JP2010140091A - Crime prevention device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a crime prevention device and program for more effectively preventing a crime. <P>SOLUTION: The crime prevention device is configured to detect the location of a person who is present in a monitoring area 60 at predetermined time intervals on the basis of image information obtained by a camera 40 which captures the image information of the monitoring area 60 in real time by imaging the monitoring area 60, to specify whether or not the detected person is an unidentified person other than a predetermined guard and guarded person by using an IC tag 90 and an antenna, to estimate the age and sex of the person specified as the unidentified person and the number of persons moving together on the basis of the image information, to derive the rate of a criminal probability that the unidentified person commits a crime on the basis of the estimation result, to calculate a crime risk value showing the degree of a crime risk by the unidentified person to the guarded person on the basis of the derived criminal rate, and to execute predetermined processing for preventing a crime by using the calculated crime risk value. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a crime prevention apparatus and program, and more particularly, to a crime prevention apparatus and program for preventing a crime by an unspecified person in a predetermined area.

  As a technique that can be applied to prevent the occurrence of crimes against a predetermined person in an area where an unspecified person enters or exits such as an open space or a park, Patent Document 1 discloses a danger warning system adapted to an individual. For the purpose of providing a storage area for storing a predetermined individual danger area, a person position detecting means for detecting the position of a person, a personal identification means for identifying the predetermined person, and a warning A specific person identified by the reporting means, the personal identification means and a person whose position is detected by the person position detecting means, and the identified predetermined person stored in the storage means is identified. In addition, there is disclosed a technology having control means for issuing an alarm by means of the reporting means when entering a dangerous area corresponding to a predetermined individual.

  By applying this technology as a dangerous area where a crime is likely to occur in the above-mentioned area where an unspecified person enters and exits, it is possible to prevent a crime from occurring for a predetermined person.

Patent Document 2 discloses a device that allows a person to enjoy a crime prevention service without carrying or operating a reporting device, allowing a monitor to monitor a wide surveillance area with little effort, and contributing to the police's initial investigation. For detecting a physical signal emitted from within the monitoring area and its transmission position, an image capturing section for capturing images in the monitoring area in time series, and the image capturing section When the physical signal detected by the detection unit satisfies a predetermined setting condition, the transmission position (target) of the physical signal is stored. A detection result analysis unit that extracts a point) and a detection time, an image extraction unit that extracts image information captured by the image capturing unit within an extraction period from the image storage unit, and the image extracted by the image extraction unit. It analyzes the information, technology with a suspected object image extracting unit which extracts an image of an object approaching to the target point is disclosed.
JP 2004-234061 A JP 2005-346545 A

  By the way, in areas where unspecified people come and go, such as open spaces and parks, people who want to protect against crime (hereinafter referred to as “defenders”) (hereinafter referred to as “defense”) Are often present in the vicinity of defenders. For example, when the guardian is a child, the guardian is a guardian or a school teacher. When the guardian is an adult, the guardian is a guard or a manager of the above area.

  Here, out of the persons in the area where the unspecified person enters and exits, the person excluding the defender and the defender (hereinafter referred to as “indefinite person”) does not necessarily commit a crime against the defender. Rather, people who commit crimes are extremely rare.

  Therefore, it is very important to consider the probability that the unspecified person will commit a crime against the defender in order to construct an effective crime prevention system.

  However, the techniques disclosed in Patent Document 1 and Patent Document 2 do not take into account whether or not the indefinite person commits a crime, and whether or not the indefinite person exists. However, there was a problem that it was not always possible to effectively prevent crime.

  The present invention has been made to solve the above-described problems, and an object thereof is to provide a crime prevention apparatus and program capable of preventing crime more effectively.

  First, the principle of the present invention will be described.

  Figures 15 to 19 show the types of crimes committed against people in Japan from 2000 to 2006 as announced by the National Police Agency, and act together with the criminal's age and gender. It is the number of crimes per year for each number of people. 15 relates to “assault”, FIG. 16 relates to “injury”, FIG. 17 relates to “forced obscenity”, FIG. 18 relates to “public obscenity”, and FIG. 19 relates to “almost kidnapping”.

  As shown in the figure, crimes committed against people are highly dependent on age, gender, and the number of people acting together. For example, “forced obscenity”, “public obscenity”, and “substantial kidnapping” tend to decrease gradually as the age rises, peaking in the 20s and 30s. A large percentage is shown. In addition, for each crime type, the number of men is overwhelmingly larger than that of women, and the number of people who act alone is overwhelmingly larger than the number of people who act as multiple people.

  Therefore, the probability that an indefinite person commits a crime against a person depends greatly on age, sex, and the number of people acting together.

  Based on the above principle, in order to achieve the above object, the crime prevention apparatus according to claim 1 includes an imaging unit that captures image information of the target area in real time by imaging the target area, and an imaging unit. Based on the acquired image information, detection means for detecting the position of a person existing in the target area at predetermined time intervals, and a person detected by the detection means excluding a predetermined defender and defender Based on the image information, a specifying means for specifying whether or not the person is an indefinite person, and at least one of the age, sex, and number of people acting together determined by the specifying means as an indefinite person And a deriving unit for deriving a criminal rate that is a probability that the undetermined person commits a crime based on an estimation result by the estimating unit, and a crime derived by the deriving unit. The crime is prevented by using a calculation means for calculating a crime risk value indicating the level of crime risk caused by the indefinite person with respect to the defender based on the security rate, and a crime risk value calculated by the calculation means. And a process execution means for executing a predetermined process.

  According to the crime prevention apparatus according to claim 1, image information of the target area is acquired in real time by imaging the target area by the imaging unit, and based on the image information acquired by the imaging unit by the detection unit. Thus, the position of the person existing in the target area is detected at predetermined time intervals. As described above, the image capturing unit acquires image information in real time. For the acquisition, in addition to continuous acquisition by moving image capturing, the detection unit detects the position of the person. Intermittent acquisition at the timing corresponding to. The photographing means includes various cameras such as a monochrome camera, a color camera, and an infrared camera capable of photographing at least one of a moving image and a still image.

  Here, in the present invention, it is specified by the specifying means whether or not the person detected by the detecting means is a predetermined defender and an indefinite person excluding the defender, and the estimating means specifies the specifying means. At least one of the age, sex, and the number of persons acting together is determined based on the image information, and is derived by the derivation unit based on the estimation result by the estimation unit. A criminal rate, which is a probability that a person will commit a crime, is derived. Further, based on the criminal rate derived by the deriving unit, a high risk of crime by the unidentified person against the defender is calculated by the calculating unit. The indicated crime risk value is calculated.

  In the present invention, the process execution means executes a process predetermined to prevent crime using the crime risk value calculated by the calculation means.

  Thus, according to the crime prevention apparatus according to claim 1, the target area is captured based on the image information acquired by the imaging unit that acquires the image information of the target area in real time by capturing the target area. Detects the position of an existing person at a predetermined time interval, specifies whether or not the detected person is an indefinite person excluding a predetermined defender and defender, and the age of the person identified as an indefinite person, Estimating at least one of gender and the number of people acting together based on the image information, and deriving a criminal rate, which is the probability that the indeterminate will commit a crime, based on the estimation result Based on a criminal rate, a crime risk value indicating the level of crime risk caused by the indeterminate person against the defender is calculated, and a predetermined process is performed to prevent crime using the calculated crime risk value As a result of being able to execute a predetermined process for preventing crimes based on the criminal rate by indefinite persons derived with high accuracy, as compared with the case where the present invention is not applied. Can be more effective in crime prevention.

  In the present invention, as in the invention described in claim 2, the crime is actually caused by a person corresponding to at least one of the age, sex, and the number of persons acting together as an estimation target by the estimation means. A criminal rate corresponding to an estimation result by the estimation unit, further comprising storage means stored in advance in association with a condition corresponding to the corresponding criminal rate derived based on the ratio performed May be derived from the storage means. Thereby, compared with the case where this invention is not applied, a criminal rate can be derived more easily and in a short time. 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 described in claim 3, the criminal rate may be derived in advance from a statistical value of the past crime occurrence number based on Bayesian theory. Thereby, compared with the case where this invention is not applied, a criminal rate can be derived more easily and with high precision. In addition, as a statistical value of the past crime occurrence number of this invention, the value shown by FIGS. 15-19 can be illustrated. Here, when there are values of a plurality of years as shown in FIGS. 15 to 19 as the statistical values, a form in which the value of the year closest to the current time is applied, and a value of the year with the highest number of crimes is applied. The form which applies, the form which applies the average value of several years, etc. are applicable.

  The Bayesian theory is a probability theory theorem published in 1863, where P (B) is the probability of occurrence of event B (prior probability) and P (B | A) is occurrence of event A. When the probability of occurrence of event B after the occurrence (posterior probability) is assumed, if P (A)> 0, the following equation (1) is established.

When the criminal rate is derived using the equation (1), P (A) is set to at least one condition of age, sex, and the number of people acting together by the estimation means of the present invention. At least one of the age, gender, and the number of people acting together with P (B) as the probability that an actual crime occurred and P (A | B) as the estimation target by the estimation means The probabilities of criminals that meet the conditions are calculated by substituting each into the equation (1).

  Note that P (A) may be derived from the ratio of the number of people who meet the above condition to the total number of people who existed within a predetermined period in a predetermined region by observation, past statistical values, or the like. Here, as the predetermined region, any region can be applied, but it is preferable to apply a region having an environment similar to the target region of the present invention, and it is more preferable to apply the target region of the present invention. . In addition, the predetermined period includes each time zone such as morning, noon, evening, and night, and each divided time zone obtained by dividing the day by a predetermined time interval such as 3 hours or 6 hours. It is preferable to apply the same time zone as the time zone in which the crime risk value is calculated by the calculation means.

  In addition, P (B) is a target for the total number of people (the population of Japan when the statistical values shown in FIGS. 15 to 19 are applied) existing in the area targeted for the statistical value. What is necessary is just to derive | lead-out the ratio of the crime occurrence number from the said statistics value.

  In practice, it is derived based on statistical values for each region, or the number of persons and crime occurrences in the predetermined area are measured by day of the week or by the time zone, and are present in the predetermined area. It is preferable to derive the ratio of the number of crimes to be targeted with respect to the total number of people by day of the week, time zone, or the like.

  Further, P (A | B) may be derived from the statistical value as a ratio of the number of persons who satisfy the above condition to the total number of persons who committed the targeted crime.

  Since Bayesian theory is conventionally known, further detailed explanation is omitted.

  By the way, the tendency of crime to occur varies greatly depending on the crime type. For example, “injury” (see FIG. 16) tends to decrease in number as the age rises with a peak at less than 20 years old, whereas “publicly obscene” (see FIG. 18) has a significant number of cases under 20 years old. Low.

  Therefore, in the present invention, as in the invention described in claim 4, the derivation means may derive the criminal rate for each crime type. Thereby, crime can be prevented for each crime type.

  By the way, when a defender exists in the vicinity of the defender, it is very important to effectively use the defender to protect the defender in order to construct an efficient crime prevention system.

  On the other hand, in the techniques disclosed in Patent Document 1 and Patent Document 2, no consideration is given to the defender, and it is not always possible to efficiently prevent crime.

  Therefore, according to the present invention, as in the invention described in claim 5, the specifying means determines whether the person detected by the detecting means is the defender, the defender, or the indefinite person. A first distance that 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 that is a distance of the first distance, and the computing unit is derived by the ratio of the first distance to the second distance derived by the distance deriving unit and the deriving unit. The crime risk value may be calculated based on the criminal rate. Thereby, as a result of being able to use the defender effectively, crime can be prevented more efficiently than in the case where the present invention is not applied.

  The invention according to claim 5 is derived by the distance deriving means at a time point before the first distance derived by the distance deriving means and the predetermined time, as in the invention according to claim 6. The distance between the defender and the defender after the predetermined time is predicted based on the amount of change from the first distance, and the second distance derived by the distance deriving means at the present time and the predetermined distance Further comprising distance predicting means for predicting the distance between the indefinite person and the defender after the predetermined time based on the amount of change from the second distance derived by the distance deriving means at a time point before time; The calculating means calculates the ratio of the distance between the defender and the defender predicted by the distance predicting means, the distance between the indeterminate person and the defender, and the criminal rate derived by the deriving means. Based on the above The crime risk value may be calculated. Thereby, as a result of being able to predict the crime risk value after the predetermined time, crime can be prevented more immediately compared to the case where the present invention is not applied.

  Further, according to the fifth aspect of the present invention, as in the seventh aspect of the present invention, 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 a criminal rate derived by the deriving unit. Thereby, compared with the case where this invention is not applied, a crime can be prevented more accurately.

  In particular, the invention according to claim 7 further includes second estimation means for estimating at least one of the age, sex, and height of the person detected by the detection means based on the image information, and the arrival time. The derivation unit may adjust the first arrival time and the second arrival time according to at least one of age, sex, and height estimated by the second estimation unit. Thereby, compared with the case where this invention is not applied, a crime can be prevented more accurately.

  According to a seventh aspect of the present invention, as in the eighth aspect of the present invention, the arrival time derivation is performed at a time point before the first arrival time derived by the arrival time deriving means and the predetermined time. Based on the amount of change from the first arrival time derived by the means, the time when the defender reaches the defender after the predetermined time is predicted, and at the present time, the arrival time deriving means The indefinite person after the predetermined time reaches the defender based on the amount of change between the second arrival time and the second arrival time derived by the arrival time deriving means at a time point before the predetermined time. It further comprises arrival time predicting means for predicting time, and the computing means predicts the time when the defender arrives at the defender predicted by the arrival time predicting means, and the indefinite person reaches the defender. You Time ratio, and may be calculated the crime risk value based on the derived criminal rate by said deriving means. Thereby, as a result of being able to predict the crime risk value after the predetermined time, crime can be prevented more immediately compared to the case where the present invention is not applied.

  Further, in the invention according to any one of claims 5 to 8, as in the invention according to claim 9, the traveling direction for deriving the traveling direction of the defender and the traveling direction of the indefinite person. The calculation means further calculates the crime risk value so that the value becomes larger as the traveling direction of the undefined person is closer to the traveling direction of the defender derived by the traveling direction deriving means. May be. Thereby, compared with the case where this invention is not applied, a crime can be prevented more accurately.

  Further, in the invention according to any one of claims 5 to 9, as in the invention according to claim 10, area information indicating an area of an obstacle that hinders a person from walking in the target area. If the area of the obstacle indicated by the area information exists between the defender and the defender, the distance deriving means further stores area information storage means for storing the obstacle information. The first distance is derived as a detour, and if the area of the obstacle exists between the indefinite person and the defender, the first distance is deduced as a detour of the obstacle area. A distance of 2 may be derived. Thereby, compared with the case where this invention is not applied, a crime can be prevented more accurately. The area information storage means includes the semiconductor storage element, the portable recording medium, the fixed recording medium, and the external storage device.

  In addition, as in the invention described in claim 11, the present invention relates to guarder identification information, which is information for identifying the defender given in advance to the defender, and to the defender. Identification information storage means for preliminarily storing defender identification information, which is information for identifying the defender given in advance, and the defensive person identification information and the defensive information from the person detected by the detection means Acquisition means for acquiring any identification information of the person identification information, wherein the identification means is the defender identification information in which the identification information acquired by the acquisition means is stored in the identification information storage means If they match, the person who acquired the identification information is identified as the defender, and the identification information acquired by the acquisition means is stored in the identification information storage means. The acquisition source of human identification information identifies assumed as an object to be defensive person may be identified as another person is indeterminate user when matching the information. Thereby, compared with the case where this invention is not applied, a defender, a defender, and an indefinite person can be specified more reliably, and as a result, crime can be prevented with higher accuracy. The identification information storage means includes the semiconductor storage element, the portable recording medium, the fixed recording medium, and the external storage device.

  Further, according to the present invention, as in the invention described in claim 12, the processing execution unit stores at least one of the crime risk value and the criminal rate as the predetermined processing, the crime A process for displaying at least one of the risk value and the criminal rate, a process for issuing a warning when at least one of the criminal risk value and the criminal rate is equal to or greater than a predetermined threshold, and closest to the target defender A process for notifying the defender that the crime risk is high, and there is an indefinite person with a high criminal rate nearby the defender closest to the indefinite person whose criminal rate is equal to or greater than the predetermined threshold. You may perform at least 1 process of the process which alert | reports doing. Thereby, the effect according to the applied process can be acquired.

  The display of at least one of the crime risk value and the criminal rate includes not only visual display by a display device or the like, but also permanent display by an image forming device or the like, and audible display by an audio generation device or the like.

  Further, according to the present invention, the detecting means detects the position of the defender and the defender existing in the target area at the predetermined time interval using an IC tag or GPS (Global Positioning Systems). It is good. Thereby, compared with the case where this invention is not applied, this invention can be implement | achieved more easily and a crime can be prevented more precisely. Note that the IC tag is sometimes referred to as an RFID tag, a wireless tag, an ID tag, an electromagnetic induction tag, or the like. In this specification, these are collectively referred to as an IC tag.

  On the other hand, in order to achieve the above object, a program according to claim 13 is based on image information acquired by an imaging means for acquiring image information of a target area in real time by imaging the target area. 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 the defender. Identifying means for identifying, estimating means for estimating at least one of the age, sex, and number of people acting together determined by the identifying means based on the image information; and the estimating means Based on the estimation result, the deriving means for deriving a criminal rate that is a probability that the unidentified person commits a crime, and based on the criminal rate derived by the deriving means , A calculation means for calculating a crime risk value indicating the level of crime risk caused by the indefinite person with respect to the defensive person, and a crime risk value calculated by the calculation means are used to prevent crime. It is for functioning as a process execution means for executing the processes.

  Therefore, according to the program of the thirteenth aspect, the computer can be caused to act in the same manner as the first aspect of the invention, so that, similarly to the first aspect of the invention, the present invention is not applied. In comparison, crime can be more effectively prevented.

  According to the present invention, based on the image information acquired by the imaging unit that acquires the image information of the target area in real time by capturing the target area, the position of the person existing in the target area is determined at predetermined time intervals. Detects and identifies whether the detected person is an indeterminate person excluding predetermined defenders and defenders, and the age, gender, and number of persons acting together as the unidentified person Is estimated based on the image information, and based on the estimation result, a criminal rate that is a probability that the unidentified person commits a crime is derived, and the defensive rate is calculated based on the derived criminal rate. The crime risk value indicating the level of crime risk by the indefinite person for the person is calculated, and using the calculated crime risk value, a process predetermined to prevent crime is executed, so with high accuracy Derivation As a result of being able to execute a predetermined process for preventing crimes based on the criminal rate by the unspecified persons, it is possible to prevent crime more effectively than when the present invention is not applied. The effect of is obtained.

  The best mode for carrying out the present invention will be described below in detail with reference to the drawings. Here, the case where the present invention is applied to a crime prevention system for monitoring a park in order to prevent the occurrence of a crime in the park will be described.

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

  As shown in the figure, the crime prevention system 10 according to the present embodiment includes a crime prevention device 20 that plays a central role in the system 10, and a plurality of individuals possessed by a predetermined defender and defender. IC tag 90, a plurality of antennas 30 for acquiring information transmitted from each IC tag 90, and a region to be monitored in the system 10 (here, a park, hereinafter referred to as “monitoring target region”) .) And a plurality of cameras 40 for photographing the inside, and the antenna 30 and the camera 40 are electrically connected to the crime prevention apparatus 20.

  In the crime prevention system 10 according to the present embodiment, an active IC tag is applied as the IC tag 90, and the IC tag 90 is located at a relatively long distance (here, 20 m) by the antenna 30. The information transmitted from can be received.

  Here, in crime prevention system 10 according to the present embodiment, as shown in FIG. 2, the entire area 60 to be monitored is divided into rectangular areas having predetermined dimensions (here, 10 m in both vertical and horizontal directions). The antenna 30 is provided at each of the positions where the boundary lines of the divided areas intersect.

  The crime prevention apparatus 20 identifies the three antennas 30 receiving the same information from the IC tag 90, and uses triangulation technology based on the reception strength of the radio waves received by the identified antennas 30. The position of the source IC tag 90, that is, the position of the person carrying the IC tag 90 can be specified.

  On the other hand, in the crime prevention system 10 according to the present embodiment, as shown in FIG. 2, the cameras 40 are located at a plurality of positions (four locations in the present embodiment) around the monitoring target area 60. The target region 60 is provided at a position and a state where the target region 60 can be photographed. In addition, since the camera 40 is for monitoring the monitoring target area 60, it is preferable that the camera 40 is provided in a state where no blind spots are generated in the entire monitoring target area 60. The shape of the monitoring target area, The number of installations and installation positions are determined according to the state of obstacles, usage, etc. Further, in the crime prevention system 10 according to the present embodiment, a digital camera capable of shooting a moving image in color is applied as the camera 40, and the image of the monitoring target region 60 is captured by the camera 40. The image information shown can be acquired.

  Next, with reference to FIG. 3, the structure of the main part of the electrical system of the crime prevention apparatus 20 having a particularly important role in the crime prevention system 10 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 external I / F (interface) 20G for exchanging various signals between external devices and the like are provided. These units 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 external I / F 20G. Various signals can be exchanged between them. The antenna 30 and the camera 40 described above are electrically connected to the crime prevention apparatus 20 via the external I / F 20G.

  On the other hand, FIG. 4 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 stores a database area DB for storing various databases, a control program for controlling the crime prevention apparatus 20, a program for performing various processes, and the like. A program area PG is provided.

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

  In crime prevention system 10 according to the present embodiment, IC tag 90 is distributed to each of a predetermined defender and defender. At this time, the IC tags 90 to be distributed are each configured to transmit unique identification information so that a person to whom the distribution is made can be specified individually.

  The identification information database DB1 is mainly for storing this identification information. As shown in FIG. 5 as an example, the identification information and the types of information that are targeted by the crime prevention apparatus 20 include It is configured to be stored for each defender.

  The type is information indicating whether the person who has the IC tag 90 that transmits the corresponding identification information is a defender or a defender. In the example shown in FIG. 5, for example, the person holding the IC tag 90 that transmits identification information “10001” is “defender”, and the IC tag that transmits identification information “20003”. The person holding 90 is shown to be a 'guardian'.

  Since there are many IC tags that transmit serially assigned serial numbers, in this case, the serial number may be applied as the identification number.

  On the other hand, as shown in FIG. 6 as an example, the attribute information database DB2 is configured to store attributes for each identification information.

  The attribute is information indicating the characteristics of the person who has the IC tag 90 that transmits the corresponding identification information. In the attribute information database DB2 according to the present embodiment, as shown in FIG. It consists of gender, height, and status information. In the example shown in FIG. 6, for example, a person who possesses an IC tag 90 that transmits identification information “10001” is a 7-year-old man whose height is 110 cm, and “20003”. It is shown that the person who possesses the IC tag 90 that transmits the identification information is a 50-year-old man and a guard whose height is 173 cm.

  On the other hand, as shown in FIG. 7 as an example, the obstacle information database DB3 includes obstacle ID (Identification), area, and type information that exists in the monitoring target area 60 and prevents human walking. It is configured to be stored for each of the obstacles.

  The obstacle ID is information that is different for each obstacle by the crime prevention apparatus 20 in order to identify an obstacle existing in the monitoring target area 60 (as an example, the implanted obstacle 62 shown in FIG. 2). (In this embodiment, it is given in advance as information combining alphabets and numerals).

  The area is information indicating an area (position) where a corresponding obstacle exists. As shown in the figure, in the obstacle information database DB3 according to the present embodiment, an XY coordinate system having the origin as a predetermined base point position when the area to be monitored is viewed in plan is shown in the obstacle information database DB3. Is represented by a pair of diagonal coordinate values of a circumscribed rectangular frame of the corresponding obstacle, but is not limited to this, for example, a coordinate value by the XY coordinate system of the contour position of the corresponding obstacle It cannot be overemphasized that it can be set as other forms, such as a form denoted by.

  Moreover, the said classification is information which shows classifications, such as implantation, a fountain, and a heel, of a corresponding obstacle.

  On the other hand, as shown in FIG. 8 as an example, the position information database DB4 is configured so that information on camera ID, pixel position, and position coordinates is stored for each camera 40.

  The camera ID is given in advance as information different for each camera by the crime prevention apparatus 20 (in this embodiment, information combining alphabets and numbers) in order to identify the camera 40.

  By the way, in the crime prevention system 10 according to the present embodiment, each camera 40 is fixed in the shooting range (view angle) within a predetermined range by fixing the shooting direction and the enlargement ratio, and the state The pixel position by the solid-state image sensor incorporated in each camera 40 and the corresponding position coordinate in the XY coordinate system are stored in association with each other, and the camera position is obtained from the camera 40 based on this information. The position of a person existing in the image of the monitoring target area 60 indicated by the image information is specified.

  The pixel position and the position coordinate in the position information database DB4 correspond to the pixel position by the solid-state imaging device and the position coordinate in the XY coordinate system. The position of a person existing in the displayed image can be specified.

  In the position information database DB4 according to the present embodiment, as shown in FIG. 8, as the pixel position, a pair of diagonal coordinates of a rectangular pixel region (imaging region) in the solid-state imaging device. 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, as shown in FIG. 9 as an example, the criminal rate database DB5 stores a combination of sex, age, and single conditions for each crime type, and the criminal rate corresponding to each condition. It is comprised so that it may memorize | store for every combination.

  The crime type is information indicating the type of crime targeted by the crime prevention system 10 according to the present embodiment. In the crime prevention system 10 according to the present embodiment, the crime types are five types of crimes of assault, injury, forced obscenity, public obscenity, and general kidnapping, but not limited to this. It goes without saying that other types of crimes committed against this may be targeted, and any of the above five types may be excluded from the target.

  In addition, it is a condition that indicates whether the gender in the above conditions is male or female, and is a condition that indicates whether the age is young or not, whether single or multiple acts alone or multiple. It is a condition to show. In the crime prevention system 10 according to the present embodiment, whether or not the age is young is determined based on whether or not the age is less than 20, but it goes without saying that the present invention is not limited to this. .

  Further, the criminal rate is information indicating a criminal rate that is a probability that a person who matches a combination of corresponding conditions will perform the corresponding crime.

  In the crime prevention system 10 according to the present embodiment, the probability P (B) and the probability P (A | B) for each combination of corresponding conditions are converted into statistical values shown in FIGS. 15 to 19 as an example. Derived based on. In addition, the crime prevention system 10 observes the ratio of the number of people who apply the probability P (A) to the combination of the corresponding conditions with respect to the total number of people present in the time zone to be monitored in the monitoring target area 60. Derived based on past statistics. Then, a value obtained by substituting the derived probability P (B), probability P (A | B), and probability P (A) into the equation (1) is registered as the criminal rate.

  Note that the statistical values shown in FIGS. 15 to 19 show values for a plurality of years. In this case, the value of the year closest to the current time is applied, and the value of the year with the highest number of crimes is applied. In the crime prevention system 10 according to the present embodiment, the probability P (B) is calculated by applying the value of the year with the largest number of cases. And the probability P (A | B) is derived.

On the other hand, as shown in FIG. 10 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. In addition, S ₁ , S ₂ ,... Represent different indefinite persons, and V ₁ , V ₂ ,.

  By the way, in the crime prevention system 10 according to the present embodiment, the crime type targeted for crime prevention (hereinafter referred to as “crime type targeted for crime prevention”) may be designated via the keyboard 20E of the crime prevention device 20 or the like. In the crime prevention system 10, crime prevention is performed with respect to the designated crime target crime type.

  Next, the operation of the crime prevention system 10 according to the present embodiment will be described with reference to FIG. FIG. 11 is a flowchart showing a flow of processing of a crime prevention program executed by the CPU 20A when an execution instruction is received via the keyboard 20E of the crime prevention device 20 or the like. The program is a secondary storage. Stored in advance in the program area PG of the unit 20D. In addition, here, in order to avoid complications, the identification information database DB1, the attribute information database DB2, the obstacle information database DB3, the location information database DB4, and the criminal rate database DB5 are constructed in advance, and crime types targeted for crime prevention The case where is already specified will be described.

  In step 100 in the figure, all the information related to the monitoring target area 60 to be processed is read from the identification information database DB1, the attribute information database DB2, and the position information database DB4, and designated in advance from the criminal rate database DB5. All the information related to crime types targeted for crime prevention is read out, and in the next step 102, image information indicating captured images is acquired from all the cameras 40. In the next step 104, all identification information received by each antenna 30 is acquired. To get.

  In the next step 106, all persons existing in the image are detected from the image indicated by the image information acquired by the process of step 102, and the positions of the detected persons are detected by the position information database DB4 by the process of step 100. Detection is performed by the above-described method using information read from. In addition, the detection of the person who exists in the said image from the said image is a technique etc. which are used by FieldAnalyst (registered trademark) (NEC Soft Corp.), IMS (Intelligent Monitoring System, Exit Corp.) etc. as an example. This can be done by a conventionally known technique.

  In the next step 108, based on the identification information acquired by the process of step 104, the types of all persons detected by the process of step 106 are specified as follows.

  First, the position of the person (hereinafter referred to as “IC tag holder”) who has the IC tag 90 that transmitted the identification information acquired by the process of step 104 is specified by the above-described triangulation technique, The types of all IC tag holders are specified by referring to the types corresponding to the acquired identification information from the information read from the identification information database DB1 by the process of step 100 above.

  Next, the positions of all persons detected by the process of step 106 (hereinafter referred to as “regional person”) are compared with the positions of all identified IC tag holders, and the positions of the IC tag holders are compared. By identifying the person who is in the area closest to the person who is the same person as the IC tag holder, the type of the IC tag holder among the person in the area is specified.

  Finally, it is determined that the person in the area excluding the IC tag holder is an indefinite person.

In the next step 110, the distance between the defender and the defender identified by the processing in step 108 is calculated for all combinations of the defender and the defender by the following equation (2), and the secondary storage unit 20D. Is stored in a predetermined area. Note that in equation (2), 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 112, the distance between the indeterminate person and the defensive person specified by the process in step 108 is calculated for all combinations of the indefinite person and the defensive person by the following equation (3), and the secondary storage unit 20D Is stored in a predetermined area. In Equation (3), 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 114, it is determined whether or not the execution of the processing of the above steps 102 to 112 is the first execution after the execution of the crime prevention program is started. On the other hand, if the determination is negative, the process proceeds to step 116.

In step 116, the following equation (4) and (5), 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 (4) is a distance between the defender G _k and the defender V _i before the predetermined time δt from the present time, and D _ViSj (t−δt) in the equation (5). ) 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 110 and step 112 is applied.

In the calculation of this step 116, it is necessary to apply the values obtained by the previous processing of step 110 and step 112 related to the same person to each of the defender, the defender, and the indefinite person. For a person who is a person and a defender, a person whose identification information previously obtained by the process of step 104 and the identification information obtained this time coincides may be applied as the same person. The same person may be specified by the image recognition technique such as a conventionally known pattern matching technique using the image information obtained last time and the image information obtained this time.

As an example, as shown in FIG. 12, the distance D _ViGk (t + δt) according to the flow lines of the defender G _k , the defender V _i , and the indefinite person S _j is obtained by the calculation in this step 116. And the distance D _ViSj (t + δt) can be predicted with high accuracy.

In the next step 118, the condition in the criminal rate database DB5 regarding the indeterminate person _Sj is estimated. The gender and age of the indeterminate person S _j can be estimated by a conventionally known technique such as the technique used in the IMS or the like as an example. Further, the estimation as to whether or not the indeterminate person S _j is acting alone is that the distance from the position of the indeterminate person S _j detected by the processing of step 106 is within a predetermined threshold (2 m in the present embodiment). It can be performed by estimating that the person is acting alone when there is no other indeterminate person, and presuming that the person is acting plurally when the other person is uncertain.

In the next step 120, the criminal rate P _j corresponding to the combination of the conditions of the indefinite person S _j estimated by the process of step 118 is acquired from the information read from the criminal rate database DB5 by the process of step 100. And is stored in a predetermined area of the secondary storage unit 20D in association with the corresponding indefinite person _Sj .

In the next step 122, the distance D _ViGk (t + δt) and the distance D _ViSj (t + δt) obtained by the process of step 116 and the criminal rate P _j obtained by the process of step 120 are expressed by the following (6 ), The crime risk value R _ij (t + δt) indicating the level of crime risk for the defender V _i by the indefinite person S _j after a predetermined time δt is calculated and stored in the crime risk value database DB6. (sign up. Here, min _k () in Equation (6) is a function indicating that the minimum value for all k of the calculation results in parentheses is applied.

In the next step 124, the crime risk value R _ij (t + δt) obtained by the process in the above step 122 is used to execute a predetermined process for preventing crime, and then the process proceeds to step 126.

In the crime prevention program according to the present embodiment, the following five types of processes are applied as the predetermined processes in step 124.
Process 1. A process of displaying the crime risk value R _ij (t + δt) and the criminal rate 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 criminal rate P _j is equal to or greater than a predetermined second threshold value.
Process 5. When the criminal rate P _j is equal to or greater than the predetermined second threshold, a process of notifying that there is an indeterminate person with a high criminal rate nearby to the defender closest to the target indeterminate person.

  In addition, when applying the process 2 and the process 4 above, a speaker is provided in the monitoring target area 60 and a warning is issued by the speaker, and a PDA ( Various forms such as a form for issuing a warning via a terminal device such as a personal digital assistant or a portable information terminal can be applied.

  In addition, when applying the process 3 described above, a speaker is provided in the monitoring target area 60, and the speaker notifies the defender closest to the target defender that the crime risk is high. Various forms can be applied, such as a form that notifies the defender that the crime risk is high via a terminal device such as a PDA.

  Furthermore, even when the process 5 is applied, a speaker is provided in the monitoring target area 60, and the speaker is an indeterminate person who has a high criminal rate with respect to the defender closest to the target indeterminate person. Various forms, such as a form for notifying that the person is near, a form for notifying the defender that an unidentified person with a high criminal rate is 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 program according to the present embodiment, the five types of processing 1 to 5 are applied as the predetermined processing. Any one of these or a combination of up to four may be applied.

  In step 126, it is determined whether or not a predetermined end condition is satisfied. If the determination is negative, the process proceeds to step 128 and waits for a predetermined time, and then returns to step 102. If the determination in step 126 is affirmative, the crime prevention program is terminated. The predetermined time applied in step 128 is a time that is adjusted in advance so that the repetition process of steps 102 to 128 is executed at intervals of the predetermined time δt as much as possible. Further, in the crime prevention program according to the present embodiment, the condition that the time set in advance as the time to end the monitoring of the monitoring target area 60 has been applied as the end condition to be applied in the processing of step 126 described above. However, the present invention is not limited to this. For example, a condition that an instruction input for instructing the end of the crime prevention program is made via the keyboard 20E or the like, and the remaining storage capacity of the secondary storage unit 20D is a predetermined amount. It goes without saying that other conditions such as the following conditions can also be applied.

  The process of step 106 of the crime prevention program is the detection means of the present invention, the process of step 108 is the specifying means of the present invention, the processes of steps 110 and 112 are the distance deriving means of the present invention, and the process of step 116 is In the distance predicting means of the present invention, the processing of step 118 is the estimating means of the present invention, the processing of step 120 is the deriving means of the present invention, the processing of step 122 is the computing means of the present invention, and the processing of step 124 is the present. Each corresponds to the processing execution means of the invention.

  As described above in detail, in the present embodiment, based on the image information acquired by the imaging means (here, the camera 40) that acquires the image information of the target area in real time by imaging the target area. The position of the person existing in the target area is detected at a predetermined time interval (here, the predetermined time δt interval), and whether or not the detected person is a predetermined defender and an indefinite person excluding the defender. Based on the image information, the age, gender, and the number of people who act together (in this case, single or multiple) Deriving a criminal rate that is the probability that the indefinite person commits a crime, and calculating a criminal risk value indicating the level of criminal risk by the indeterminate against the defender based on the derived criminal rate, Crime Since a predetermined process is executed to prevent a crime using a risk value, a process predetermined to prevent a crime based on a criminal rate by an unspecified person derived with high accuracy As a result, the crime can be more effectively prevented as compared with the case where the present invention is not applied.

  Further, in the present embodiment, the criminal rate (here, the criminal rate) derived based on the percentage of crimes actually committed by people corresponding to all conditions of age, gender, and the number of people acting together. The criminal rate registered in the criminal rate database DB5) is stored in advance by the storage means (here, the secondary storage unit 20D) in association with the corresponding condition, and the criminal rate corresponding to the estimation result is stored. Since the criminal rate is derived by reading from the storage means, the criminal rate can be derived more easily and in a short time.

  In particular, in the present embodiment, the criminal rate is derived in advance based on the Bayesian theory from the statistical values of the number of past crimes, so that the criminal rate can be derived more easily and with high accuracy. .

  In this embodiment, since the criminal rate is derived for each crime type, crime can be prevented for each crime type.

Further, in the present embodiment, it is specified whether the detected person is the defender, the defender, or the indefinite person, and based on the position of the detected person and the identification result, the defender 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 of the first distance to the second distance and the derived criminal rate, so that the defender can be used effectively. As a result, crime can be prevented more efficiently.

Further, 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 criminal rate, the result of being able to predict the crime risk value after the predetermined time, more Immediate 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 criminal rate, the process of displaying the criminal risk value and the criminal rate, the crime risk value And a process for issuing a warning when the criminal rate is equal to or higher than a predetermined threshold, a process for notifying that the criminal risk is high for the defender closest to the target defender, and the criminal rate is Since the process of notifying that there is an indeterminate person with a high criminal rate nearby to the defender closest to the indeterminate person who is equal to or greater than a predetermined threshold, obtain an effect according to these processes. Can do.

  Furthermore, in the present embodiment, since the positions of the defender and the defender existing in the target area are detected at the predetermined time intervals using an IC tag, the present invention is more easily realized. It is possible to prevent crimes with higher accuracy.

[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 criminal rate of the undefined person has been described. In the second embodiment, the crime risk value is calculated based on the time for the defensive person to reach the defensive person, the time for the undefined person to reach the defensive person, and the criminal rate of the undefined person. An example will be described.

  The configuration of the crime prevention system 10 according to the second embodiment is the same as that of the crime prevention system 10 according to the first embodiment (see FIGS. 1 to 4). Description is omitted.

  Next, the operation of the crime prevention system 10 according to the second embodiment will be described with reference to FIG. FIG. 13 shows the flow of processing of the crime prevention 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 is a flowchart, and the program is stored in advance in the program area PG of the secondary storage unit 20D. Further, steps in FIG. 13 that execute the same processing as in FIG. 11 are denoted by the same step numbers as in FIG. 11, and description thereof is omitted here.

In step 111 of the figure, by substituting the distance D _ViGk (t) obtained by the processing of step 110 into the following equation (7), the time P _ViGk ( t) is calculated and stored in a predetermined area of the secondary storage unit 20D. Here, the F in the equation (7), (as one example, 1.3 m / s) average walking speed of adults is, _{W G} is one or more weighted values for the walking speed F.

In this embodiment, as the weighting value W _G, corresponding to the information read from the attribute information database DB2 by the processing of step 100, the identification information corresponding defensive individual is acquired from the IC tag 90 in possession Information on age, gender, and height of attributes to be extracted is extracted, and values corresponding to these 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. compared with increases in the case, and calculates the weighting value W _G to be larger as the height increases.

In this way, crime prevention system 10 according to the present embodiment, as a weighting value W _G, the age of the corresponding defensive person, although derived by applying all the sex and height, is not limited thereto, For example, it may be a form derived by applying any one of these age, gender, or height, or a combination of the two, and a form derived by applying a parameter that affects other travel speeds. You can also.

On the other hand, at Step 113, the distance _{P ViSj} (t) obtained by the processing at Step 112 above is substituted into the following equation (8) to allow each indeterminate person to reach each defender P _ViSj (t ) And is stored in a predetermined area of the secondary storage unit 20D. Here is one or more weighted values for W _S is walking speed F in (8).

In this embodiment, as the weighting value W _S, the age of the corresponding undefined person, gender, estimates the height, is applied a value corresponding to the information. Note that the age, sex, and height of the indeterminate person can be estimated by a conventionally known technique such as the technique used in the IMS or the like 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. increases, and it calculates the weighting value W _S so as to be larger as the height increases.

Thus, in the crime prevention system 10 according to the present embodiment, even if the weighting value W _S, similarly to the weighting value W _G, derived by applying the age of the corresponding defensive person, gender, and all height 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 parameters that affect other traveling speeds may be used. It is also possible to adopt a form derived by applying.

On the other hand, in step 116 ', the following equation (9) and (10), the predetermined time .DELTA.t defense's _{G k} after (here one second) time to reach the defensive person _{V i P ViGk (t + δt} ) And the time P _ViSj (t + δt) for the indeterminate person S _j to reach the defender V _i is calculated (predicted). Here, P _ViGk (t−δt) in the equation (9) is the time for the defender G _k to reach the defender V _i before the predetermined time δt from the current time, and P _ViSj (t− in the equation (10)). 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 111 and step 113 is applied.

In the calculation of step 116 ′, it is necessary to apply the values obtained by the previous processing of step 111 and step 113 related to the same person for each of the defender, the defender, and the indeterminate. For the defender and the defender, a person whose identification information previously obtained by the processing of step 104 and the identification information obtained this time coincides may be applied as the same person. The same person may be specified by an image recognition technique such as a conventionally known pattern matching technique using the image information obtained last time by the processing and the image information obtained this time.

As an example, as shown in FIG. 14 by the calculation in step 116 ′, 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 117, the traveling direction of the defender V _{i and} the traveling direction of the indefinite person S _j are derived. In the crime prevention 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 process of the previous step 106 and the process of the current step 106. This is performed 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 same person, but is not limited to this. The difference between the positions of the defender V _i and the undefined person S _j obtained by the processing and the positions of the defender V _i and the undefined person S _j obtained by the process of the previous step 106 (hereinafter referred to as “first” a difference "hereinafter.), a position of the defensive's V _i and unspecified persons S _j obtained by the processing of the previous step 106, the defense's V _i and indeterminate obtained by the process of this step 106 Difference between the position of 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, the other It can also be in the form.

Thereafter, in step 122 ′, the arrival time P _ViGk (t + δt) and the arrival time P _ViSj (t + δt) obtained by the process of step 116 ′ and the criminal rate P _j obtained by the process of step 120 are calculated. By substituting into the following equation (11), a crime risk value R _ij (t + δt) ′ indicating the level of crime risk against the defender V _i by the indefinite person S _j after a predetermined time δt is calculated, and the crime risk Store (register) in the value database DB5. Here, (11) W _VS in the equation, one or more weighting values as the value becomes larger near the traveling direction of the traveling direction to be defensive person V _i indefinite's S _j obtained by the process of step 117 Yes, min _k () is a function indicating that the minimum value for all k of the operation results in parentheses is applied.

The steps 111 and 113 of the crime prevention program are the arrival time deriving means and second estimation means of the present invention, the processing of step 116 'is the arrival time prediction means of the present invention, and the process of step 117 is the present invention. The processing in step 122 ′ corresponds to the advancing direction deriving means and the computing means of the present invention.

As described above in detail, the second embodiment can achieve substantially the same effects as those of the first embodiment, and the defender can use the first distance based on the first distance. A first arrival time (here, arrival time P _ViGk (t)) that is a time to reach the defender is derived, and the time that the indeterminate person reaches the defender based on the second distance. The second arrival time (here, arrival time P _ViSj (t)) is derived, and the crime is based on the ratio of the derived first arrival time to the second arrival time and the derived criminal rate. Since the risk value is calculated, crime can be prevented with higher accuracy.

  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 for reaching the defender and the time for the indeterminate to reach the defender, and the derived criminal rate, after the predetermined time Can predict the crime risk value of That 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, 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 (4) and (5) are applied as the distance between the defender and the defender and the distance between the indeterminate person and the defender, and the second In the embodiment, the case where the predicted values obtained by the equations (9) and (10) are applied as the time for the defender to reach the defender and the time for the indefinite 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 116 of the crime prevention program (see FIG. 11) according to the first embodiment is deleted, and crime is performed in step 122. An arithmetic expression applied to calculate the risk value is the following expression (12).

In addition, when applying the actual reach to the second embodiment, the step 116 ′ of the crime prevention program (see FIG. 13) according to the second embodiment is deleted. An arithmetic expression applied to calculate the crime risk value in step 122 ′ is the following expression (13).

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

  Further, in each of the above embodiments, the case where the crime risk value is derived without considering any obstacles present in the monitoring target area 60 has been described, but the present invention is not limited to this, The crime risk value may be derived in consideration of the obstacle.

  As an example of this case, in steps 110 and 112 of the crime prevention program, the distance between the defender and the defender (hereinafter referred to as “first distance”) and the distance between the indeterminate person and the defender (hereinafter referred to as “first distance”). When deriving “the second distance”), when there is an obstacle area indicated by the area information registered in the obstacle information database DB3 between the defender and the defender, The first distance is derived as a detour for the obstacle area, and if the obstacle area exists between the indefinite person and the defender, the first distance is assumed as a detour for the obstacle area. A mode of deriving the distance of 2 can be exemplified. In this case, the secondary storage unit 20D corresponds to the area information storage unit of the present invention.

  Thereby, crime can be prevented with higher accuracy.

  In each of the above embodiments, the case where the positions of the defender and the defender are detected using the IC tag 90 has been described. However, the present invention is not limited to this, for example, using GPS. Thus, the positions of the defender and the defender can be detected.

  As an example of this case, the guarder and the defender have a device and a wireless transmission device that can specify their own position by GPS, information indicating the position specified by the device, The form which transmits the identification information 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 this case, it is not necessary to provide the antenna 30 in the monitoring target area, so that the present invention can be realized more easily than in the above embodiments.

  Further, in each of the above embodiments, the case where the antenna 30 and the camera 40 are electrically connected to the crime prevention apparatus 20 by wire has been described, but the present invention is not limited to this, and these Each device can be electrically connected wirelessly. Also in this case, the same effects as those of the above embodiments can be obtained.

  In each of the above embodiments, the case where four cameras 40 are provided has been described. However, the present invention is not limited to this, and only one camera 40 may be provided, and a plurality of cameras other than four may be provided. Needless to say, it may be provided. In these cases, the same effects as those in the above embodiments can be obtained.

  In each of the above-described embodiments, the case where the Euclidean distance is applied as the distance of the present invention has been described. However, the present invention is not limited to this, and, for example, a form in which another distance such as a Manhattan distance is applied. It can also be. Also in this case, the same effects as those of the above embodiments can be obtained.

  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, and for example, the IC tag 90 includes the IC tag 90. It is also possible to store in advance attribute information related to the person who owns and acquire the attribute information via the antenna 30. Also in this case, the same effects as those of the above embodiments can be obtained.

  Further, in each of the above embodiments, the case where a camera capable of shooting a moving image in color is applied as the shooting means of the present invention, but the present invention is not limited to this, for example, Another camera such as a camera capable of shooting a moving image in monochrome or an infrared camera may be applied. Also in this case, the same effects as those of the above embodiments can be obtained.

  Moreover, in each said embodiment, although the case where a park was applied as an object area | region of this invention was demonstrated, this invention is not limited to this, For example, the form which applies other areas, such as an open space It can also be. Also in this case, the same effects as those of the above embodiments can be obtained.

  In addition, the application target of the attribute described in each of the above embodiments is also an example. For example, when the status of the attribute of the defender is a child, the crime risk value is increased as compared with other cases. It can also be a form or the like.

  In each of the above-described embodiments, the case where the age, sex, and the number of people acting together are applied as the conditions for the indeterminate to be applied when the criminal rate of the indeterminate is derived. However, the present invention is not limited to this, and one of these three kinds of conditions or a combination of the two can be applied. In addition, for these three conditions, the clothes of unspecified persons (such as “wearing sunglasses”), appearance (such as “foreigners”), personal belongings (such as “having a knife”), behavior patterns ( It is also possible to adopt a form in which one or a combination of these conditions is applied, including conditions such as “drunk wind”. In these cases, the criminal rate corresponding to the applied condition is registered and applied to the criminal rate database DB5. Also in this case, the same effects as those of the above embodiments can be obtained.

  In each of the above embodiments, the age condition is divided into two stages of “young” and “not young”, and the condition of the number of persons acting together is “single” and “multiple”. Although the case where it divided into two steps was demonstrated, this invention is not limited to this, For example, about the conditions of the said age, less than 20 years old, less than 20 years old and less than 30 years old, more than 30 years old and less than 40 years old, It is good also as a form divided into 3 steps or more like, and about the conditions of the number of people who act together, for example, alone, 2-3 people, 4-5 people, ... It is good also as a form which divides into three steps or more. Also in this case, the criminal rate according to the condition set to the same category as the applied category is registered and applied to the criminal rate database DB5. Also in this case, the same effects as those of the above embodiments can be obtained.

  In addition, the configuration of the crime prevention system 10 described in the above embodiments (see FIGS. 1 to 4) is merely 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 process flow of the crime prevention program shown in the above embodiments (see FIGS. 11 and 13) is also an example, and unnecessary processing steps can be deleted without departing from the gist of the present invention. Needless to say, new processing steps can be added or the order of the processing steps can be changed.

  The configurations of various databases shown in the embodiments (see FIGS. 5 to 10) are also examples, and some information may be deleted or new within the scope not departing from the gist of the 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 the expressions (1) to (13)) 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.

It is a mimetic diagram showing the whole crime prevention system composition concerning an embodiment. It is a schematic diagram which shows the arrangement | positioning relationship etc. of each part which comprises the crime prevention system which concerns on embodiment. 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 obstruction 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 criminal rate 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 crime prevention program which concerns on 1st Embodiment. It is a schematic diagram with which it uses for description of the process by the crime prevention program which concerns on 1st Embodiment. It is a flowchart which shows the flow of a process of the crime prevention program which concerns on 2nd Embodiment. It is a schematic diagram with which it uses for description of the process by the crime prevention program which concerns on 2nd Embodiment. It is a graph which shows the number of crime occurrences of domestic assault published by the National Police Agency. It is a graph which shows the crime occurrence number of the injury in Japan which the National Police Agency announced. It is a graph showing the number of compulsory obscene crimes in Japan that the National Police Agency announced. It is a graph showing the number of public obscene crimes published in Japan by the National Police Agency. It is a graph which shows the number of crime occurrences of domestic kidnapping published by the National Police Agency.

Explanation of symbols

10 Crime Prevention System 20 Crime Prevention Device 20A CPU
20D secondary storage unit (storage means, identification information storage means, area information storage means)
20F Display 30 Antenna (Acquisition means)
40 Camera (photographing means)
90 IC tag DB1 Identification information database DB2 Attribute information database DB3 Obstacle information database DB4 Location information database DB5 Criminal rate database DB6 Crime risk value database

Claims (13)

Photographing means for obtaining image information of the target area in real time by photographing the target area;
Detecting 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;
Estimating means for estimating at least one of the age, sex, and the number of people acting together determined by the specifying means based on the image information;
Deriving means for deriving a criminal rate that is a probability that the undetermined person commits a crime based on the estimation result by the estimating means;
Based on the criminal rate derived by the derivation means, calculation means for calculating a crime risk value indicating the level of crime risk by the indeterminate against the defender;
Using the crime risk value calculated by the calculation means, a process execution means for executing a process predetermined as preventing crime,
Crime prevention device equipped with. Corresponding to the criminal rate derived based on the proportion of crimes actually committed by people corresponding to at least one condition of age, gender, and the number of people acting together estimated by the estimation means Storage means stored in advance associated with the condition to be
The crime prevention apparatus according to claim 1, wherein the derivation unit derives the criminal rate by reading a criminal rate corresponding to the estimation result by the estimation unit from the storage unit. The crime prevention device according to claim 1, wherein the criminal rate is derived in advance based on a Bayesian theory from a statistical value of the number of past crime occurrences. The crime prevention apparatus according to any one of claims 1 to 3, wherein the derivation means derives the criminal rate for each crime type. 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 indefinite 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 criminal rate derived by the deriving means. The crime prevention device according to claim 4. The defender after the predetermined time based on the amount of change between the first distance derived by the distance deriving means at the present time and the first distance derived by the distance deriving means at the time before the predetermined time; While predicting the distance of the defender, the amount of change between the second distance derived by the distance deriving means at the present time and the second distance derived by the distance deriving means at the time before the predetermined time Further comprising distance predicting means for predicting the distance between the indeterminate person and the defender after the predetermined time,
The calculating means includes a ratio between the distance between the defender and the defender predicted by the distance predicting means, a distance between the indeterminate person and the defender, and a criminal rate derived by the deriving means. The crime prevention apparatus according to claim 5, wherein the crime risk value is calculated based on the crime. 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 computing means computes the crime risk value based on a ratio between the first arrival time and the second arrival time derived by the arrival time deriving means, and a criminal rate derived by the deriving means. Item 6. A crime prevention apparatus according to item 5. Based on the amount of change between 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, the time after the predetermined time The time that the defender reaches the defender is predicted, and the second arrival time derived by the arrival time deriving means at the present time and the arrival time deriving means at the time before the predetermined time An arrival time predicting means for predicting the time when the indeterminate person after the predetermined time reaches the defender based on the amount of change from the second arrival time;
The computing means is derived by the ratio of the time that the defender arrives at the defender predicted by the arrival time predicting means and the time at which the indefinite person reaches the defender, and derived by the deriving means. The crime prevention apparatus according to claim 7, wherein the crime risk value is calculated based on the committed criminal rate. A traveling direction deriving means for deriving the traveling direction of the defender and the traveling direction of the indeterminate person;
The said calculating means calculates the said crime risk value so that a value becomes large, so that the advancing direction of the said uncertain person is near to the advancing direction of the said defensive person derived | led-out by the said advancing direction deriving means. 9. The crime prevention apparatus according to any one of items 8. A region information storage unit that stores in advance region information indicating an area of an obstacle that hinders a person's walking in the target region,
The distance deriving means derives the first distance assuming that the area of the obstacle is detoured when the area of the obstacle indicated by the area information exists between the defender and the defender. When the area of the obstacle exists between the indeterminate person and the defender, the second distance is derived as a detour around the area of the obstacle. The crime prevention device according to any one of 9. These are information for identifying the defender given in advance to the defender, and information for identifying the defender given in advance to the defender. Identification information storage means for storing the defender identification information in advance;
Obtaining means for obtaining any identification information of the defender identification information and the defender identification information from a person detected by the detection means;
Further comprising
The identification means identifies that the person who acquired the identification information is the defender when the identification information acquired by the acquisition means matches the defender identification information stored by the identification information storage means When the identification information acquired by the acquisition means matches the defender identification information stored by the identification information storage means, the person who acquired the identification information is identified as the defender. The crime prevention device according to any one of claims 1 to 10, wherein another person is identified as an indefinite person. The process execution means includes, as the predetermined process, a process for storing at least one of the crime risk value and the criminal rate, a process for displaying at least one of the criminal risk value and the criminal rate, A process for issuing a warning when at least one of the risk value and the criminal rate is equal to or greater than a predetermined threshold, a process for notifying that the criminal risk is high for the defender closest to the target defender, The at least one process of notifying that there is an indeterminate person with a high criminal rate nearby to the defender closest to the indeterminate person whose criminal rate is equal to or greater than the predetermined threshold is executed. The crime prevention apparatus according to any one of claims 11 to 11. Computer
Detecting means for detecting a position of a person existing in the target area at predetermined time intervals based on image information acquired by an imaging unit that acquires image information of the target area in real time 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;
Estimating means for estimating at least one of the age, sex, and number of people acting together determined by the specifying means based on the image information;
Deriving means for deriving a criminal rate that is a probability that the undetermined person commits a crime based on the estimation result by the estimating means;
Based on the criminal rate derived by the derivation means, calculation means for calculating a crime risk value indicating the level of crime risk by the indeterminate against the defender;
Using the crime risk value calculated by the calculation means, a process execution means for executing a process predetermined as preventing crime,
Program to function as.