after the identifier and first suspiciousness degree P _a corresponding to the behavior condition detected by the processing of step 104 is acquired from the information read from the first suspiciousness degree database DB4 by the processing of step 100, acquired type, identifier, and the first suspiciousness degree P _a is stored in a predetermined area of the secondary storage unit 20D in association with the identification information, and then proceeds to step 116.

  On the other hand, if a negative determination is made in step 106, the action state detected by the process in step 104 is regarded as the third action state, and the process proceeds to step 112.

  In addition, when the third action state, that is, the manual authentication state is performed by the regular action execution entrance person, the person in the room corresponding to the room number input by the regular action execution entrance person is provided in the room. In the case where it is possible to confirm whether or not the regular action execution admission person is a person who can enter by talking with the regular action execution admission person via the intercom 44, The door 80B is instructed to be unlocked by pressing the unlock button provided on the intercom 44. Accordingly, the door 80B is locked in the closed state after being temporarily opened as described above, so that a regular action executing visitor can enter the door 80B during the period in which the door 80B is open. And enter the inside of the monitoring target building 90.

In step 112, identification information different from that of other visitors is newly given to the regular action execution visitors, and in the next step 114, the identification information is associated with the identification information and “undefined person” is set as the type. information indicating (in this embodiment, 'T') identifier corresponding to the manual authentication state and _(in this embodiment, '0.5') first suspiciousness degree P _a and the secondary storage unit 20D After storing in the predetermined area, the process proceeds to step 116.

  By the way, when the door 80B is opened as described above and the regular action execution visitor enters the monitored building 90, a person other than the regular action execution visitor approaches the regular action execution entrance person. There may be a situation where you enter the building (a shared state).

Therefore, in step 116, based on the detection result of the person position by the person position detection function using the image information input from the camera 40, another person (hereinafter, “ It is determined whether or not the person has entered the building.) If the determination is negative, the process proceeds to step 122 described later, whereas if the determination is affirmative, the process proceeds to step 118. New identification information different from that of other visitors is assigned to the person, and in the next step 120, information indicating “unknown person” as the type is associated with the identification information, and the accompanying state is supported. After storing the identifier (“N” in the present embodiment) and the first suspicious degree P _a (“1” in the present embodiment) in the predetermined area of the secondary storage unit 20D, the process proceeds to step 122. .

  In step 122, the feature point tracking process is started for a visitor who has been confirmed to enter the monitored building 90 by the above process, which is executed according to a predetermined feature point tracking algorithm by the automatic tracking function described above. After that, the program for categorizing visitors is terminated.

  Note that the feature point tracking process executed in step 122 is executed as an interrupt process every predetermined period (in this embodiment, 0.1 second), and image information input from each of the cameras 42. Is used to individually determine the location of all visitors in the monitored building 90, and the location information indicating the location (in this embodiment, XY defined by the location information database DB3). Information indicating the position on the coordinate system) is sequentially stored in real time in a predetermined area of the secondary storage unit 20D in association with the identification information given to the corresponding visitor.

  Next, the operation of the crime prevention system 10 when executing crime prevention processing will be described with reference to FIG. FIG. 14 is a flowchart showing the flow of the crime prevention processing program executed by the CPU 20A when an execution instruction is accepted via the keyboard 20E of the crime prevention device 20, etc. It is stored in advance in the program area PG of the storage unit 20D. Here, a case will be described in which the second suspiciousness database DB5 is constructed in advance in order to avoid complications.

  In step 200 in the figure, all the information in the second suspiciousness degree database DB5 is read, and in the next step 202, step 122 of the above-mentioned visitor stratification processing program relating to all visitors to the inside of the monitored building 90. The latest identification information and presence position information sequentially stored by the feature point tracking process started by the above process are read from the secondary storage unit 20D.

In the next step 204, the identification information and type stored by any of the steps 110, 114, and 120 of the above-mentioned visitor stratification processing program regarding all visitors to the inside of the monitored building 90 read identifier, and the first suspiciousness degree _{P a} from the secondary storage unit 20D.

In the next step 206, the distance between the defender and the defender specified by the identification information and type read out by the above processing is determined within a predetermined area (this embodiment) by the following equation (1). In the embodiment, all combinations of defenders and defenders existing in the same space such as continuous rooms and corridors are calculated and stored in a predetermined area of the secondary storage unit 20D. Note that in equation (1), t is the current _{time, X Vi} is the X coordinate in the X-Y coordinate system of the position of the i-th of the defensive's _{V i, Y Vi} is the i-th of the defensive person a Y-coordinate in the X-Y coordinate system of the position of the V _{i, X Gk} is the X coordinate in the X-Y coordinate system of the position of the k-th defensive's _{G k, Y Gk} is k th defensive's a Y-coordinate in the X-Y coordinate system of the position of the G _{k, D ViGk} (t) is the distance between the defensive's _{G k} and the defensive's _{V i} at the present time.

In the next step 208, the distance between the indeterminate person and the defensive person specified by the identification information and the type is determined within a predetermined area (in the present embodiment, within the same space by the following equation (2)). ) Are calculated for all combinations of indefinite persons and defenders, and stored in a predetermined area of the secondary storage unit 20D. In Equation (2), X _Sj is the X coordinate in the XY coordinate system of the position of the j-th indeterminate person S _j , and Y _Sj is the XY of the position of the j-th indeterminate person S _j. The Y coordinate in the coordinate system, and D _ViSj (t) is the distance between the defender V _i and the indefinite person S _j at the present time.

  In the next step 210, it is determined whether or not the execution of the processing in steps 202 to 208 is the first execution after the execution of the crime prevention processing program is started. If the determination is negative, the process proceeds to step 212.

In step 212, the following equation (3) and (4), the predetermined time .DELTA.t distance _{D ViGk} the defensive's _{G k} and the defense's _{V i} after (here one second) (t + .DELTA.t), undefined user A distance D _ViSj (t + δt) between S _j and the defender V _i is calculated (predicted). Here, D _ViGk (t−δt) in the equation (3) is a distance between the defender G _k and the defender V _i before the predetermined time δt from the current time, and D _ViSj (t−δt) in the equation (4). ) Is the distance between the indeterminate person S _j and the defender V _i before the predetermined time δt from the present time, and the value obtained and stored by the processing of the previous step 206 and step 208 is applied.

  In the calculation of step 212, it is necessary to apply the values obtained by the previous processing of step 206 and step 208 related to the same person to each of the defender, the defender, and the indeterminate. In this case, a person whose identification information obtained last time by the process of step 202 matches the identification information obtained this time may be applied as the same person.

As an example, as shown in FIG. 15 by the calculation of step 212, the distance D _ViGk (t + δt) is _determined according to the flow lines of the defender G _k , the defender V _i , and the indefinite person S _j. And the distance D _ViSj (t + δt) can be predicted with high accuracy.

In the next step 214, it is determined whether the behavior state at the time of tracking regarding the indeterminate person _Sj is any of the above-described non-permitted area existence state, non-permitted time stay state, unauthenticated state, or other state. To be specific.

That is, the above-described entrance restricted area information and stayable time information are read from the secondary storage unit 20D, and the section indicated by the entry restricted area information (the only authorized person may enter the position indicated by the presence position information). It is assumed that the indeterminate person S _j located inside the area) and having the identifier “T” is in the non-permitted area existence state, and the time (indeterminate person It is assumed that the indeterminate person S _j who has stayed longer than the time (which may stay in the monitoring target building 90) and whose identifier is “T” is in the staying state during the non-permitted time. As described above, in the crime prevention system 10 according to the present embodiment, the non-permitted time stay state using the indefinite person's stay time in the hall is applied as the behavior state at the time of tracking. When the feature point tracking process for the indeterminate person is started in the processing program, the time at that time is stored in the secondary storage unit 20D in association with the identification information given to the indefinite person.

On the other hand, the distance from the regular action execution person who entered the inside of the monitored building 90 is not located within a predetermined distance (2 m in the present embodiment), and the identifier is “N”. It is assumed that a certain unidentified person S _j is in an unauthenticated state, and an undefined person S _{j that} is not in any of the non-permitted area existence state, the non-permitted time stay state, and the unauthenticated state is in another state. .

  At this time, the indeterminate person whose identifier is 'T' may be in the two states of the non-permitted area existence state and the non-permitted time stay state. In this case, according to a predetermined priority order, It is assumed that it is one of these states. The priority order at this time may be fixed in advance, but may be appropriately set according to the use of the crime prevention system 10 or the crime type targeted for crime prevention.

In the next step 216, specified by the processing of step 214, information of the second suspiciousness degree P _t corresponding to the action state of the indefinite's S _j, read from the second suspiciousness degree database DB5 by the processing of step 200 And is stored in a predetermined area of the secondary storage unit 20D in association with the identification information of the corresponding indeterminate person _Sj .

In the next step 218, a first suspiciousness degree _{P a} obtained by the process of step 204, the distance obtained by the process of step 212 _{D ViGk} (t + δt) and the distance _{D ViSj} (t + _δt), the step 216 The crime risk value R _ij (t + δt) indicating the level of crime risk against the defender V _i by the indeterminate person S _j after a predetermined time δt is calculated based on the second suspicious degree P _t obtained by the process of And stored (registered) in the crime risk value database DB6.

In the crime prevention processing program according to the present embodiment, the crime risk value R _ij (t + δt) is calculated as follows.

First, the provisional crime risk value R _ij ′ (t + δt) is calculated by substituting the distance D _ViGk (t + δt) and the distance D _ViSj (t + δt) into the following equation (5). Here, min _k () in the expression (5) is a function indicating that the minimum value for all k of the calculation results in parentheses is applied.

Further, the coefficient _CR is calculated by the following equation (6). Here, _{C 1} is in (6), a coefficient for adjusting the crime risk value is the value of the temporary crime risk value _{R ij '(t + δt)} = 1 crime risk value _R ij in the case of (t + .DELTA.t).

Further, by substituting the corresponding first suspiciousness degree P _a and the second suspiciousness degree P _t to the next equation (7), calculates the overall suspiciousness degree P _j indefinite's S _j.

Then, the crime risk value R _ij (t + δt) is calculated by substituting the provisional crime risk value R _ij ′ (t + δt), coefficient C _R , and suspicious degree P _j obtained as described above into the following equation (8). To do.

Incidentally, normally by applying a 0.5 as a coefficient _{C 1,} the coefficient _{C R} -1. Thereby, the equation (8) is transformed into the following equation (9).

In the next step 220, the crime risk value R _ij (t + δt) obtained by the process of step 218 is used to execute a predetermined process for preventing crime, and then the process proceeds to step 222.

In the crime prevention processing program according to the present embodiment, the following five types of processing are applied as the predetermined processing in step 220 described above.
Process 1. Processing for displaying the crime risk value R _ij (t + δt) and the suspicious degree P _j on the display 20F.
Process 2. Processing for issuing a warning when the crime risk value R _ij (t + δt) is equal to or greater than a predetermined threshold.
Process 3. When the crime risk value R _ij (t + δt) is greater than or equal to a predetermined threshold value, a process of notifying the defender closest to the target defender that the crime risk is high.
Process 4. Processing for issuing a warning when the suspicious degree P _j is equal to or greater than a predetermined second threshold.
Process 5. A process of notifying that there is an indeterminate person with a high suspicious degree nearby to the defender closest to the indeterminate subject when the suspicious degree P _j is equal to or greater than a predetermined second threshold.

  In addition, when applying the process 2 and the process 4 above, a speaker is provided in the monitoring target building 90 and a warning is issued by the speaker. Various forms such as a form for issuing a warning via a terminal device such as a PDA (Personal Digital Assistant, portable information terminal) can be applied.

  In addition, when the process 3 is applied, a speaker is provided inside the monitoring target building 90, and the speaker has a high crime risk with respect to the defender closest to the target defender. Various forms such as a form for notifying that the crime risk is high via a terminal device such as a PDA can be applied.

  Further, even when the process 5 is applied, a speaker is provided inside the monitoring target building 90, and the speaker causes the indefinite degree of suspiciousness to the defender closest to the target indefinite person. Various forms, such as a form for notifying that a person is nearby, a form for notifying an unidentified person with a high suspicious degree nearby via a terminal device such as a PDA, etc. it can.

  Here, the predetermined threshold value and the predetermined second threshold value when applying each of the processes 2 to 5 are automatically set according to the required safety level, usage, etc. It can also be set as the form made to input via the keyboard 20E etc. by the user of the crime prevention system 10. FIG.

  As described above, in the crime prevention processing program according to the present embodiment, the five types of processing 1 to 5 are applied as the predetermined processing. Any one of the processes or a combination of up to four processes may be applied.

  In step 222, it is determined whether or not a predetermined end condition is satisfied. If the determination is negative, the process proceeds to step 224 to wait for a predetermined time, and then returns to step 202. If the determination in step 222 is affirmative, the process proceeds to step 226, and control is performed to stop the feature point tracking process for all visitors started by the visitor stratification processing program. End this crime prevention processing program.

  The predetermined time applied in step 224 is a time that is adjusted in advance so that the repetition process of steps 202 to 224 is executed at intervals of the predetermined time δt as much as possible. Further, in the crime prevention processing program according to the present embodiment, as an end condition to be applied in the process of step 222, a condition that a time set in advance as a time to end monitoring of the monitoring target building 90 is reached. However, the present invention is not limited to this. For example, the condition that the instruction input for instructing the end of the crime prevention processing program is made via the keyboard 20E or the like, and the remaining storage capacity of the secondary storage unit 20D is It goes without saying that other conditions such as a condition that the amount is equal to or less than the predetermined amount can be applied.

As described above in detail, in the present embodiment, the position of a person existing in the target area based on the image information acquired by photographing the target area (in this case, inside the monitoring target building 90). Is detected at predetermined time intervals, while it is determined whether the detected person is a predetermined defender and an indefinite person excluding the defender, and the detected position of the person identified as the indefinite person The suspicious person's suspicious degree (here, second suspicious degree P _t ) is derived based on the detected behavioral state, and the suspicious person's behavioral state is derived based on the derived suspicious degree. Since the crime risk value indicating the level of crime risk by the indefinite person for the defender is calculated, and the predetermined crime risk is executed using the calculated crime risk value, the above indefinite person is executed. Depending on the behavioral state of As compared with the case of not using the suspiciousness degree of the indefinite person can be prevented more effectively the occurrence of crime.

  Further, in the present embodiment, the storage unit (here, the behavior state of the person detected based on the position of the person existing in the target region and the suspicious degree corresponding to the behavior state are stored in advance) Then, since the secondary storage unit 20D) is further provided and the suspicious degree of the unidentified person is derived by reading out the suspicious degree corresponding to the detected behavior state from the storage means, the crime can be more easily generated. Can be prevented.

Further, in the present embodiment, it is specified whether the detected person is the defender, the defender, or the indefinite person, and the defender is based on the position of the detected person and the specified result. and the (in this case, the distance D _{ViGk (t))} first distance is the distance of the defensive person, and a second distance wherein a distance indefinite's and the object to be defensive person (in this case, the distance D _ViSj ( t)) is derived, and the crime risk value is calculated based on the ratio between the first distance and the second distance and the derived suspicious degree, so that the defender can be used effectively. , Can be crime prevention more efficiently.

In particular, in the present embodiment, the defender after the predetermined time based on the amount of change between the first distance derived at the present time and the first distance derived at the time before the predetermined time. The distance of the defender (here, the distance D _ViGk (t + δt)) is predicted, and the second distance derived at the present time and the second distance derived at the time before the predetermined time Based on the amount of change, the distance between the indeterminate person and the defender after the predetermined time (here, the distance D _ViSj (t + δt)) is predicted, and the predicted distance between the defender and the defender, Since the crime risk value is calculated based on the ratio of the distance between the indeterminate person and the defender and the derived degree of suspiciousness, the result of being able to predict the crime risk value after the predetermined time is more immediate. Can be crime prevention.

  Further, in the present embodiment, defender identification information that is information for identifying the defender given in advance to the defender, and the defender given in advance to the defender. The identification information storage means (in this case, the secondary storage unit 20D) stores in advance the identification information of the defender, which is information for identifying the identification number, and the identification information of the defense and the defense field from the detected person. If any identification information of the person identification information is acquired and the acquired identification information matches the fielder identification information stored by the identification information storage means, the person who acquired the identification information is the fielder When the acquired identification information matches the defender identification information stored by the identification information storage means, the person who acquired the identification information is identified as the defender, People are undefined Since identified as those which are more reliably defensive person, the defensive person, and can determine the indefinite person, as a result, it is possible to prevent the crime more accurately.

  Further, in the present embodiment, as the predetermined process of the present invention, the process of storing the crime risk value and the suspicious degree, the process of displaying the crime risk value and the suspicious degree, the crime risk value and the Processing for issuing a warning when the degree of suspiciousness is equal to or higher than a predetermined threshold, processing for notifying the defender closest to the target defender that the crime risk is high, and the degree of suspiciousness being equal to or higher than the predetermined threshold Since the process of notifying the defender closest to a certain uncertain person that an uncertain person with a high suspicious degree is nearby is being executed, it is possible to obtain an effect corresponding to these processes.

[Second Embodiment]
In the first embodiment, the example of the case where the crime risk value is obtained based on the distance between the defender and the defender, the distance between the indeterminate person and the defender, and the suspicious degree of the indefinite person has been described. In this second embodiment, an example of a case in which a crime risk value is calculated based on the time for the defender to reach the defender, the time for the unidentified person to reach the defender, and the suspicious degree of the unidentified person. explain.

  The configuration of the crime prevention system 10 according to the second embodiment is the same as the crime prevention system 10 (see FIGS. 1 to 5) according to the first embodiment. Description is omitted.

  Next, the operation of the crime prevention system 10 according to the second embodiment will be described. In addition, since the effect | action when a visitor enters the inside of the monitoring object building 90 in the crime prevention system 10 which concerns on this 2nd Embodiment is the same as that of the said 1st Embodiment, it demonstrates here. The operation of the crime prevention system 10 according to the second embodiment when executing crime prevention processing will be described with reference to FIG. FIG. 16 shows the flow of processing of the crime prevention processing program according to the second embodiment, which is executed by the CPU 20A when an execution instruction is received via the keyboard 20E of the crime prevention device 20 or the like. This program is stored in advance in the program area PG of the secondary storage unit 20D. In addition, steps in FIG. 16 that execute the same processing as in FIG. 14 are assigned the same step numbers as in FIG.

In step 200 ′ in the figure, all information in the attribute information database DB2 and the second suspiciousness database DB5 is read, and then in step 207, the distance D _ViGk (t) obtained by the processing in step 206 is calculated as follows. By substituting into the equation (10), the time P _ViGk (t) for each defender to reach each defender is calculated and stored in a predetermined area of the secondary storage unit 20D. Here, F in the equation (10) is an average adult walking speed (as an example, 1.3 m / s), and _WGk is a weighting value of 1 or more for the walking speed F.

In the present embodiment, as the weighting value _WGk , from the information read from the attribute information database DB2 by the process of step 200 ′, the age, gender of the attribute corresponding to the identification information given to the corresponding defender, Each piece of height information is extracted, and values corresponding to these pieces of information are applied.

In crime prevention system 10 according to the present embodiment, the age increases as it approaches a predetermined age (for example, 30 years old) as the age at which walking speed is maximum, and the woman is female when the gender is male. The weighting value _WGk is calculated so as to be larger than the case and larger as the height increases.

As described above, in the crime prevention system 10 according to the present embodiment, the weighting value _WGk is derived by applying all of the corresponding defender's age, gender, and height. For example, it may be a form derived by applying any one of these age, gender and height, or a combination of the two, and a form derived by applying other parameters affecting the walking speed. You can also.

On the other hand, in step 209, the distance _{P ViSj} (t) obtained by the processing of step 208 is substituted into the following equation (11), so that the time P _ViSj (t ) And is stored in a predetermined area of the secondary storage unit 20D. Here, W _{Sj in the} equation (11) is a weighting value of 1 or more for the walking speed F.

In the present embodiment, as the weighting value _WSj , the age, sex, and height of the corresponding indeterminate are estimated, and values corresponding to these pieces of information are applied. The estimation of the age, sex, and height of the indeterminate person can be performed by a conventionally known technique such as a technique used in IMS (Intelligent Monitoring System, Exit Corporation) as an example.

In the crime prevention system 10 according to the present embodiment, the age increases as it approaches a predetermined age as the age at which the walking speed is maximized, compared to a case where the gender is male and the female. The weight value W _Sj is calculated so as to increase and increase as the height increases.

As described above, in the crime prevention system 10 according to the present embodiment, the weight value W _Sj is derived by applying all of the age, sex, and height of the corresponding defender, similarly to the weight value W _Gk. However, the present invention is not limited to this. For example, it may be derived by applying any one of these age, gender, height, or a combination of the two, and other parameters that affect the walking speed may be used. It is also possible to adopt a form derived by applying.

On the other hand, in step 212 ′, the time P _ViGk (t + δt) for the defender G _k to reach the defender V _i after a predetermined time δt (here 1 second) by the following equations (12) and (13). And the time P _ViSj (t + δt) for the indeterminate person S _j to reach the defender V _i is calculated (predicted). _{Here, (12) P ViGk (t} -δt) in the expression, in time defensive's _{G k} before a predetermined time .DELTA.t from the present time is reaching the defensive person _{V i, P} ViSj in (13) (t- δt) is the time for the indefinite person S _j to reach the defender V _{i a} predetermined time δt before the present time, and the value obtained and stored by the previous processing of step 207 and step 209 is applied.

  In the calculation of step 212 ′, it is necessary to apply the values obtained by the previous processing of step 207 and step 209 regarding the same person to each of the defender, the defender, and the indeterminate. For this purpose, a person whose identification information obtained last time by the process of step 202 matches the identification information obtained this time may be applied as the same person.

As an example, as shown in FIG. 17 by the calculation of step 212 ′, the arrival time P _ViGk (in accordance with the flow lines of the defender G _k , the defender V _i , and the indefinite person S _j is _shown. t + δt) and arrival time P _ViSj (t + δt) can be predicted with high accuracy.

In the next step 213, the traveling direction of the defender V _{i and} the traveling direction of the indeterminate person S _j are derived. In the crime prevention processing program according to the present embodiment, the direction of travel is derived from the positions of the defender V _i and the indefinite person S _j obtained by the processing of the previous step 202 and the current step 202. This is done by deriving the direction of the line segment connecting the positions of the defender V _i and the indefinite person S _j obtained by the processing between the same persons. However, the present invention is not limited to this. the position of the defense's V _i and unspecified persons S _j obtained by the processing of the difference between the position of the defense's V _i and unspecified persons S _j obtained by the process of the previous step 202 (hereinafter, "second that first difference. "), a position of the defensive's V _i and unspecified persons S _j obtained by the processing of the previous step 202, the defense's V _i and obtained by the process of this step 202 Difference between the position of makers S _j (hereinafter, referred to as "second difference".) Derives, forms like the direction of the variation and change of the first difference and the second difference is reflected in the direction of the line segment, Other forms are also possible.

Then, 'the, a first suspiciousness degree _{P a} obtained by the process of step 204, step 212' step 218 the arrival time obtained by the processing of _{P ViGk} (t + δt) and the arrival time _{P ViSj} and (t + .DELTA.t) Based on the second suspicious degree P _t obtained by the process of step 216, a crime risk value R _ij indicating the level of crime risk against the defender V _i by the unidentified person S _j after a predetermined time δt ( t + δt) ′ is calculated and stored (registered) in the crime risk value database DB5.

In the crime prevention processing program according to the present embodiment, the crime risk value R _ij (t + δt) ′ is calculated as follows.

First, the provisional crime risk value R _ij ′ (t + δt) ′ is calculated by substituting the arrival time P _ViGk (t + δt) and the arrival time P _ViSj (t + δt) into the following equation (14). _{Here, (14) W ViSj (t} + δt) in the expression, the traveling direction of the indefinite's _{S j} obtained by the process of step 213 is one or more of higher value increases closer to the traveling direction of the defensive's _{V i} It is a weighting value, and min _k () is a function indicating that the minimum value for all k of the calculation results in parentheses is applied.

Moreover, to calculate the equation (6) as well as the coefficient C _{R ',} the corresponding first suspiciousness degree P _a and the second suspiciousness degree P _t by substituting the equation (7), indefinite's S _j The overall suspicious degree P _j is calculated.

Then, the provisional crime risk value _{R ij '(t + δt)} ' obtained by the above, the coefficient _{C R} ', and by substituting the suspiciousness degree _{P j} to the next (15), crime risk value _R ij (t + .DELTA.t) 'Is calculated.

In general, the coefficient C _R ′ is set to −1 by applying 0.5 as the coefficient C ₁ . Thereby, the equation (15) is transformed into the following equation (16).

As described above in detail, in the second embodiment, it is possible to achieve substantially the same effect as in the first embodiment, and it is time for the defender to reach the defender. A first arrival time (here, arrival time P _ViGk (t)) is derived, and a second arrival time (here, arrival time P _ViSj (where the indefinite person reaches the _defender ). t)) is derived, and the crime risk value is calculated based on the derived ratio of the first arrival time and the second arrival time, and the derived suspicious degree, so that crime can be prevented with higher accuracy. be able to.

  In particular, in the second embodiment, a person's age, sex, and height are estimated based on the image information, and the first arrival time and the second time are determined according to the estimated age, sex, and height. Since the arrival time is adjusted, crime can be prevented with higher accuracy.

In the second embodiment, the time after the predetermined time based on the amount of change between the first arrival time derived at the current time and the first arrival time derived at the time before the predetermined time. The time when the defender reaches the defender (here, the arrival time P _ViGk (t + δt)) is predicted, and the second arrival time derived at the present time and the first time derived at the time before the predetermined time. Based on the amount of change from the arrival time of 2, the time that the indefinite person reaches the defender after the predetermined time (here, the arrival time P _ViSj (t + δt)) is predicted, and the predicted defender Since the crime risk value is calculated based on the ratio of the time to reach the defender and the time at which the indeterminate person reaches the defender and the derived suspicious degree, Crime risk value can be predicted As a result, it is possible to more immediate to crime prevention.

  Further, in the second embodiment, the traveling direction of the defensive person and the traveling direction of the undefined person are derived, and the value increases as the traveling direction of the undefined person is closer to the derived traveling direction of the defender. Since the crime risk value is calculated so as to increase, the occurrence of crime can be prevented with higher accuracy.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. Various modifications or improvements can be added to the above-described embodiment without departing from the gist of the invention, and embodiments to which such modifications or improvements are added are also included in the technical scope of the present invention.

  The above embodiments do not limit the invention according to the claims (claims), and all the combinations of features described in the embodiments are essential for the solution means of the invention. Is not limited. The embodiments described above include inventions at various stages, and various inventions can be extracted by appropriately combining a plurality of disclosed constituent elements. Even if some constituent requirements are deleted from all the constituent requirements shown in the embodiment, as long as an effect is obtained, a configuration from which these some constituent requirements are deleted can be extracted as an invention.

  For example, in the first embodiment, the predicted values obtained by the expressions (3) and (4) are applied as the distance between the defender and the defender and the distance between the indeterminate person and the defender. In the above embodiment, the case where the predicted values obtained by the expressions (12) and (13) are applied as the time for the defender to reach the defender and the time for the undefined person to reach the defender has been described. The present invention is not limited to this, and instead of these predicted values, the actual distance and arrival time at that time can be applied.

  When the actual distance is applied to the first embodiment, step 212 in the crime prevention processing program (see FIG. 14) according to the first embodiment is deleted and step 218 is performed. The following formula (17) is applied instead of the formula (5) applied to calculate the crime risk value.

  When the actual arrival time is applied to the second embodiment, step 212 ′ of the crime prevention processing program (see FIG. 16) according to the second embodiment is deleted. In step 218 ′, the following equation (18) is applied instead of the equation (14) applied to calculate the crime risk value.

  In these cases as well, substantially the same effects as in the above embodiments can be obtained.

  In each of the above-described embodiments, the case where the visitor is authenticated by any one of the presentation of the ID card 52, the input of the identification information, and the call of the visit destination has been described. However, the present invention is not limited to this. Instead, for example, the permitter has an RFID (Radio Frequency Identification) tag in which identification information previously given to the permitter is stored, and is stored in the RFID tag in the vicinity of the operation panel 30. It is also possible to employ a form in which authentication is automatically performed by providing a tag reader that can read the identification information without contact, and reading the identification information from the RFID tag by the tag reader.

Moreover, although each said embodiment demonstrated the case where the process of the process 1-the process 5 was applied as a process performed in step 220 of a crime prevention process program, this invention is not limited to this. For example, as shown below, the processing content may be made different depending on the calculated crime risk value.
a. When the crime risk value <0.25, an image indicated by the image information obtained from the camera 42 photographing the corresponding indefinite person is displayed on the display 20F.
b. When 0.25 ≦ crime risk value <0.5, among the images indicated by the image information obtained from the camera 42 photographing the corresponding indeterminate person, the indefinite person is enlarged and displayed on the display 20F. At the same time, a warning is displayed on the site.
c. In the case of 0.5 ≦ crime risk value, in addition to the process in the case of b, the corresponding indefinite person is threatened by voice or the like.

  In each of the above-described embodiments, the case where the positions of the defender and the defender are detected by the feature point tracking process has been described. However, the present invention is not limited to this. For example, an RFID tag is used. Or the position of the defender and the defender can be detected by using GPS (Global Positioning Systems).

  As an example of a case where a position is detected using an RFID tag, three or more antennas are provided inside the monitoring target building 90, and three antennas receiving the same information from the RFID tag are specified. Then, based on the received intensity of the radio wave received by the specified antenna, a mode of specifying the position of the source RFID tag, that is, the position of the person carrying the RFID tag by the triangulation technique is illustrated. be able to. In addition, as an example of a case where the position is detected using GPS, the defender and the defender have a device capable of specifying their position by GPS and a wireless transmission device, and the device The form which transmits the information which shows the specified position, and the identification information previously allocated to self to the crime prevention apparatus 20 by the said radio | wireless transmission apparatus every said predetermined time (delta) t can be illustrated.

  In each of the above embodiments, the case where the distance between the defensive person and the defensive person and the distance between the indefinite person and the defensive person are derived as linear distances between the respective position coordinates has been described. However, the present invention is not limited to this, and when a wall partitioning each partition region is interposed therebetween, the distance when the wall is detoured may be derived.

  In each of the above embodiments, the operation panel 30, the camera 40, the camera 42, the intercom 44, the card reader 50, the locking / unlocking unit 60, and the crime prevention apparatus 20 are electrically connected by wire. However, the present invention is not limited to this, and at least one of these devices can be electrically connected wirelessly.

  Further, although cases have been described with the above embodiments where the Euclidean distance is applied as the distance, the present invention is not limited to this, and for example, other distances such as a Manhattan distance are applied. You can also.

  In each of the above-described embodiments, the case where the attribute information is registered in advance by the attribute information database DB2 has been described. However, the present invention is not limited to this. For example, the ID card 52 includes the ID card 52. It is also possible to store attribute information relating to the person who holds the card in advance and acquire the attribute information via the card reader 50.

  In each of the above-described embodiments, the case where three types of behavior states, that is, the automatic authentication state, the manual authentication state, and the accompanying state are applied as the behavior state at the time of entering the building is described. However, the present invention is not limited to this. For example, in addition to these action states, other action states such as a state where the user enters without being authenticated when the door 80B is in an open state due to a failure of the locking / unlocking part 60 or the like. One of the included behavior states or a combination of a plurality of behavior states may be applied.

  In each of the above-described embodiments, the case where four types of behavior states of the non-permitted area presence state, the non-permitted time stay state, the unauthenticated state, and other states are applied as the behavior state during tracking has been described. The present invention is not limited to this. For example, one or more combinations of behavioral states including other behavioral states such as a behavioral state acting alone may be applied. Good.

  Further, in each of the above embodiments, the case where the inside of a building is applied as the target area of the present invention has been described, but the present invention is not limited to this, for example, a shrine / buddhist temple, a hotel / theatre, etc. An area where unspecified persons enter and exit such as a lobby, an open space, a park, etc. (hereinafter referred to as “open area”) or a combination of the inside of the building and the open area may be applied.

  In addition, when an open area is applied as the target area of the present invention and the crime type targeted for crime prevention is an arson, etc., as a defender, fuel, combustible garbage, dry wooden structures, etc. It is also possible to apply a form that is easy to ignite, and when the crime targeted for crime prevention is a thief, etc. It is good also as a form to do. In this case, since the defensive person is a still life, by registering the position of the defensive person in advance, it is not necessary to track the defensive person using the automatic tracking function.

  Similarly, in each of the above embodiments, an important object such as the server device 85A and the safe 86A may be applied as a defender. In this case, the position of the defender is registered in advance. Thus, it is no longer necessary to track the defender using the automatic tracking function.

Further, in each of the above embodiments, all indefinite persons S _j that are located inside the section area (area where only the authorized person may enter) indicated by the entrance restricted area information and whose identifier is 'T'. However, the present invention is not limited to this, and the indefinite person who entered in the manual authentication state and the indefinite person who entered in the accompanying state are indefinite. As a form of determining in advance a section area that should not be entered for each type of person, and determining that the indefinite person is in the non-permitted area when the indefinite person is located inside the corresponding section area Good.

  In addition, the configuration (see FIGS. 1 to 5) of the crime prevention system 10 described in each of the above embodiments is an example, and unnecessary components may be deleted without departing from the gist of the present invention. Needless to say, new components can be added.

  Further, the flow of processing of the various processing programs shown in the above embodiments (see FIGS. 12, 14, and 16) is also an example, and unnecessary processing steps are performed within the scope not departing from the gist of the present invention. Needless to say, it can be deleted, a new processing step can be added, or the order of processing steps can be changed.

  The configurations of various databases (see FIGS. 6 to 11) shown in the above embodiments are also examples, and some information may be deleted or new within the scope not departing from the gist of the present invention. It goes without saying that information can be added and the storage location can be changed.

  Furthermore, the various arithmetic expressions shown in the above embodiments (see Expressions (1) to (18)) are also examples, and unnecessary parameters can be deleted without departing from the gist of the present invention. It goes without saying that new parameters can be added and the order of operations can be changed.

10 Crime Prevention System 20 Crime Prevention Device 20A CPU
20D Secondary storage unit 20E Keyboard 20F Display 30 Operation panel 30A Display unit 30B Operation unit 30C Alarm unit 40 Camera 42 Camera 44 Interphone 50 Card reader 60 Unlocking unit 80 Hall 90 Monitoring target building DB1 Identification information database DB2 Attribute information database DB3 Position Information database DB4 First suspicious degree database DB5 Second suspicious degree database DB6 Crime risk value database

Claims (6)

Photographing means for obtaining image information of the target area by photographing the target area;
Detection means for detecting positions of persons existing in the target area at predetermined time intervals based on image information acquired by the photographing means;
A specifying means for specifying whether or not the person detected by the detecting means is an indefinite person excluding a predetermined defender and a defender;
Detection means for detecting the behavioral state of the indeterminate person based on the position detected by the detection means of the person identified as the indeterminate person by the specifying means;
Derivation means for deriving the suspicious degree of the unidentified person based on the behavior state detected by the detection means;
Based on the suspicious degree derived by the deriving means, computing means for computing a crime risk value indicating the level of crime risk by the unidentified person against the defender;
Using the crime risk value calculated by the calculation means, execution means for executing a process predetermined as preventing crime,
Crime prevention device equipped with. A storage unit that stores the behavior state of the person detected based on the position of the person present in the target area and the suspicious degree corresponding to the behavior state, and is stored in advance;
The crime prevention apparatus according to claim 1, wherein the deriving unit derives the suspicious degree of the unidentified person by reading out the suspicious degree corresponding to the behavior state detected by the detecting unit from the storage unit. The behavior state of the indefinite person is a first behavior state indicating whether or not the indefinite person has entered the entrance permission area where only the defender and the defender are allowed to enter in advance. A second action state indicating whether or not the undefined person has stayed for a predetermined time or more, and a third state indicating whether or not the undefined person is acting with the defender or the defender. The crime prevention device according to claim 1, wherein the crime prevention device includes at least one of the following behavioral states. The specifying means specifies whether the person detected by the detecting means is the defender, the defender, or the indefinite person,
Based on the position of the person detected by the detecting means and the specifying result by the specifying means, a first distance that is a distance between the defender and the defender, and a distance between the indeterminate person and the defender A distance deriving unit for deriving a second distance;
The calculation means calculates the crime risk value based on a ratio between the first distance and the second distance derived by the distance deriving means and a suspicious degree derived by the deriving means. Item 4. The crime prevention apparatus according to any one of item 3. A first arrival time, which is a time for the defender to reach the defender, is derived based on the first distance, and the indefinite person reaches the defender based on the second distance. An arrival time deriving means for deriving a second arrival time that is a time to
The calculation means calculates the crime risk value based on a ratio between a first arrival time and a second arrival time derived by the arrival time deriving means, and a suspicious degree derived by the derivation means. 4. The crime prevention apparatus according to 4. Computer
Detecting means for detecting the position of a person existing in the target area at predetermined time intervals based on the image information acquired by the imaging means for acquiring the image information of the target area by shooting the target area;
A specifying means for specifying whether or not the person detected by the detecting means is an indefinite person excluding a predetermined defender and a defender;
Detection means for detecting the behavioral state of the indeterminate person based on the position detected by the detection means of the person identified as the indeterminate person by the specifying means;
Derivation means for deriving the suspicious degree of the unidentified person based on the behavior state detected by the detection means;
Based on the suspicious degree derived by the deriving means, computing means for computing a crime risk value indicating the level of crime risk by the unidentified person against the defender;
Using the crime risk value calculated by the calculation means, execution means for executing a process predetermined as preventing crime,
Program to function as.