JP2012099136A - Estimation device and estimation method for number of persons in room - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an estimation device and a method for the number of persons in a room that estimate the number of persons in the room using a low-cost human body detection sensor.SOLUTION: The estimation device includes: a data gathering part 102 which gathers detection states of a plurality of human body detection sensor groups 101 provided in a plurality of areas; first storage means of storing calculation information representing the total number of persons in the plurality of areas, and the maximum number and minimum number of persons in each of the plurality of respective areas; second storage means of storing connection information on connections among the plurality of areas; an update part 103 for the number of persons in the room which updates at least one of the total number of persons, the maximum number and minimum number of persons in a processing object area or adjacent area specified with the connection information through one of movement/joining calculation, separation calculation, generation calculation, and disappearance calculation according to relation between whether a corresponding human body detection sensor responds and the maximum number or minimum number of persons in the adjacent area; and a certainty factor calculation part 104 for the number of persons in the room which outputs the number of persons in the room in the plurality of areas based upon the updated calculation information.

Description

  The present invention relates to a occupancy number estimation device that estimates the number of people in a room and the occupancy status by calculation.

  In the case of performing device control in accordance with the watching of the consumer and the situation, it is necessary to monitor the state such as the position of the consumer. As a method for acquiring position information, conventionally, a method using a monitoring camera, an IR image sensor, a floor pressure sensor, an ultrasonic sensor, a wireless tag, a reader, or the like is known. However, when these advanced sensors are used, there are problems relating to privacy and cost. In relation to this, the following Patent Document 1 describes a technique that uses a pyroelectric sensor and a number detection sensor in combination, and obtains the occupancy status of a person in each area by calculation from information obtained from these sensors. Yes.

JP 2008-77361 A

  However, the technique described in Patent Document 1 has a problem that although it is possible to calculate a rough occupancy status, it is not possible to calculate a more specific number of occupants. In addition, the entrance / exit only considers the passage of one person at the same time in order to detect the number of people, and the cost increases because a new sensor is used.

  The present invention has been made paying attention to the above circumstances, and an object thereof is to provide a occupancy number estimation device and method for estimating the occupancy number by calculation using a low-cost human body detection sensor. It is in.

  In order to solve the above-described problem, a room occupancy estimation apparatus according to an aspect of the present invention includes a collection unit that collects detection states of a plurality of human body detection sensors provided in at least a part of a plurality of areas, and the plurality And a second storage for storing connection information between the plurality of areas, and a first storage means for storing calculation information representing the maximum number and the minimum number of people possible in each of the plurality of areas. Means, each of the plurality of areas as a processing target area, depending on the relationship between the presence or absence of the response of the corresponding human body detection sensor and the maximum or minimum number of adjacent areas specified by the connection information, Execute any one of separation calculation, generation calculation, and extinction calculation to update at least one of the total number of persons, the maximum number of persons in the processing target area or the adjacent area, or the minimum number of persons That the updating means, and output means for outputting the number of people of the plurality of areas based on the updated the calculated information, characterized by comprising a.

  ADVANTAGE OF THE INVENTION According to this invention, the occupancy number estimation apparatus and method which estimate the occupancy number by calculation using a low-cost human body detection sensor can be provided. Specifically, the number of persons in the entire area and the number of people in each area can be obtained from the information of the human body detection sensor.

The figure which shows the structural example of the occupancy number estimation apparatus which concerns on one Embodiment of this invention. The figure which shows an example of human body detection information Figure showing an example of the total number of people Diagram showing examples of maximum and minimum number of people Diagram showing an example of unknown detection time The figure which shows an example of reliability reduction information A figure showing an example of the number of people in the room Diagram showing an example of certainty The figure which shows an example of the connection information between areas Diagram showing an example of the elapsed time Diagram showing an example of transition elapsed time Diagram showing a general-purpose computer device Flow chart showing operation of occupancy estimation device Flow chart showing occupancy update processing Flow chart showing operation procedure of calculation judgment unit Diagram showing a part of the scenario for estimating the number of people in the room Diagram showing a part of the scenario for estimating the number of people in the room Diagram showing a part of the scenario for estimating the number of people in the room Diagram showing a part of the scenario for estimating the number of people in the room The figure which shows the legend of Drawing 16 thru / or 19 Diagram for explaining movement / merging calculation processing Flow chart showing operation procedure of moving / merging calculation unit Diagram for explaining separation calculation processing Flow chart showing operation procedure of separation calculation unit Diagram for explaining generation calculation processing Flow chart showing operation procedure of generation calculation unit Diagram for explaining the extinction process Flow chart showing operation procedure of annihilation calculator Diagram for explaining transition calculation processing Flow chart showing operation procedure of transition calculation unit Diagram for explaining the recalculation process Flow chart showing the operation procedure of the recalculation section Flow chart showing the operating procedure of the occupancy / confidence calculator Flow chart showing the operating procedure of the occupancy calculation unit Flow chart showing operation procedure of certainty factor calculation unit Diagram for explaining the certainty factor calculation unit Flow chart showing the operation procedure of the certainty factor lowering information calculation unit

  Embodiments of the present invention will be described below with reference to the drawings.

  FIG. 1 shows a configuration example of a occupancy number estimation apparatus according to an embodiment of the present invention. A human body detection sensor group 101, a data collection unit 102, an occupancy number update unit 103, an occupancy number and certainty factor. It includes a calculation unit 104, a certainty factor lowering information calculating unit 105, calculation information 106, certainty factor degrading information 107, output information 108, a separation non-detection time 109, and area information 110.

  The human body detection sensor group 101 is a human body detection sensor such as a pyroelectric sensor installed for each area for calculating the number of people, and transmits detected information to the data collection unit 102.

  The data collection unit 102 collects the human body detection information transmitted from the human body detection sensor group 101 and transmits it to the occupancy number update unit 103. An example of human body detection information is shown in FIG.

  The occupancy update unit 103 calculates calculation information 106 that is a base for calculating the output information 108 by using the human body detection information collected by the data collection unit 102 and the area information 110 that is prior information about the area. The calculation determination unit 103a, the movement / merging calculation unit 103b, the separation calculation unit 103c, the generation calculation unit 103d, the annihilation calculation unit 103e, the transition calculation unit 103f, and the number recalculation unit 103g. The calculation determination unit 103a selects one calculation from 103b to 103f, the movement / merge calculation unit 103b calculates the movement and merge of people between areas, and the separation calculation unit 103c calculates the separation of people between areas. The generation calculation unit 103d calculates the increase in the number of people, the disappearance calculation unit 103e calculates the decrease in the number of people, the transition calculation unit 103f calculates the movement of the person to the area where the human body detection sensor is not installed, and the number of people recalculation unit 103g The total number of persons 106a and the maximum and minimum number of persons 106b are recalculated from the situation of the entire area.

  The occupancy / confidence calculating unit 104 calculates the output information 108 by using the calculation information 106 calculated after the execution of the occupant number updating unit 103 and the certainty factor decrease information 107. Unit 104a and certainty factor calculation unit 104b. The occupancy calculation unit 104a calculates the occupancy number, and the certainty factor calculation unit 104b calculates the certainty factor.

  The certainty level decrease information calculation unit 105 is called during the execution of the separation calculation unit 103c, updates the undetected time 109 at the time of separation, and outputs the certainty level decrease information 107.

  The calculation information 106 is information serving as a base for calculating the output information 108. The total number of people 106a representing the number of people in the entire area, the maximum and minimum number of people 106b representing the maximum and minimum number of people possible in each area, and the last. There is an undetected time 106c that represents the time that has passed since the detection. FIG. 3 shows an example of the total number of people, FIG. 4 shows an example of the maximum number of people and the minimum number of people, and FIG. 5 shows an example of the undetected time.

  The certainty factor reduction information 107 is information required when calculating the certainty factor. FIG. 6 shows an example of the certainty factor reduction information.

  The output information 108 is information that is output from the occupancy estimation device, and includes the occupancy 108a and the certainty factor 108b. FIG. 7 shows an example of the number of people in the room, and FIG. 8 shows an example of the certainty factor.

  The separation non-detection time 109 is information serving as a base for calculating the certainty factor lowering information 107.

  The area information 110 is advance information about the area, and the inter-area connection information 110a used for calculation of adjacent areas, the disappearance elapsed time 110b used when determining the disappearance process, and the transition used when determining the transition process. There is an elapsed time 110c. FIG. 9 shows an example of the inter-area connection information, FIG. 10 shows an example of the disappearance elapsed time, and FIG. 11 shows an example of the transition elapsed time.

  The configuration of the occupancy estimation device shown in FIG. 1 can be realized by using a general-purpose computer device as basic hardware as shown in FIG. 12, for example.

  The general-purpose computer device includes a CPU 202, an input unit 203, a display unit 204, a communication unit 205, a main storage unit 206, and an external storage unit 207, and each unit is connected to each other via a bus 201.

  The input unit 203 includes input devices such as a keyboard and a mouse, and outputs an operation signal generated by operating the input device to the CPU 202.

  The display unit 204 includes a display such as an LCD (Liquid Crystal Display) and a CRT (Cathode Ray Tube).

  The communication unit 205 includes communication means such as Ethernet (registered trademark), wireless LAN (Local Area Network), and Bluetooth (registered trademark), and performs communication with the human body detection sensor 210.

  The external storage unit 207 includes, for example, a hard disk or a storage medium such as a CD-R, a CD-RW, a DVD-RAM, a DVD-R, and the like, and includes the above-described data collection unit 102, occupancy number update unit 103, occupancy A control program for causing the CPU 202 to execute processing by the number of persons / certainty factor calculation unit 104 and the certainty factor decrease information calculation unit 105 is stored.

  The main storage unit 206 is configured by a memory or the like, expands a control program stored in the external storage unit 207 under the control of the CPU 202, data necessary for execution of the program, and data generated by execution of the program Memorize etc.

  The occupancy estimation device may be realized by installing the control program in a computer device in advance, or may be stored in a storage medium such as a CD-ROM or distributed through the network. Then, this program may be realized by appropriately installing it in a computer device. In addition, the calculation information 106, area information 110, output information 108, confidence reduction information 107, and separation non-detection time 109 in FIG. 1 are the main storage unit 206 and external storage unit that are built in or externally attached to the computer device. It can be realized by appropriately using a memory, a hard disk or a storage medium such as a CD-R, a CD-RW, a DVD-RAM, a DVD-R, and the like.

  In addition to the above-described components, calculation information 106, area information 110, output information 108, certainty reduction information 107, information stored in the undetected separation time 109, abnormality notification, and the like are printed. A printer may be provided. Further, the configuration of the occupancy number estimation device shown in FIG. 12 may be changed according to the target device for collecting usage status.

  Next, the operation of the occupancy estimation device will be described with reference to the flowchart shown in FIG.

  First, step S301 is started when the power is turned on. In step S <b> 301, human body detection information is collected from the human body detection sensor group 101. In step S302, the occupancy update process shown in FIG. 14 is performed to update the calculation information 106. In step S303, in order to calculate the output information 108, the occupancy / confidence level calculation process shown in FIG. 11 is performed. In order to perform these processes periodically, for example, the process returns to step S301 every second and is repeatedly executed. The process may be terminated due to an abnormality or the like (step S304).

  The operation of the occupancy update unit 103 will be described with reference to the flowchart shown in FIG. By executing step S302, step S401 is started. In step S401, one of all areas is selected, and steps S402 to S407 are executed. In step S402, the process shown in FIG. 15 for selecting one of steps S403 to S407 using the human body detection information, the calculation information 106, and the area information 110 is performed. In step S403, the process shown in FIG. 22 for calculating the movement and merging of people between areas is performed. In step S404, the process shown in FIG. 24 for calculating person separation between areas is performed. In step S405, the process shown in FIG. 26 for calculating the increase in the number of people is performed. In step S406, the process shown in FIG. 28 for calculating the decrease in people is performed. In step S407, the process shown in FIG. 30 for calculating the movement of the person to the area where the human body detection sensor is not installed is performed. In step S408, if selection of all areas is completed, the next step S409 is executed, and if not, step S401 is executed. In step S409, the process shown in FIG. 32 is performed to recalculate the total number of people 106a and the maximum and minimum number of people 106b from the situation of the entire area.

  The operation of the calculation determination unit 103a will be described with reference to the flowchart shown in FIG. By executing step S402, step S2501 is started. In step S2501, if there is a response to the human body detection sensor in the area (selected area) selected in step S401, step S2502 is executed, and if there is no response, step S2503 is executed. In step S2502, an adjacent area having a minimum number of persons of 1 or more is searched, and if there is, the calculation determination process is terminated and the movement / merging process step S405 is executed. Otherwise, step S2504 is executed. In step S2504, the maximum number of people in the selected area is calculated, and if it is 1 or more, step S2505 is executed. If not, the calculation determination process ends and the separation process step S403 is executed. In step S2505, an adjacent area having a maximum number of persons of 1 or more is searched. If there is, the calculation determination process is terminated, and the movement / merging process step S405 is executed. If not, the calculation determination process ends and the generation process step S404 is executed. In step 2503, when the minimum number of people in the selected area is 1 or more and the undetected time has passed the disappearance elapsed time, the calculation determination process is terminated and the disappearance calculation processing step S406 is executed. Otherwise, step S2506 is executed. In step S2506, if the minimum number of people in the selected area is 1 or more and the undetected time has passed the transition elapsed time or more, the calculation determination process is terminated and the transition calculation process step S407 is executed. Otherwise, the calculation determination process is terminated and step S408 is executed.

  Here, for example, a specific procedure for estimating the number of people in the room according to the present embodiment will be described by taking as an example a scenario for estimating the number of people in each room in the 2LDK residential area. This scenario is shown in FIGS. 20A to 20C show human body detection sensors and human legends provided in each room (area). In FIG. 16 to FIG. 19, the not-detected time is not shown.

  The scenario of FIGS. 16 to 19 shows a series of step times (1) to (32) until the total number of people changes from one to two, and then to one again. Specifically, one person (for example, “A”) is already in a room (for example, area L), another one (for example, “B”) comes home, and this B goes out again. is there. For example, it is assumed that A continues to be in area L during this time. On the other hand, B returns home, enters area E (entrance), moves out in the order of areas H → I → L → I → F → B → F → I → H → E. A more specific example of this change in occupancy status is that, for example, A and B are family members, and when B comes home, they turn to Area L (Living) and greet A right now in Area L (step time) (1) to (8)). Then, in area L, A requests usage to B (step time (9)). B accepts this, but the angel decides to go after taking a bath. Then, B moves to area B (bathroom) and bathes (step times (11) to (22)), and then returns to area E without returning to area L (step times (23) to (27)). Go out for use (step times (28) to (32)). So far, A remains in the area L, but is watching TV, for example. For this reason, the human body detection sensor in the area L reacts when A moves a large hand or B enters the room, and the detection interval of the sensor becomes longer.

  In this embodiment, the human body detection sensor does not detect A and B separately. For this reason, A and B are not distinguished in the figure. Moreover, the human body detection sensor is not provided in the area B (bathroom).

  In the scenarios of FIGS. 16 to 19, all of the movement / merging calculation, separation calculation, generation calculation, annihilation calculation, and transition calculation are executed at least once. Hereinafter, specific processing procedures of these calculations will be described, and specific processing procedures will also be described regarding the recalculation of the number of persons, the number of people in the room / confidence level calculation, and the reliability level reduction information calculation process.

  FIG. 21 is a diagram for explaining the movement / merging calculation processing. The operation of the movement / merging calculation unit 103b will be described with reference to the flowchart shown in FIG. Note that FIG. 21 merely helps to explain FIG. 22, and does not correspond to FIGS.

  By executing step S405, step S501 is started. In steps S501 to S502, the undetected time of the selected area is set to 0, and the minimum number of people is set to 1. In step S503, an adjacent area having a minimum number of persons of 1 or more is searched, and if there is, step S504 is executed, and if not, step S506 is executed. In step S504, the sum of the maximum number of adjacent areas having a minimum number of one or more is set as the maximum number of selected areas. In step S505, it is assumed that a person has moved, and the minimum number of people in the adjacent area is set to zero. In step S506, the total of the maximum number of people in the adjacent area is set as the maximum number of people in the selected area.

  FIG. 23 is a diagram for explaining the separation calculation process. The operation of the separation calculation unit 103c will be described with reference to the flowchart shown in FIG. By executing step S403, step S601 is started. In step S601, the certainty factor reduction information calculation processing step S1401 for calculating the certainty factor reduction information using the undetected time at the time of separation is executed. In step S602 to step 603, the undetected time of the selected area is set to 0, and the minimum number of people is set to 1.

  FIG. 25 is a diagram for explaining the generation calculation process. The operation of the generation calculation unit 103d will be described with reference to the flowchart shown in FIG. By executing step S404, step S701 is started. In steps S701 to S703, the undetected time of the selected area is set to 0, the minimum number of people is set to 1, and the maximum number of people is set to 1. In step S704, the total number of people is increased by one.

  FIG. 27 is a diagram for explaining the disappearance process. The operation of the annihilation calculation unit 103e will be described with reference to the flowchart shown in FIG. By executing step S406, step S801 is started. In steps S801 to S802, the maximum number of people in the selected area is set to 0 and the minimum number of people is set to 0. In step S803, the total number of people is reduced by the minimum number of people in the selected area.

  FIG. 29 is a diagram for explaining the transition calculation processing. The operation of the transition calculation unit 103f will be described with reference to the flowchart shown in FIG. By executing step S407, step S901 is started. In step S901, the minimum number of people in the transition destination area is increased by the minimum number of people in the selected area, and in step S902, the maximum number of people in the transition destination area is increased by the maximum number of people in the selected area. In step S903, the minimum number of selected areas is set to zero.

  FIG. 31 is a diagram for explaining the number recalculation process. The operation of the number recalculation unit 103g will be described with reference to the flowchart shown in FIG. By executing step S409, step S1001 is started. If it is determined in step S1001 that the total number of minimum persons is equal to or greater than the total number of persons, the total number of persons is set to the total of the minimum number of persons in step S1002. If the total of the minimum number of people is 0 in step S1003, the total number of people is set to 0 in step S1004. In step S1005, 0 is set when the total number of people is a negative value. In steps S1006 to S1008, one area is selected from all areas, and step S1007 is repeated for all areas. In step S1007, the maximum number of people in the selected area is set to the sum of the total number of people—the minimum number of people + the minimum number of people in the selected area.

  The operation of the occupancy / confidence calculator 104 will be described with reference to the flowchart shown in FIG. By executing step S303, step S1101 is started. In order to calculate the number of persons and the certainty factor for each area, in steps S1101 to S1104, one area is selected from all areas, and steps S1102 to S1103 are repeated for all areas. In step S1102, step S1201 is executed to calculate the number of people in the room. In step S1103, step S1301 is executed to calculate the certainty factor.

  The operation of the occupancy calculation unit 104a will be described with reference to the flowchart shown in FIG. By executing step S1102, step S1201 is started. In step S1201, if the minimum number of people in the selected area is 1 or more, the number of people in the room is set to the maximum number of people in the selected area (step S1203). If not, the number of people in the room is set to 0 (step S1202).

The operation of the certainty factor calculation unit 104b will be described with reference to the flowchart shown in FIG. By executing step S1103, step S1301 is started. In step S1301, step S1303 is executed when the minimum number of people in the selected area is 1 or more, and step S1302 is executed otherwise. In step S1303, when n is the total number of people, m is the sum of the minimum number of people, h is the maximum number of people in the selected area, and P (n, k) is a permutation, the certainty factor is P (n−m, hm) / Calculate as ^mn-m . This considers the probability that the remaining number of people nm is greater than the maximum number of people when it is distributed to possible locations with duplication allowed. In step S1302, the certainty factor is calculated using a function that monotonously increases according to the undetected time. When the undetected time is 0, the certainty factor is 0, and when the undetected time is the certainty level decrease information, the certainty factor is 1.

  As a monotonically increasing function, for example, as shown in FIG. Alternatively, a monotonically increasing function may be a sigmoid function. Alternatively, as shown in FIG. 36 (b), a step function that keeps the certainty degree 0 and suddenly becomes 1 may be used.

  The operation of the certainty factor lowering information calculation unit 105 will be described with reference to the flowchart shown in FIG. By executing step S601, step S1401 is started. In step S1401, the non-detection time of the selected area is added to update the separation non-detection time 109. In step S1402, the distribution of the undetected time at the time of separation is obtained from the information on the undetected time at the time of separation 109, and the reliability decrease information is calculated based on this distribution. As an example of the calculation, a value that covers 99% of the undetected time is set as the certainty factor decrease information, the average value is set as the certainty factor decrease information, and the median value is set as the certainty factor decrease information.

  According to the embodiment of the present invention described above, it is possible to provide a occupancy number estimation device and method for estimating the occupancy number by calculation using a low-cost human body detection sensor. Specifically, using the number of people in the entire area, the maximum and minimum number of people in each area, and the time that has elapsed since the human body detection sensor was in the undetected state, the number of people in each area and the certainty factor can be output. The total number of people in the target area and the number of people in each area can be obtained.

  Note that the present invention is not limited to the above-described embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

101 ... human body detection sensor group;
102: Data collection unit;
103 ... Number of people updating in the room;
103a ... calculation judgment part;
103b ... movement / merging calculation unit;
103c: separation calculation unit;
103d ... generation calculation unit;
103e ... annihilation calculation unit;
103f ... transition calculation unit;
103g ... Number of people recalculation part;
104 ... Number of people in the room and certainty calculation section;
104a ... Number of people in the room calculation section;
104b ... certainty factor calculation unit;
105 ... confidence reduction information calculation part;
106 ... calculation information;
106a ... Total number of people;
106b ... maximum and minimum number of people;
106c: Undetected time;
107: Decrease in certainty information;
108 ... output information;
108a ... Number of people in the room;
108b ... certainty factor;
109 ... Undetected time during separation;
110 ... area information;
110a ... Inter-area connection information;
110b ... disappearance elapsed time;
110c: Elapsed transition time

Claims (5)

A collecting means for collecting detection states of a plurality of human body detection sensors provided in at least a part of the plurality of areas;
First storage means for storing calculation information representing the total number of people in the plurality of areas and the maximum number of people and the minimum number of people possible in each of the plurality of areas;
Second storage means for storing connection information between the plurality of areas;
Each of the plurality of areas is a processing target area, depending on the presence or absence of the response of the corresponding human body detection sensor and the maximum number or minimum number of adjacent areas specified by the connection information, movement / merging calculation, separation calculation, Update means for performing either generation calculation or extinction calculation to update at least one of the total number of persons, the maximum number of persons in the processing target area or the adjacent area, or the minimum number of persons,
An occupancy number estimation device comprising: output means for outputting the occupancy number of the plurality of areas based on the updated calculation information.   The apparatus according to claim 1, wherein the update unit further executes a transition calculation for detecting a transition to an area where the detection state of the human body detection sensor cannot be obtained and updating the calculation information. Further comprising a certainty factor calculating means for calculating the certainty factor of the number of people in the plurality of areas,
The apparatus according to claim 1, wherein the output unit outputs the number of people in the plurality of areas together with the certainty factor. Further comprising a certainty factor lowering information calculating means for calculating certainty factor lowering information based on the distribution of the undetected time of the human body detection sensor,
4. The apparatus according to claim 3, wherein the certainty factor lowering information is used for calculating the certainty factor. A data collection unit collecting detection states of a plurality of human body detection sensors provided in at least a part of the plurality of areas; and
The first storage means stores calculation information representing the total number of people in the plurality of areas and the maximum number of people and the minimum number of people possible in each of the plurality of areas;
A second storage unit storing connection information between the plurality of areas;
Each of the plurality of areas is a processing target area, and depending on the presence or absence of the response of the corresponding human body detection sensor and the maximum or minimum number of adjacent areas specified by the connection information, movement / merging calculation, separation calculation, An update unit that performs at least one of the total number of persons, the processing target area or the adjacent area, or the minimum number of persons by performing either generation calculation or extinction calculation; and
An occupancy number estimation method, wherein the output means outputs the occupancy number of the plurality of areas based on the updated calculation information.

Images