JP2010108037A - Action tracking system, action tracking method, and action tracking program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To track the action of an individual without neither requiring the individual to possess a special device nor to concern about the violation of his/her privacy. <P>SOLUTION: An action tracking system 1 includes: a control part 11; an identification information reading part 12; a person information storage part 13; an information selecting part 14; a person position detecting part 15; a determining part 16; and a position information storage part 17. The identification information reading part 12 reads identification information of a user 3, and recognizes the user 3. The determining part 16 compares positions detected by the person position detecting part 15 with positions expressed by the individual characters and conducts of the users 3 called by the information selecting part 14 with respect to the plurality of users 3, thereby determining that the user 3 with the least distance is the specified user 3. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an action tracking system, an action tracking method, and an action tracking program.

  In recent years, with the development of sensing technology, it is becoming possible to measure a person's position and recognize a person's behavior. Sensors for security measures such as late-night parking lots and shopping streets, and sensors for preventing elevator jamming. In addition, sensor lights that automatically turn on when people are detected are not only safe, but also have convenience and energy saving effects, and are widely used.

  Not only sensing technology but also network technology has advanced, sensors are installed in various places, and their purposes are diversified. By associating the collected information with time series, you can relive what happened in the past, predict the future by matching the information up to now and the past information, and propose actions .

  In Patent Document 1, the identification information of a plurality of moving bodies and the data (shape data / sound data / weight data) representing the characteristics of each of the plurality of moving bodies are stored in a database unit in association with each other. It is described that a mobile object identification / tracking apparatus using a data correlation process that can be tracked / identified even when there is a large number of mobile objects is not provided.

  In Patent Literature 2, an image is captured by a camera, user recognition is performed, user work behavior is estimated, and work support sufficiently corresponding to a cooking facility function is automatically performed according to a kitchen work situation for each user. It is described to provide a kitchen work support system that can.

  In Patent Document 3, the user's goal is detected based on the user's activity state or environmental situation detected by monitoring the activity with a sensor group, and the user's activity for achieving the goal is planned, and the plan is made. It is described that effective information suggesting activities is presented according to the environment and emotions.

  In Patent Document 4, mobile body information that is information on a mobile body that passes through a specific position is acquired from a specific position sensor that monitors a specific position in a predetermined range, and collated with the mobile body information acquired by the specific position sensor. As possible information, the tracking result by the tracking sensor is converted into moving body information that is information on the moving body that passes through the specific position, and the converted moving body information matches the moving body information acquired by the specific position sensor. Whether or not the reliability of the tracking result by the tracking sensor is determined.

  In Patent Document 5, passers are classified based on a face detection result by a first face detection unit and a face detection result by a second face detection unit, and face matching by a face matching unit is performed based on the classification result. The threshold value for authentication used in the process is adjusted, and the face matching unit calculates the similarity with the registrant's facial feature information, and whether the calculated similarity is equal to or higher than the adjusted authentication threshold. It describes a person recognition device and a person recognition method for determining whether or not a passerby is a registered person.

  Patent Document 6 relates to a position information tracking system using an electronic tag, and the mobile electronic tag uses a built-in battery as a power source even if the mobile phone cannot communicate without depending on the GPS function or the like. As described above, it is described that the position information of a management subject such as a child is tracked by generating an electromagnetic wave and transmitting an identification number to a fixed electronic tag.

Japanese Patent Application Laid-Open No. 07-287781 JP-A-2005-284408 JP 2005-332309 A JP 2008-046927 A JP 2008-108243 A JP 2008-113308 A

  However, in the identification / tracking device of Patent Document 1, the sensors included are a direction sensor, a distance sensor, a weight sensor, and a sound sensor, which may make installation difficult. In the techniques of Patent Literature 2 and Patent Literature 5, since monitoring is performed by an installed camera, there is a risk that personal privacy may be infringed. In the techniques of Patent Document 3 and Patent Document 6, it is necessary for a user to carry or wear an electronic tag or a sensor, and to notify the position according to movement, which is inconvenient in daily life. In the tracking reliability determination of Patent Document 4, the moving body mainly assumes a vehicle, and the behavior pattern is different from that when a person is assumed.

  The present invention has been made in view of the above circumstances, and it is not necessary for an individual to have a special device, and there is no risk of infringement of privacy, and an action tracking system and an action tracking method capable of tracking the individual's behavior And to provide a behavior tracking program.

The behavior tracking system according to the first aspect of the present invention is:
A storage means for storing an identification code unique to the person and information representing the personality line of the person to be tracked in association with each other;
Recognizing means for acquiring the identification code of a person existing in a limited space of a subject whose behavior is to be tracked;
For each place where the space is divided, a person detecting means for detecting the presence of a person and acquiring positional information representing the place where the person exists;
The position information acquired by the person detecting means is compared with the information indicating the individuality line corresponding to the identification code of the person existing in the space acquired by the recognizing means, and the personality line closest to the position information is compared. Determining means for associating an identification code corresponding to information representing the position information of a person existing in the place;
It is characterized by providing.

The behavior tracking method according to the second aspect of the present invention includes:
A recognition step for obtaining an identification code unique to a person existing in a limited space for tracking an action;
A personality line information acquisition step of acquiring information representing a personality line of a person corresponding to the identification code recognized in the recognition step;
For each place where the space is divided, a person detection step of detecting the presence of a person and obtaining position information representing the place where the person exists;
The position information acquired in the human detection step is compared with the information indicating the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. A determination step of associating an identification code corresponding to information representing a close personality line with position information of a person existing in the place;
It is characterized by providing.

The behavior tracking program according to the third aspect of the present invention is:
On the computer,
A recognition step for obtaining an identification code unique to a person existing in a limited space for tracking an action;
A personality line information acquisition step of acquiring information representing a personality line of a person corresponding to the identification code recognized in the recognition step;
For each place where the space is divided, a person detection step of detecting the presence of a person and obtaining position information representing the place where the person exists;
The position information acquired in the human detection step is compared with the information indicating the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. A determination step of associating an identification code corresponding to information representing a close personality line with position information of a person existing in the place;
Is executed.

  According to the present invention, it is not necessary for an individual to have a special device, and there is no risk of infringement of privacy, and the behavior of the individual can be tracked.

  In the present invention, individuality refers to a behavioral feature (癖) indicating behavior associated with some place. For example, a person who smokes often goes near the ashtray, and a person who drinks coffee often stops in front of the vending machine. In addition, the present invention includes a case where the person can be identified by a place, such as a seat that is fixed at the workplace. Furthermore, although not related to the place, the moving speed is also included in the personality line.

  In the present invention, privacy infringement means knowing the content of an individual's action, and does not include knowing the place where the individual has gone.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals.

(Embodiment 1)
FIG. 1 is a block diagram showing a configuration example of the entire behavior tracking system according to Embodiment 1 of the present invention. The behavior tracking system 1 includes a control unit 11, an identification information reading unit 12, a person information storage unit 13, an information selection unit 14, a person position detection unit 15, a determination unit 16, a position information storage unit 17, Is provided. With the program that operates in the control unit 11, each of the identification information reading unit 12, the person information storage unit 13, the information selection unit 14, the person position detection unit 15, the determination unit 16, and the position information storage unit 17 realizes an independent operation. To do.

  The identification information reading unit 12 receives identification information from the tag 31. The identification information reading unit 12 receives a signal transmitted by the tag 31 and detects information of the tag 31. The tag 31 is something the user has in some form. For example, the tag 31 is incorporated in the form of an IC card or the like in an admission card or a mobile phone or a wristwatch. There are various signal reception methods depending on the type of the tag 31, such as a type capable of non-contact wireless communication and a type directly passing through a card reader.

  The person information storage unit 13 stores the identifier of the tag 31 of the user 3, the name and identification number of the user 3 who owns the tag 31, and the personality row. Names, identification numbers, etc. and personality rows are stored in association with each other. The user 3 stored in the person information storage unit 13 is for the predetermined user 3 who tracks the behavior by the behavior tracking system 1, and there may be a plurality of users 3. Information is input and stored in advance using an input device (not shown) such as a keyboard.

  FIG. 2 shows an example of personal information stored in the personal information storage unit 13. The personal information indicates the user ID, name, and personality of the individual. Examples of personality activities include daily activities such as turning on an air conditioner or TV immediately after entering the room, using a dark fluorescent light, or sitting in a fixed chair. Can be mentioned.

  The information selection unit 14 reads the corresponding information from the person information storage unit 13 when any information is input. For example, the name of the user 3 can be read from the information representing the personality line, or the information representing the personality line can be read from the identification number of the user 3.

  The person position detection unit 15 converts the information of the sensor 2 and detects the position of the user 3. The sensor 2 detects an existing person for each of the divided parts of the detectable range, and transmits the information to the person position detection unit 15. For example, the sensor 2 is an infrared sensor or the like. When detecting the movement of a person in the set area, first, the change in the wavelength distribution of the infrared energy emitted from the object is measured. The direction in which the change is detected is the direction in which the person exists, and serves as information on the position in which the person exists. A method of detecting the direction of light received by rotating the sensor 2 or a method of arranging light receiving elements may be used. Although different from the sensor 2, the position of a person may be detected from an image captured by an infrared camera. The operation of the sensor 2 is started when the identification information reading unit 12 detects the information of the tag 31.

  The determination unit 16 compares the position detected by the person position detection unit 15 with the personality row of the user 3 called by the information selection unit 14 and determines which user 3 is the user 3. The range in which the user 3 acts is deeply related to personality and has different characteristics. From the detected position, the user 3 who is highly likely to be there is selected and determined by the determination unit 16.

  The position information storage unit 17 stores and saves information detected by the person position detection unit 15. The information stored at this time is the position information of the user 3 or the like. When the user 3 can be determined, not only the position information but also information for identifying an individual such as a name and a number are stored and stored together.

  FIG. 3 is an example illustrating a setting area of the behavior tracking system according to the first embodiment. The dotted line in FIG. 3 shows the tracking of the behavior of each user 3. The action tracking system 1 is installed near the entrance 4D of the setting area 4, and the sensor 2 is installed at one corner of the setting area 4. For example, as shown in FIG. 3, when the sensor is attached indoors and at the corner of a room, the sensor 2 capable of measuring a range of a central angle of 85 degrees and a radius of 12 m when used on a plane is used.

  User 3 sets two users, user 3A and user 3B. In the personality line, it is described that the user 3A smokes a cigarette and the user 3B opens a window. Due to the personality of the personal information, after entering the room, it is predicted that the user 3A goes to a place with an ashtray and the user 3B goes to a place with a window.

  The users 3A and 3B enter the setting area 4 by causing the behavior tracking system 1 to read the tag 31 when entering the room. The identification information reading unit 12 of the behavior tracking system 1 detects information of the tag 31. The information of the tag 31 is detected, the presence of the user 3 is recognized in the setting area 4, and the sensor 2 starts operation.

  The identification information reading unit 12 sends the information of the tag 31 to the person information storage unit 13, and it is understood that the user 3 is the users 3A and 3B. The person position detection unit 15 detects the presence or absence of a person with the sensor 2 in the divided area in the time to be measured, and creates the position data of the user 3. At this time, the behavior tracking system 1 includes information that there are two users 3 in the setting area 4 and that the position data indicates two locations.

  If two users 3A and 3B enter the setting area 4 and each act separately, and there is no contact at the same time and place, it is possible to track each user 3 as it is. When touching at the same time and the same position, for example, when entering the room at almost the same time, behavior tracking is performed without knowing which user 3 is.

  The information selection unit 14 selects information representing the personality row of the user 3 from the personal information storage unit 13 as soon as it is possible to determine who the user 3 entered the setting area 4 is. The position information detected by the sensor 2 is transmitted to the person position detection unit 15. The determination unit 16 compares the information represented by the personality row selected from the person information storage unit 13 and the position detected by the person position detection unit 15, and which user 3 is the user 3 at the detected position. Judgment is made.

  For example, if the position detected by the person position detection unit 15 gradually moves toward the ashtray, the user 3 is more likely to be the user 3A than the personality row of the person information storage unit 13. The determination unit 16 determines that the user 3 is the user 3A if there is information that detects the user 3 within a range (threshold value) predicted from the information represented by the personality row. Similarly, the determination unit 16 associates information that detects the user 3 in the vicinity of the window and information that opens the window written in the personality line, identifies the user 3 from the personality line, and the user 3 is the user 3B. Judge.

  The detected position is stored / saved in the position information storage unit 17 for each user 3. Every time a predetermined time elapses, the position information from the sensor 2 is detected by the person position detection unit 15, stored in the position information storage unit 17, and action tracking is performed. The end of the action tracking may be given to the identification information reading unit 12 as information that the user exits the setting area 4 as when entering the setting area 4. The action tracking may be terminated when the identification information is not read and the sensor 2 deviates from the measurable range or when the user leaves the setting area 4. Further, it can be arbitrarily set according to the purpose, for example, until a predetermined time has elapsed after entering the setting area 4 or when the user 3 stays at the same position for a certain time.

  For example, in the case of a company, the system is set so that action tracking is performed until 15 minutes have elapsed from the work start time. In the case of a bedroom in the house, the system is set to stop behavior tracking when the same place (bed) is shown for 5 minutes or more.

  FIG. 4 is a flowchart illustrating an example of presence recognition of the operation of the behavior tracking system according to the first embodiment. FIG. 5 is a flowchart showing an example of personal position determination of the operation of the behavior tracking system according to the first embodiment. The behavior tracking system 1 refers to FIG. The user 3 and the setting area 4 refer to FIG.

  First, presence recognition is performed. The identification information reading unit 12 always transmits and receives signals and reads the identification information of the user 3 by reading the information of the tag 31 (step S11). And it recognizes that the specific user 3 enters into the setting area 4 (step S12; YES). The personal information stored in the person information storage unit 13 is collated with the information read from the tag 31, and the presence of the user 3 is stored in, for example, the person information storage unit 13 or the position information storage unit 17 (step S13). Similarly, when the information is read and it is recognized that the user goes out of the setting area 4 (step S14; YES), the storage of the information on which the user 3 is present is erased (step S15).

  The identification information reading unit 12 always transmits / receives a carrier and recognizes the presence of the user 3 in the setting area 4 from the presence / absence of the identification information of the user 3. When the user 3 does not enter the setting area 4 (step S12; NO), information on the presence of the user 3 is not stored. Further, when the user 3 does not come out of the setting area 4 (step S14; NO), the storage of the information on which the user 3 is present is not performed. From the information obtained by presence recognition, it can be known which user 3 is in the setting area 4, and the information selection unit 14 selects information related to the personality of the user 3 who has been recognized.

  Next, the personal position is determined. The order in which the information indicating the personality row is selected is assigned to the user 3 as the i-th item, and the number assigned to the positions indicated by the number of the users 3 is indicated as the j-th item. At this time, the specific user 3 can be specified from the i-th.

  There are n users 3 and n positions are detected. The user 3 can be identified by determining whether all the detected positions are within the threshold of the action range assumed from the position indicated by the personality row for all the users 3. From the state in which the position of the user 3 is detected (step S21), the operation for determining who the user 3 is at that position is started. The i-th, here, the first personality row of n persons of the information related to the personality row of the user 3 recognized in the presence is selected (step S22). The nth j-th, here, the first one of the detected positions is selected (step S23). Also, Min (i) is set to the maximum value that can be taken. Then, a distance d (i, j) between the position indicated in the personality row and the detected position is calculated (step S24). The distance d is represented by, for example, a linear sum of a spatial distance (a distance between a location in the sexual activity information and the detection position) and a temporal distance (a difference between the time to go to the location in the sexual activity information and the current time). be able to. In addition, it is possible to use some evaluation function that represents the distance between the sexual information in spatio-temporal and the detection position / time.

  If the calculated distance d (i, j) is smaller than the possible position distance Min (i) (step S25; YES), the determination unit 16 determines the position indicated by the personality row of the i-th user 3. If the jth position matches, the person at the jth position is determined as the ith user 3 (step S26). That is, Min (i) is replaced with d (i, j), and the identification code ID (i) of the i-th user 3 is associated with the variable p (j) representing the user 3 at that position.

  Then, the process proceeds to the position (j + 1) th position which is the next number (j + 1) after the position j (step S27). If the distance d (i, j) is larger than the possible position distance Min (i) (step S25; NO), the position indicated by the personality line of the i-th user 3 and the j-th position do not match. As a result, the process proceeds to the position (j + 1) th position which is the next number (j + 1) after the position j (step S27).

  If the position number j is smaller than n (step S28; NO), the process returns to step S24 and is repeated. Gradually increase the position number and repeat until all the n positions have been confirmed. All positions of the i-th user 3 that is the first user 3 are confirmed.

  When the position number j is larger than n (step S28; YES), the process proceeds to the case of the personality line of the next user 3, that is, the (i + 1) th user 3 (step S29). Similarly, all positions of the (i + 1) th person are confirmed. The number of the position indicated by the personality line is gradually increased until confirmation of all n persons is completed. When the position number i is smaller than n (step S30; NO), the process returns to step S23 and is repeated. If it is larger than n (step S30; YES), all the users 3 have been confirmed, and the personal position determination is completed.

  Although not shown in the flowchart, when the same user 3 is associated with two detection positions, the closer position is prioritized and the other position is associated with another user 3. Alternatively, when it is determined that the user 3 is the same at the two detection positions, the determination result of the personal position of the user 3 may be erased and the personal position may be determined at the last nth. . If there is a corresponding record of another user 3 at either position, the user 3 is associated with the remaining position by the erasing method.

  For all the users 3, the position indicated by the personality row is compared with the detected position, and the determination unit 16 can identify the most suitable user 3 at the position. The determination unit 16 finishes the determination, and the position information storage unit 17 stores the specific user 3 and the position information detected by the person position detection unit 15 together. When a plurality of users 3 are specified from the position represented by the sex act and the detected position, or when there is no particularly close result and the user 3 is not specified, the user 3 is stored as unspecified.

  By memorizing a specific user 3 and its position, it is possible to track the action of the user 3. Although the behavior of the specific user 3 can be tracked, the user 3 only needs to read the identification information when entering the setting area 4 and does not take time. Even if a plurality of users 3 enter the setting area 4 almost simultaneously and become unspecified, or even if the user 3 becomes unspecified due to contact during tracking, the user can be determined by performing personal position determination. 3 can be determined. Furthermore, even when there is an unspecified history, it may be possible to trace the action of the user 3 retroactively from the specified time point.

(Embodiment 2)
FIG. 6 is a block diagram showing a configuration example of the entire behavior tracking system according to Embodiment 2 of the present invention. The behavior tracking system 10 according to the second embodiment has the same basic structure as the behavior tracking system 1 shown in the first embodiment. In the second embodiment, a plurality of sensors 2 are provided, and a sensor position management unit 18 that manages the positions of the sensors 2 is added. In addition, a history record management unit 19 provided with a position information storage unit 17 is provided. In the second embodiment, it is assumed that the user 3 does not have the tag 31 and enters and leaves the setting area 4 by, for example, fingerprint authentication and password input.

  FIG. 7 is an example illustrating a setting area of the behavior tracking system according to the second embodiment. The dotted lines in FIG. 7 show the behavior tracking of each user 3 (user 3A, user 3B). The user 3 can move to the setting areas 41, 42, and 43 adjacent to the setting area 4 through the doors 41D, 42D, and 43D. Sensors 21, 22, and 23 are attached to the setting area 4, particularly at positions where people's movements near the doors 41 </ b> D, 42 </ b> D, and 43 </ b> D can be observed. The behavior of the user 3 when moving to the setting areas 41, 42, 43 can be tracked by the respective sensors 21, 22, 23.

  The behavior tracking system 10 is separately provided with a reading device 32 that reads identification information, and information read by the reading device 32 is transmitted to the identification information reading unit 12 of the behavior tracking system 10 by communication. . Communication may be wireless or wired.

  The determination unit 16 includes an information selection unit 14 therein. Mainly, the information selection unit 14 selects personal information such as the personality line of the user 3 identified by the identification information reading unit 12. The determination unit 16 collates the position of the person position detection unit 15 with the information based on the information.

  The sensor position management unit 18 stores information on the positions of the plurality of sensors 21, 22, and 23. When the setting area 4 has a complicated shape or is wide, one sensor 2 cannot cover the setting area 4 and requires a plurality of sensors 2. The sensor position management unit 18 collates the sensor 2 positions with the setting area 4 of the plurality of sensors 2 placed at various places in the setting area 4. The sensor position management unit 18 can grasp the position of the user 3 in the entire setting area 4 and smoothly track the action of the user 3.

  The history record management unit 19 stores a record related to the action of the user 3 in addition to the record in the position information storage unit 17. A change in position may be recorded with the time and position information recorded in the position information storage unit 17 as the axis. Hereinafter, what captured time and a position with time change is called a locus. In addition, it is possible to record a history of whether or not the personality row in the person information storage unit 13 and the actual action of the user 3 coincide with each other and use it when updating the personality row of the personal information. Further, the behavior history of the unspecified user 3 when the user 3 cannot be identified by the behavior is temporarily stored / saved.

  Even if it is an unspecified user 3, if the user 3 is known from a certain time, it can be understood that the continuous trajectory up to that time is that of the user 3. In addition, it is possible to identify an unspecified user 3 by grasping the overall state of the user 3 (the number of people in the setting area 4 or the like) or specifying other users 3.

  FIG. 8 is a diagram illustrating an example of behavior tracking trajectory data according to the second embodiment. A hyphen in the figure indicates no recorded data. FIG. 8A shows trajectory basic data. The time t when the position is detected by the sensor 2 and the coordinates (x, y) of the detected position at that time are recorded. The trajectory can be extracted by continuously recording the adjacent positions when changing with time. The ID number in the top row of the trajectory basic data is the number indicating the user 3 when the user 3 is specified.

  When the user 3 comes into contact or the like and is present at substantially the same position at the same time and the next adjacent position cannot be captured, recording is performed on the trajectory holding data in FIG. 8B. Since the trajectory A and the trajectory B have the same coordinates at time tn1 in FIG. 8A, the trajectories A and B are recorded in the trajectory hold data as the trajectories X and Y from the next time tn2. . At this time, the continuation of the trajectory A becomes the trajectory X or the trajectory Y, but it is not known which is. By specifying the user 3 from the position represented by the personality line corresponding to the trajectory and determining the corresponding trajectory A and the trajectory X or Y continuing to the trajectory A, the trajectory that was the pending data is also included. , It can be recorded as the history of the user 3. For example, when the personality row of the user 3 having the ID number a is associated with the trajectory A and the trajectory Y, the trajectory A including the recording of the coordinates before the time tn1 and the trajectory including the recording of the coordinates after the time tn2. Y is collected as the locus of the identified user 3 and stored in the history record management unit 19.

  FIG. 9 is a flowchart illustrating an example of behavior trajectory extraction of the operation of the behavior tracking system according to the second embodiment. FIG. 10 is a flowchart showing an example of personal trajectory determination of the operation of the behavior tracking system according to the second embodiment. The behavior tracking system 10 refers to FIG. The user 3 and the setting area 4 refer to FIG. Further, as one of the personality lines of personal information, it is described that the user 3A works in the setting area 42 and the user 3B works in the setting area 43.

  First, presence recognition shown in FIG. 4 is performed. The user 3 existing in the setting area 4 is recognized, and the presence of the user 3 is stored in, for example, the person information storage unit 13 or the position information storage unit 17.

  Next, action trajectory extraction is performed. The person position detection unit 15 receives the information of the sensor 2 and detects the position of the user 3 (step S31), and the position information storage unit 17 temporarily stores the position (step S32). Data increases as time elapses, and it is possible to extract a trajectory indicating the relationship between time and position. The history record management unit 19 extracts a trajectory from the position information storage unit 17 and time data (step S33), and records the trajectory (step S34).

  Next, the personal position is determined. The order in which the information indicating the personality row is selected is assigned to the user 3 as the i-th order, and the number assigned to the trajectory indicated by the number of the users 3 is set as the k-th order. At this time, the specific user 3 can be specified from the i-th.

  There are n users 3 and n kinds of trajectories are extracted. The user 3 can be identified by determining whether all the extracted trajectories are within the threshold of the action range assumed from the position indicated by the personality row for all the users 3. From the state in which the locus of the user 3 is extracted (step S41), an operation for determining which user 3 the locus is is started. The i-th, here, the first personality row of n persons of the information related to the personality row of the user 3 who is recognized in the presence is selected (step S42). Of the trajectories extracted for a plurality of patterns, the nth k-th, here, the first one is selected (step S43). Also, Min (i) is set to the maximum value that can be taken.

  Then, a distance d (i, k) between the position indicated in the personality row and the extracted trajectory is calculated (step S44). The distance d is, for example, a spatial distance (a distance between a location in the sexual activity information and a detection position) and a temporal distance (a value of the sexual activity information) between each position of the trajectory and each location of the sexual activity information. The difference between the time to go to the place and the current time) can be expressed as the sum of the linear sums. In addition, any evaluation function that represents the distance between the sexual activity information and the trajectory in time and space can be used.

  If the calculated distance d (i, k) is smaller than the possible trajectory distance Min (i) (step S45; YES), the determination unit 16 determines the position indicated by the personality row of the i-th user 3. If the kth trajectory coincides, the person who is in the trajectory kth is determined as the i th user 3 (step S46). That is, Min (i) is replaced with d (i, k), and the identification code ID (i) of the i-th user 3 is associated with the variable p (k) representing the user 3 of the trajectory.

  And it progresses to the locus | trajectory of the number (k + 1) following the locus | trajectory k (step S47). If the distance d (i, k) is greater than the possible trajectory distance Min (i) (step S45; NO), the position indicated by the personality line of the i-th user 3 and the k-th trajectory are inconsistent. Then, the process proceeds to the trajectory of the next number (k + 1) after the trajectory k (step S47).

  If the trajectory number k is smaller than n (step S48; NO), the process returns to step S44 and is repeated. Gradually increase the track number and repeat until all n tracks have been checked. All trajectories are confirmed for the i-th user 3 that is the first user 3.

  When the trajectory number k is larger than n (step S48; YES), the process proceeds to the case of the personality line of the next user 3, that is, the (i + 1) th user 3 (step S49). Similarly, all the loci are confirmed for the (i + 1) th person. The number of the position indicated by the personality line is gradually increased until confirmation of all n persons is completed. When the position number i is smaller than n (step S50; NO), the process returns to step S43 and is repeated. If it is larger than n (step S50; YES), all the users 3 have been confirmed, and the personal trajectory determination ends.

  Although not shown in the flowchart, when the same user 3 is associated with two trajectories, the closer trajectory is prioritized and the other trajectory is associated with another user 3. Alternatively, when it is determined that the user 3 is the same in the two trajectories, the personal position determination result of the user 3 may be erased and the personal position may be determined in the last nth. If there is a correspondence record of the other user 3 in one of the trajectories, the user 3 is associated with the remaining trajectory by the erasing method.

  For all the users 3, the position indicated by the personality row is compared with the extracted trajectory, and the determination unit 16 can specify the most suitable user 3 on the trajectory. The specific user 3 determined by the determination unit 16 and the extracted locus and the locus information temporarily stored in the position information storage unit 17 are stored together in the history record management unit 19. When a plurality of users 3 are specified from the position represented by the sexual activity and the extracted trajectory, or when there is no particularly close result and the user 3 is not specified, the user 3 is not specified and the history record management unit 19 Remember.

  By memorizing a specific user 3 and its trajectory, the action of the user 3 can be tracked. Although the behavior of the specific user 3 can be tracked, the user 3 only needs to read the identification information when entering the setting area 4 and does not take time. Even when a plurality of users 3 enter the setting area 4 almost simultaneously and become unspecified, or even when the user 3 becomes unspecified due to contact during tracking, the user's trajectory determination makes it possible to 3 can be determined. Furthermore, even when there is an unspecified history, it may be possible to trace the action of the user 3 retroactively from the specified time point.

  In particular, since the user 3 is specified using the trajectory, the reliability is higher than when specifying using the position. Also, the trajectory itself can be used as action tracking data. By utilizing the data of the trajectory for updating the data of the personality line of the user 3, it becomes possible to track the behavior with higher reliability, and even if the case where the user 3 is unspecified occurs, the user again It is possible to shorten the time until the identification of 3 is performed.

  Information of the user 3 when the position and trajectory represented by the sexual activity are the closest is set, and the determination unit 16 identifies the user 3 in response to an instruction from the control unit 11. The control unit 11 records the record of the specific user 3 determined by the determination unit 16 together with the record stored in the history record management unit 19. When a plurality of users 3 are specified from the position represented by the trajectory and sex, or when the user 3 is not specified, such as none of the users 3, the user 3 is recorded as unspecified. When the number of extracted trajectories is n, individual trajectory determination is performed for each of the n trajectories.

  As described above, according to the behavior tracking system according to the present embodiment, behavior tracking is possible even if the user 3 does not always have a device equipped with a tag or the like. Accordingly, when the user 3 enters the setting area 4, the user 3 only has to perform an authentication procedure at the time of entering the room (for example, pass the entrance card through the reader or hold the mobile phone over the reader). There is no special equipment when moving. Further, as a method for tracking behavior, only position information is required without using a surveillance camera, and privacy can be protected.

  In the present embodiment, the case where the user 3 carries an IC card or a mobile phone when the user 3 enters and leaves the setting area 4 and the case of biometric authentication using fingerprints have been described as examples. The authentication method of the identification information of the user 3 only needs to be able to authenticate the user 3. In the case of biometric authentication, there are various other methods such as iris in the pupil, finger vein, and voice. Further, a combination of several authentication methods such as a method of directly inputting a password to the authentication machine, face recognition and password input, tag 31 and password input may be used.

  In the present embodiment, only the behavior related to the personality of the person is described in the present embodiment. However, the present invention is not limited to the above-described example but can be applied. For example, the position of the seat frequently used by the user 3 may be used as information for specifying the user 3. Information that is frequently used by the user 3, such as the location of a desk in the case of a company and the location of a sofa placed in a living room in the case of a house, can be used as personality information. In addition, when the action tracking of the user 3 is recorded as a trajectory, the moving speed of the user 3 can be made one of personality lines.

  In addition, by keeping the time interval for storing the position information detected by the person position detection unit 15, the action tracking of the user 3 becomes accurate and accurate. When the measurement interval is short, the position information of the user 3 is frequently updated, the predicted action range of the user 3 can be reduced, and the error between the prediction and the actual position is reduced. Is easy to do. In addition, it is possible to measure the gait of the user 3 in detail.

  Furthermore, the past action history in the history record management unit 19 of the user 3 is compared with the personality row recorded in the person information storage unit 13 and the personality row data is updated according to the user 3. Also good. By recording information according to the action of the user 3, the user 3 can be identified more easily. In particular, when there are a large number of users 3 who are subject to behavior tracking, there is an advantage that it is easy to identify the user 3 by reflecting the feature such as the personality line of the user 3 to the position where the feature is finely detected. Further, even when the user 3 cannot be specified, the user 3 can be specified again by the action pattern of the user 3.

  In addition, the sensor 2 is not only high in human detection accuracy but also can be easily installed and convenient by using an infrared sensor. Many infrared sensors have a large sensing distance and sensing angle, and the number of sensors 2 to be used can be minimized. Infrared sensors are highly sensitive to heat, but by using a filter that transmits 6-14 μm of wavelength that matches the human body temperature, even if there are other moving objects, Can only sense. However, the sensor is not necessarily limited to the infrared sensor, and may be an ultrasonic sensor using vibration sensing. An infrared camera may also be used. It is only necessary that individual behavior can be traced without infringing on privacy.

  FIG. 11 is a block diagram showing an example of a hardware configuration of the activity record document creation system 1 shown in FIG. The hardware structure of the activity record document creation system 10 shown in FIG. 6 has the same basic structure. As shown in FIG. 11, the behavior tracking system 1 includes a control unit 21, a main storage unit 22, an external storage unit 23, an operation unit 24, a display unit 25, an input / output unit 26, and a transmission / reception unit 27. The main storage unit 22, the external storage unit 23, the operation unit 24, the display unit 25, the input / output unit 26, and the transmission / reception unit 27 are all connected to the control unit 21 via the internal bus 20.

  The control unit 21 includes a CPU (Central Processing Unit) and the like, and in accordance with the control program 30 stored in the external storage unit 23, the person information storage unit 13, the information selection unit 14, and the person position detection unit 15 of the behavior tracking system 1. And each process of the determination part 16 grade | etc., Is performed.

  The main storage unit 22 is constituted by a RAM (Random-Access Memory) or the like, loads a control program 30 stored in the external storage unit 23, and is used as a work area of the control unit 21.

  The external storage unit 23 includes a nonvolatile memory such as a flash memory, a hard disk, a DVD-RAM (Digital Versatile Disc Random-Access Memory), a DVD-RW (Digital Versatile Disc ReWritable), and controls the processing of the behavior tracking system 1. A program to be executed by the unit 21 is stored in advance, and data stored by the program is supplied to the control unit 21 in accordance with an instruction from the control unit 21, and the data supplied from the control unit 21 is stored.

  The operation unit 24 includes a pointing device such as a keyboard and a mouse, and an interface device that connects the keyboard and the pointing device to the internal bus 20. Personal information, in particular personality information which is one of the personal information, is input via the operation unit 24 and supplied to the control unit 21.

  The display unit 25 is configured by a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display), and displays personal information including a registered person to be detected and a personality line, position information, and the like.

  The input / output unit 26 includes a serial interface or a parallel interface. The input / output unit 26 is connected to a device that reads tag information when the device is not built in the device main body and is attached externally. The input / output unit 26 is connected to the sensor 2 that senses and measures a person.

  The transmission / reception unit 27 includes a network termination device or a wireless communication device connected to the network, and a serial interface or a LAN (Local Area Network) interface connected to them. The transmission / reception unit 27 transmits a behavior-tracked record through the network and receives personality and the like.

  The processing such as the person information storage unit 13, the information selection unit 14, the person position detection unit 15, and the determination unit 16 of the behavior tracking system 1 illustrated in FIG. 1 is performed by the control program 30, the control unit 21, the main storage unit 22, and the external storage. The processing is executed by using the unit 23, the operation unit 24, the display unit 25, the input / output unit 26, the transmission / reception unit 27, and the like as resources.

  Other suitable modifications of the present invention include the following configurations.

About the action tracking system according to the first aspect of the present invention,
Preferably, a person position storage means for storing position information including the location and time of the person acquired by the person detection means,
Trajectory extraction means for extracting a person's movement trajectory from the position information stored in the human position storage means;
With
The determination means compares the movement trajectory of the person extracted by the trajectory extraction means with the information representing the personality line corresponding to the identification code of the person present in the space acquired by the recognition means, The identification code corresponding to the information representing the personality line closest to the movement locus is associated with the person of the movement locus.
It is characterized by that.

  Preferably, the recording apparatus includes a recording unit that records information indicating correspondence between the position information and the identification code determined by the determination unit.

  Preferably, the human detection means includes a human detection sensor arranged for each of the divided locations, detects the presence of a person based on detection information of the human detection sensor, and is stored at a position of the human detection sensor stored in advance. Identify where people are.

About the behavior tracking method according to the second aspect of the present invention,
Preferably, a person position storage step for storing position information including the location and time of the person acquired in the person detection step,
A trajectory extraction step for extracting a movement trajectory of a person from the position information stored in the human position storage step;
With
The determination step compares the movement trajectory of the person extracted in the trajectory extraction step with information representing the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. The identification code corresponding to the information representing the personality line closest to the movement trajectory of the person is associated with the person of the movement trajectory.
It is characterized by that.

  Preferably, the method includes a recording step of recording information representing the correspondence between the position information and the identification code determined in the determination step.

  Preferably, the human detection step detects the presence of a person by receiving detection information from a human detection sensor arranged for each of the divided locations, and detects a person's presence from the position information of the human detection sensor stored in advance. It is characterized by specifying an existing location.

  In addition, the above-described hardware configuration and flowchart are examples, and can be arbitrarily changed and modified.

  The central part of the system for identifying the person whose behavior is to be tracked is composed of the person information storage unit 13, the information selection unit 14, the person position detection unit 15, the determination unit 16, and the like. This can be realized using a computer system. For example, a computer program for executing the above operation is stored and distributed in a computer-readable recording medium (flexible disk, CD-ROM, DVD-ROM, etc.), and the computer program is installed in the computer. Thus, an activity record creation system that executes the above-described processing may be configured. Further, the computer program may be stored in a storage device of a server device on a communication network such as the Internet, and an activity record creation system may be configured by downloading or the like by a normal computer system.

  Further, when the activity record creation system is realized by sharing the OS (operating system) and application programs, or by cooperation between the OS and application programs, only the application program portion is stored in a recording medium or a storage device. Also good.

  It is also possible to superimpose a computer program on a carrier wave and distribute it via a communication network. For example, the computer program may be posted on a bulletin board (BBS, Bulletin Board System) on a communication network, and the computer program distributed via the network. The computer program may be started and executed in the same manner as other application programs under the control of the OS, so that the above-described processing may be executed.

It is a block diagram which shows the structural example of the whole action tracking system which concerns on Embodiment 1 of this invention. It is an example which shows the individuality line of the personal information recorded on a person information storage part. It is a figure which shows an example of the setting area of the action tracking system which concerns on Embodiment 1. FIG. 4 is a flowchart illustrating an example of presence recognition of the operation of the behavior tracking system according to the first embodiment. 4 is a flowchart showing an example of personal position determination of the operation of the behavior tracking system according to the first embodiment. It is a block diagram which shows the structural example of the whole action tracking system which concerns on Embodiment 2 of this invention. It is a figure which shows an example of the setting area of the action tracking system which concerns on Embodiment 2. FIG. It is a figure which shows an example of the locus | trajectory data of the action tracking system which concerns on Embodiment 2. FIG. (A) shows trajectory basic data, and (b) shows trajectory hold data. 12 is a flowchart illustrating an example of behavior trajectory extraction of the operation of the behavior tracking system according to the second embodiment. 10 is a flowchart illustrating an example of personal trajectory determination of the operation of the behavior tracking system according to the second embodiment. It is a block diagram which shows an example of the hardware constitutions of the action tracking system which concerns on embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1, 10 Action tracking system 2 Sensor 3 User 4 Setting area 11 Control part 12 Identification information reading part 13 Person information storage part 14 Information selection part 15 Person position detection part 16 Judgment part 17 Position information storage part 18 Sensor position management part 19 History Records management department

Claims (9)

A storage means for storing an identification code unique to the person and information representing the personality line of the person to be tracked in association with each other;
Recognizing means for acquiring the identification code of a person existing in a limited space of a subject whose behavior is to be tracked;
For each place where the space is divided, a person detecting means for detecting the presence of a person and acquiring positional information representing the place where the person exists;
The position information acquired by the person detecting means is compared with the information indicating the individuality line corresponding to the identification code of the person existing in the space acquired by the recognizing means, and the personality line closest to the position information is compared. Determining means for associating an identification code corresponding to information representing the position information of a person existing in the place;
A behavior tracking system comprising: A person position storage means for storing position information including the location and time of the person acquired by the person detection means;
Trajectory extraction means for extracting a person's movement trajectory from the position information stored in the human position storage means;
With
The determination means compares the movement trajectory of the person extracted by the trajectory extraction means with the information representing the personality line corresponding to the identification code of the person present in the space acquired by the recognition means, The identification code corresponding to the information representing the personality line closest to the movement locus is associated with the person of the movement locus.
The behavior tracking system according to claim 1.   The behavior tracking system according to claim 1, further comprising a recording unit that records information indicating correspondence between the position information and the identification code determined by the determination unit.   The human detection means includes a human detection sensor arranged for each of the divided locations, detects the presence of a human by detection information of the human detection sensor, and at a position of the human detection sensor stored in advance, The behavior tracking system according to any one of claims 1 to 3, wherein an existing place is specified. A recognition step for obtaining an identification code unique to a person existing in a limited space for tracking an action;
A personality line information acquisition step of acquiring information representing a personality line of a person corresponding to the identification code recognized in the recognition step;
For each place where the space is divided, a person detection step of detecting the presence of a person and obtaining position information representing the place where the person exists;
The position information acquired in the human detection step is compared with the information indicating the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. A determination step of associating an identification code corresponding to information representing a close personality line with position information of a person existing in the place;
A behavior tracking method comprising: A person position storage step for storing position information including the location and time of the person acquired in the person detection step;
A trajectory extraction step for extracting a movement trajectory of a person from the position information stored in the human position storage step;
With
The determination step compares the movement trajectory of the person extracted in the trajectory extraction step with information representing the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. The identification code corresponding to the information representing the personality line closest to the movement trajectory of the person is associated with the person of the movement trajectory.
The behavior tracking method according to claim 5, wherein:   The behavior tracking method according to claim 5, further comprising a recording step of recording information representing the correspondence between the position information and the identification code determined in the determination step.   The person detection step detects the presence of a person by receiving detection information from a person detection sensor arranged for each of the divided places, and the place where the person exists from the position information of the person detection sensor stored in advance. The behavior tracking method according to claim 5, wherein the behavior tracking method is specified. On the computer,
A recognition step for obtaining an identification code unique to a person existing in a limited space for tracking an action;
A personality line information acquisition step of acquiring information representing a personality line of a person corresponding to the identification code recognized in the recognition step;
For each place where the space is divided, a person detection step of detecting the presence of a person and obtaining position information representing the place where the person exists;
The position information acquired in the human detection step is compared with the information indicating the personality line corresponding to the identification code of the person existing in the space acquired in the personality line information acquisition step. A determination step of associating an identification code corresponding to information representing a close personality line with position information of a person existing in the place;
A behavior tracking program characterized by running

Images